Idea Transcript
Generating Look-alike Names via Distributed Representations Abstract—Motivated by applications in login challenge and privacy protection, we consider the problem of large-scale construction of realistic-looking names to serve as aliases for real individuals. We seek these look-alike names to preserve name characteristics like gender, ethnicity, and frequency of occurrence while being unlinkable back to the source individual. We introduce the technique of distributed name embeddings, representing names in a high-dimensional space such that distance between name components reflects the degree of cultural similarity between these strings. We present different approaches to constructing name embeddings, and evaluate their cultural coherence. We demonstrate that name embeddings strongly encode gender and ethnicity, as well as name frequency.
I. I NTRODUCTION Names are important. The names that people carry with them are arguably the strongest single facet of their identity. Names convey cues to people’s gender, ethnicity, and family history. Hyphenated last names suggest possible marital relationships. Names even encode information about age, as social trends alter the popularity of given names. That names serve as people’s primary societal identifier gives them even more power. Privacy requirements often make it undesirable or even illegal to publish people’s names without their express permission. Yet there are often technical contexts where we need names which can be shared to represent things: to serve as placeholders in databases, demonstrations, and scientific studies. In this paper, we consider the problem of constructing realistic-looking names on a large-scale to serve as aliases for real individuals. The task here is more subtle than may appear at first. We might consider randomly assigning names from reference sources such as telephone books, but these are actual names and hence violate privacy concerns. We might consider generating names at random from component first/last name parts. But these fake names will not respect gender, ethnicity, and temporal biases: consider the implausibility of names like “Wei Hernandez” or “Roberto Chen”. When replacing names to anonymize a medical study, dissonance is created when female names are replaced by male ones, and the names of elderly patients aliased by newly coined names. Our interest in generating look-alike names arose through a computer security application: how might an email user who lost their password be able to convince the account provider of their identity as part of account recovery process, or as part of the second-login challenge? We reasoned that the genuine account holder should be able to distinguish the actual contacts they have corresponded with from a background of imitation names (Fig. 1). But this is only effective when the background
Fig. 1: Three contact list based challenges using the technique proposed in this paper. In each challenge only one contact is real.
names are culturally indistinguishable from the contacts, a property which did not hold under naive name generation methods. Otherwise, the correct answer might stand out and hence be easily guessed by an attacker who tries to take control of user accounts. For example, consider an example challenge question asked to a hypothetical user, wendy wong@, given in Table I (left). If background names are generated naively without preserving ethnic properties (right), guessing the correct answer becomes much easier. However, when the generated names preserve ethnic and cultural properties of the real contacts that they replace (middle), the guessing task for attacker remains hard, because the imitation names look very similar to the real contacts. TABLE I: A security challenge question: “pick someone you contacted among the following”. Left: the contact list of a hypothetical user wendy wong@. Middle: a replacement list generated using the technique proposed in this paper (retaining one real contact Charles Wan). Right: a naively generated random replacement list. Real Contacts Angela Chiang Paresh Singh Charles Wan Yuda Lin Lin Wong Tony Kuang Hua Yim
Proposed Challenge Amanda Hsu Nirav Sharma Charles Wan Joko Yu Hua Li David Feng Jie Fung
Naive Challenge John Sander Steve Pignootti Charles Wan Jeff Guibeaux Sam Khilkevich Mary Lopez Ron Clemens
The major contributions of our work are:
•
•
•
Generating realistic replacement names through name embeddings – We propose a new technique of representing the semantics of first/last names through highdimensional distributed name embeddings. By training on millions of email contact lists, our embeddings establish cultural locality among first names, last names, and the linkages between them, as illustrated by examples in Figure II. Through nearest neighbor analysis in embeddings space, we can construct replacement aliases for any given name which preserve this cultural locality. Gender, racial, and frequency preservation through name embeddings – Through computational experiments involving ground truth data from the U.S. Census and Social Security Administration, we show that our name embeddings preserve such properties as gender and racial demographics for popular names and industrial sector for corporate contacts. Even more surprisingly, our embeddings preserve frequency of occurrence, a property that to the best of our knowledge has not been previously recognized in the distributed word embedding community. Establishment of ethnic/gender homophily in email correspondence patterns – Through large-scale analysis of contact lists, we establish that there is greater than expected concentration of names of the same gender and race for all major groupings under study.
B. Data Sources and Preparation In this section, we introduce the datasets that are used in this study, as well as a detailed description about our data preparation process. Data Sources. Datasets employed in our work are: • Contact Lists– This set of data, here after referred to as the contact lists is a proprietary sample of contact lists from 2 million distinct Yahoo email users. The length of each contact list varies from 1 to 21, because longer lists have been truncated. Names in each contact list are ordered by contacting frequency/recency. A much larger set of contacts for around 1 billion Yahoo users are available to us and the results using this larger set is very similar to those from the smaller set. Therefore in this paper we present all our results based on the smaller set. Each entry of a list is a full name but not necessarily a human name. To preserve the privacy of users, the owner associated with each contact list was not available in the data. • Census 1990 [2]– The Census 1990 dataset is a public dataset from US Census website. It records the frequently occurring surnames from US Census 1990. This dataset contains 4,725 popular female names and 1,219 popular male names. • Census 2000 [3] – The Census 2000 dataset is another public dataset from US Census website. It contains the frequently occurring 151,672 surnames from US Census 2000. Associated with each name is a distribution over six categories of races. The races are: White, Black, Asian/Pacific Islander (API), American Indian/Alaskan Native (AIAN), Two or more races (2PRACE), and Hispanics. In this paper we refer to the races and ethnicity interchangeably. The ethnicity distributions of Census 2000 and Contact lists data are given in Table III. Data Preparation. The contact lists data records the social interaction of email users. These contact lists include substantial noise in the name fields. Artifacts include omitted names [4], sometimes marked by an arbitrary string like “zzzzzzzz”, or names that are meaningful but clearly not human, like “Microsoft”, “Facebook”, and “GEICO”. Moreover, many names in contact lists data are partial, with only the first name or the last name present.
II. B UILDING NAME E MBEDDINGS A. Methodology We seek to construct a list of background names that looks very plausibly real, even though they are machine generated. One way to create such a list is to start from real contact names, and replace each one with a look-alike names of the same gender, ethnicity and name frequency. However this approach requires multiple complex components, including reliable ethnicity and gender classifiers. Instead we propose to do aways with these complex steps by deriving the signals directly from a large amount of data, through name embedding. In our approach, each name, first or last, is embedded in high dimensional space as a high dimensional vector using word2vec [1]. Our hypothesis (verified in Section III-C) is that people have a tendency to contact people of the same ethnicity and gender. Consequently, when using the contact lists of millions of users as a text corpus, the resulting embedding of names would capture this tendency by placing names of the same gender and ethnicity close-by in the highdimensional space. For each real name in the contact list, we can then choose a name near it in the high dimensional space. The resulting replacements should have good gender and ethnicity similarity to the original names (Table I (middle)). Furthermore, it turns out that in aggregate, the name frequency of the look-alike names also resemble that of the real names very well.
C. Word2vec Embeddings The word2vec software [5] is an efficient tool to learn the distributed representation of words for large text corpus. It comes with two models: the Continuous Bag-of-Words model (CBOW) and the Skip-Gram (SG) model. The CBOW model predicts the current word based on the context while the SkipGram model does the inverse and maximizes classification of a word based on another word in the same context [6]. We start our analysis by using the cleaned contact lists and the word2vec software [5]. Each contact list is treated as a sentence, and together they form a text corpus. Unless
2
NH
DUNG
UONG
AHMET THANH
NGOC
HIEN
ROBBIE
GALEN
ADAMA RANDALL
RANDAL
CLAY
THOM
DEWEY BUBBA
SCOTTY
CHIP
BJ
KIP
RANDY
CHET
DALE
SHAWN
TOD
VERN
RODGER
RUSTY
JONATHON
SCOT
CURT
DUANE WES
PRESTON
ABDOULAYE
AMADOU
TREY
CHANCE
THAD
ROBBY
DUSTY
ABDOUL
MAMADOU KIRBY
JJ
DALLAS
AS
VU
MOUSSA
JD
CAL
OLA
MUSA
DARBY
ZANE
DEL
BABA
HOA
MURAT
MIKEL
RASHAD
YUSUF
MEHMET
HUY
BASIL
ABDOU
ISSA
BRADFORD
KAREEM
CH
KALA KHANH
TODD
ROBB KURT
LOREN
BRYAN JED
MITCH
SHANE
MATT
RUSS
ERIC
PJ JON
SCOTT
JEFF
GREGG
DEREK
WILL
KARL
SKIP
RYAN
JASON
MATTHEW
MaleTRAN names 1th NN 2nd NN 3rd NN 4th NN 5th NN Female names 1th NN 2nd NN 3rd NN 4th NN 5th NN NICK H BUCK TIMMY CHARLEY LANE MAT WOODY DOYLE TOMMY GREG BRIAN TIM CARY DAN WALT DOUG SEAN MARTY Andy VAN Andrew REESEBen Chris Brian DONNIE Steve Adrienne Allison Aimee Amber Debra TIMOTHY RICK CRAIGAmy NICHOLA BUDDY GRADY BUD WARD NIK CHAU MIKE DENNY REED NGUYEN Dario Pablo Santiago Federico Hernan Diego Aisha Aliyah Nadiyah Khadijah Akil Aliya NORM MARLIN BUZZ DICK DAVE BUTCH JAY BILLY BO TATE KEVIN CHRIS CLARK KENNY AN Isaiah CHRISTOPHER UNG STEVE Elijah JoshuaPIERCE Jeremiah Bryant Brandon Brianna WALLY BrittanyCHUCK BrianaBOB JIM Samantha DEAN Jessica Christina ANH TOM BOBBY JIMMY JEFFREY HANK MITCHELLFernando DONNY TUCKER Rafael BAO COACH TREND ROB Christy Felipe Rodrigo Eduardo Ricardo Candy Connie Becky Angie Cindy HAI CARTER TED SHAN BILL ELLIOTT DON MARK WIL Clint NASH Heath JERRY Brent ChadREID Brad JARRETT Brett Chan LOWELL Wong Poon Ho Wai Yip STEVEN MICHAEL GREGORY MA PARKER SMITH COOPER YEN BA GARY BARRETT RON NED GENE JAMES DANNY Hilton Xooma Eccie Erau Plexus Gapbuster Cheyenne Destiny Madison Brittany Taylor Kayla PATRICK MAJOR LARRY MARSHALL BENNY FOSTER HI HARRISON SGT ED KEN THOMAS GRIFFIN JACK RICH KEITH HERB DC LEW Isaac Samuel Israel Eli Esther Benjamin Dominque Renarda Lakenya Lakia Lashawna Shatara JOHNNY PORTER SAM HAL REX TEDDY JOHN SULLIVAN BROOKS HONG LT DENNIS TERRY ROBERT NEAL Jamal Jameel KareemELLIS Anmar Khalifa Nadiyah Ebonie MICKEY Lakeshia Tomeka Ebony Latasha Shelonda HOMER EDDIE BENNETT FRED SAMMY RUSSELL STEPHEN CLIFF MILLER LEWIS COL BRUCE DAVID COLEMAN RUSSEL Lamar HARRIS Terrell Derrick EboniEVERETT Tyree Willie Florida Fairfield CHARLIE Integrity Beacon Southside Missouri REALTOR BART STAN FRANKIE CAMPBELL WILLIAM PAUL PHIL TOBY BERT CARL LEE CAPT ON WAYNE MOORE Mohmmad BAKER MORRIS Mohammad Shahed Ahmad Rifaat Farishta Gabriella Daniella Vanessa Marilisa Isabella Elisa HILL PHILLIP PERRY STU RICKY GLENN WALKER SONNY ESQ ROYCE ART BARNEY DONALD MD RICHARD CHIEF Moshe Yisroel Avraham Gitty Rivky Zahava JEFFERY Giovanna Giovanni Elisa Paola Giuliana Mariangela WRIGHT ONG CPA BARRY HALL LONNIE BERRY DAVIS RONNIE KJ LES MACK GERALD HAROLD SAMMIE Rocco Vito JONES Salvatore Vincenza Pasquale Nunzio Han Jin Yong Sung HuanPETE JOE Teng PHD BURT GEORGE ANTHONY CAPTAIN UNG GEN GLEN ADAMS VANCE BROWN JACKSON CHARLES BERNIEJunko ARNIE Salvatore Pasquale Nunzio Gennaro VitoVIRGIL DARRELL Tommaso Kazuko Keisuke Yumi Yuka Tomoko SID ALVIN ROGER DARYL RONALD JOSEPH PRESIDENT ATTORNEY JAE RIC ALBERT DEWAYNE Thanh Minh JOHNSON Thuy Thao Ngoc Khanh Keren Ranit Galit Haim Zeev Rochel GERRY ARNOLD ADDISON AJ LOU LELAND KENNETH FRANK MINH
QUANG
HOANG
REP
MURPHY
FATHER FR
MBA
BRO
CHEF
COUSIN
GRAY
TEACHER
UMAIR
AUNTY
SIS
MOTHER
TEE
QUEEN
ANJALI
PAPA
JUSTFAB GLOBALCASHCARD
BOSE INTUIT
AARP
BARNES
SLM
KOHLS
EBAY DELL
CANON RAKUTEN
REBTEL
CENTURYLINK
SAFECART
EBUYER
GAP
MIN
ATT
CUSTOMINK LENOVO
SERGIU
EASY RITE
MARIN
TOBI
CONSTANTIN
AKIN
VIOREL
CIPRIAN
ACASA ALINA
AURELIA
LAI
JIN
MING
RIO VIDA
ADV
JU ADAIR
LU
ADEMAR
CHEN
ALESSANDRA
AFONSO
AILTON
AIRTON
ADRIANE
ADO
NAIARA
ALDA
JEANE
DIONE
MARLI
VERA
SNIA
FTIMA
YANG
TAN
LCIA
VNIA
ROSNGELA
YARA
ONG
CHONG
WAN
NUR
NIKO BELLA MARKO SANJA MIRJANA
BRIGID
HORACE
FABIENNE
SBASTIEN
CHRISTOPHE
RUDOLPH
AURELIE
LUDOVIC
FABIEN
YANN
ROMAIN
MATTHIEU
AMANDINE
MARINE ARNAUD
AGNS
CABINET
AGENCE
AMLIE
AMELIE
FRANCIS
SALOME
ADELA
RIAN
GRACE
ANI
JOSEPHINE
WINNIE
VIVIEN
IVY
STEFANIE
ILONA
FLORA
ARON
JONAH
KATERINA
ARI
ELLY
CARLENE
DEMETRIA
LASHONDA
KATINA
D LATANYA
LATONYA
TIARA
LATRICE
LATOYA MARQUITA
VALENCIA
TAMEKA
KEISHA
MARVA
DIONNE
JAMILA
DANITA FELECIA
LAWANDA
TOYA
VONDA
MATTIE
LILLIE
ROSALIND
ROSLYN
MILLICENT
PAULETTE
MAXINE
PATRICE MONIQUE
MAMIE
CHANTE NICOLETTE
BETTYE
FREDA
NATASHA BETTIE
BLANCHE
ELOISE
LADO LENORA
SAUNDRA
BONITA
LAVERNE
VERNA
GERMAINE
TAMAR
VELMA
ROCHELLE
DELORES
DELORIS
HENRIETTA
SYBIL
SHELIA
JOHNNIE
ERNESTINE
CONSTANCE
SHANI
RABBI
AVI MIKA
BENITA
GWENDOLYN
ROSALYN
CATRINA
FELICIA
SHONDA
RENITA
LULA
PORTIA
ANIKA
AVIS
GEORGETTE
MOSHE
MIKI
JEWEL
CLAUDETTE
IRA
KEREN
MIRA
SUZETTE
SHARLENE
ELLIOT
ELI
RONI
RALF
NORBERT
MANFRED
OTTO
INGA
BESSIE
MISHA
INNA
ZINA YANA
MIKHAIL
YELENA
OKSANA
FLORIAN
GIL
PERCY MARLON
MILTON
MARICEL
ROMY
ELMA
KATYA
WILSON
VIRGILIO
SASHA
KAROL
EDY
EDI
HERMES
ADAN
AIDE
NUBIA
ELIEZER
RAFAEL
CINTHYA
SOCORRO
NIDIA
LUZ
OLGA
LEONOR
GLADYS
VIOLETA
FABIOLA ELIAS
JOSU
HOMERO JOS
BRAULIO EDGARD HUMBERTO
MARCO
EDMUNDO
MISAEL
CORINA
CARMEN
MOISES LINO
FIORELLA
MIGDALIA
NYDIA
ZOILA
MARITZA
LISSETTE
GIULIANA
JULISSA
MIRIAM
3
TERESITA
ROSA
LOURDES
AMALIA AURORA
MIRNA
HAYDEE ELSA
ROSALIA
ELVIRA
HILDA BERTA
JUANA
HIRAM
JOSELYN
YESSENIA
CONSUELO
ELEONORA VALENTINA
MARISOL
MAYRA
MARIBEL
ESPERANZA IVONNE
AMELIA
VIVIA
ALICIA
STUDIO
YADIRA
CA
SABRINA
ANGELICA
GEORGINA VIRGINIA DOLORES
ARIANA
ROXANNA
GILBER RUDY
RENE
ALEXIA
NORMA ESTELLA LIZETTE
JAZMIN BERTHA
CELESTE
ROXY
GLORIA MARTHA
EDITH
PAU
PATRICIA
MONICA
VERONICA DIANA
YESENIA
VANESSA
ANDREA SANDRA
DAISY
DENISSE
PRISCILLA
ERIKA
EMANUELA
GENESIS ILIANA
KARLA
ESTRELLA
DAVIDE
STEFANIA
LUCA
LESLY
JACQ
LILA
DI
CHIARA
GIULIA
ANTONELLA
LISETTE
GERALDINE
MASSIMO
FEDERICA
YANIRA
ANNALISA
FRANCESCA
ALESSIA
STEFANO
IVETTE
VICKY
BEA
RICCARDO
FABRIZIO
GIOVANNA
DAMARIS
MYRNA
IRENE
EVA
ANGELINA
FRANCESCO
GIUSEPPE
LILLIAN JANETTE
LUCY
MATTEO
GIOVANNI
ZAIDA
ZORAIDA
MIRTHA
FLOR
DELIA
GIANCARLO
YANET
ELBA
ROSITA
ILEANA
ISAIAS
BELKIS
REINA
ROXANA
MOISS
ARIANNA
MAURIZIO
ENZO
MILAGROS
ZULMA NILDA
DORA
LUIGI
GIANNI
MAGALY
NELLY
GLADIS
ESTHER
VINCENZO
ENRICO
PAOLO
LORENZO
GIANNA
LAR FRANCES
LYDIA
ROSIE
STELLA
SALVATORE
GIORGIO
XIOMARA
MARLEN
CARLO
GIAN
ELY
DANIA
JACKELINE
ELENA
SOFIA
HEIDY
KATTY
CARMELO
VITO
ANGELO
ANNA
YVONNE
SYLVIA
LOLA
CARMINE
GINO
CARMELA
INDIRA
LISBETH
SINDY
YULIANA
LINA
CLARA
FRIDA
REBECA
PEDRO
JOHANA
JANETH
AURA
AMPARO
WILMER
RONY
LEIDY
LUISA
ALBA
GILBERTO
FREDY
YENNY
MERY
KENIA
RAFA
LVARO
DEISY
LEYLA
EVELIN
ELOISA
HERNANDO
LIDA
DALILA
ANY
YANETH
ROSANNA
BELINDA
ELLE
GRACIE
ROCCO
DINO
GABBY
KASSANDRA
DOMINICK
LILLY
LILY
NINO
ENA
JOHANNA
EVER
JHON
CAMILO
WILFREDO
FREDDY
SAL
ATHENA
NELDA
DESIREE
MYRA
JUANITA
MARISSA
CECE
CRISTY
VINNIE
ARIANNE
MANNY
DALIA
ASTRID
JOSIE
INEZ
SUSANNA
YOLANDA
CARISSA
ANNAMARIE
YVETTE
ERICKA
THELMA
NELLIE
GIGI
VINNY
LOUIE
DINA
INGRID
EDWIN
CRISTHIAN
DAYANA
SORAYA
ALE
JHONNY
JAIRO
NATALY
ELVIN
LIZA
TITO
WILLY
EDDY
ELVIS
DARWIN
ALIDA
MARIANNA
DANIEL
WALTER
ORLANDO
DIMAS
MIRELLA
EDISON
ELMER
LANI
RICO
SUZAN
MINNIE
RUBY
CARMELITA
TESS
NOEL
MARLYN
LOLITA
GIA
JAYSON
REY
IDA
LEILANI
SHIELA
ROMEO
REYNALDO
RICHELLE
JOCELYN
LITA
ROMMEL
ERWIN
LEO
ERVIN
FRANKLIN
NELSON
ROBINSON
JENIFFER
GABRIELLA
SERGEY
OLEG
MARILOU
FE
CORA
RHEA
FERDINAND
CLEO
MANUELA
MIA
EVANGELINE
ROWENA
JUN
ARNEL
GABRIELE
ALLA
TATYANA
IRINA
NADJA
JOJO
SHERWIN
MATHIAS
LENA
ERMA
gender gray. Overall names of the same gender form mostly contiguous regions, indicating that the embedding correctly capture gender information by placing names of the same gender close-by. Figure 2 (right) is an inset showing a region along the male/female border. We can see that “Ollie”, which is considered a predominantly female name per Census data (2:1 ratio of female/male instances), is placed in the male region, close to the male/female border. Per [9], we found that “Ollie” is more often a male name, and used as a nickname for “Oliver” or “Olivia”. Hence our embedding is correct in placing it near the border. The embedding also correctly placed “Imani” and “Darian”, two names not labelled by the Census data, near the border, but in the female/male regions, respectively. Per [9], “Imani” is a African name of Arabic origin, and can be both female and male, mainly female; “Darian” can also be female and male, but mainly male, and
PIETER
STEFAN
NATALYA
GALINA
STEFANY
STEPHANY
ALDO
PALOMA
KENYA
LATASHA
LATISHA
LAKEISHA
JOI
ANTOINETTE
EZRA
VIOLET
CORINNA
ALENA
SVETLANA
RONNY
MILA
ISIS
ADOLFO
TANISHA
TAMIKA
LAKESHA
AYANNA
SHANTEL
RACQUEL
CHARMAINE
ANNMARIE
BEATRICE
PIA
HELGA
JANINA
ANASTASIA
LARISA
AIDA
ABELARDO
LAMONT
OCTAVIA
CHARISSE
DAHLIA
EDMUND
ANGELINE
MICHAELA
DARIA
BORIS
DANIELLA
ABEL
ALTHEA
KARLENE
ISAAC
ASA
JULIET
otherwise stated, all results in the paper are based on the CBOW model with the default word2vec parameter settings (see Section II-D for comparison of different models and ways of constructing the corpus). The output of word2vec is a dense matrix of dimension 517, 539 × 100, with each unique name represented as a row of the matrix. Embedding Visualization. To understand the landscape of the name embeddings, we visualize the names as a 2D map. We used the stochastic neighborhood embedding [7] to reduce the original 100-dimensional embedding to 2D. We assign
ADA ABRAHAM
LETITIA
SHANICE ANGELLA
ERROL
EUNICE
JUDE
EMMY
VIKTOR
MICHAL
VLADIMIR
ISABELLA
DAMION
WINSTON
SAMUEL
CHARLY
CHRISTIN
EWA
VITA
LIANA
TYRONE
JERMAINE
DEON
CARINE
SHELDON
LAURE
EMMANUEL
MATILDA
DONOVAN
THEO
CHRISTELLE
BATRICE
TOMS
MARTIN
LASHAWN
ROOSEVELT
AURLIE
LAETITIA
JULIAN
DAMIAN
NICOLAS
REGINALD
VON
DION
NACHO
NORBERTO
FRANCO
SEBASTIAN GUIDO
OLIVER
ELINA
ANDREY
EMI
AQUEL
MAURA
CHAR
MATHILDE
LE
SIDNEY
HANNA
FILIP
ARA
LIA
LETICIA
BEV
MAUD
VERONIQUE EMMANUELLE
ELODIE
MAMAN
KRISTIAN
VERONIKA
IRENA
PAVEL
ROMAN
NGLICA
HERV
TERRENCE
DANTE
MARTN
EMILIANO
DOUGLAS
ANDERS
MAREK
BEATA
MAGDALENA
DRI
BARB
PEG MARGE
DELPHINE
CCILE
SANDRINE VIRGINIE
JULIEN
MME NORA
SUE CATHIE
MARIBETH
KARIN
KATARZYNA KAROLINA
BRIL
MAR
FABRICE
ANGE
JESS
RODERICK
OLLIE
CARLTON
DOT
CATHI DEB
FEDERICO
FACUNDO GASTON
WESLEY
KAI
DIAN
ELA
ANCA
MAY
ELENI
KASIA
PIOTR
DELINA
MANOLO
NURIA JORDI
MAITE
ZULEMA
GEORGIA
BUNNY
GERRI LUANNE
STPHANIE
GUILLAUME
LAURENT
GRISELDA
GEMA
MARCUS LEI
SABINA
ELIZA
PILAR
FABIN
GERMN
MARU
VERO
CHRISTEL
FRANOISE VALRIE
CLINE
OLIVIER
THIERRY
DELLA
PATTIE
S
BRIDG
MARTINE
ANNICK
VRONIQUE
SEBASTIEN
PHILIPPE
FRDRIC
BILLIE MERRY
BOBBI
CYNDY
JANIS
KATHI JOANIE
ANGELIA
TIERRA
NAKIA
LUANN
JUDIE
JEANMARIE
FRANCOISE
PASCALE HLNE
REMI
STPHANE
FREDERIC
PASCAL
EDIE BETTE
PAT
MARYLOU
ROSEANN
EMILIE
LAURENCE MICHLE
NATACHA
MLANIE
GRARD
JEANMARC
STEPHANE
BERTRAND FRANCK
DEBBY PATTI
KATHIE JUDI
JAN
SANDIE
ROSANNE
MURIEL
CECILE
CELINE NATHALIE
ISABELLE
SYLVIE
JEANPIERRE
FRANOIS
JEANLUC
HERVE
DIDIER
FRAN JEANNE
MARYELLEN
BRIGITTE
PEGGY
GINNY
JUDY
LOIS
GERI CATHLEEN
LAKISHA
LELA
TASHA
KISHA
EBONY
IMANI
KESHA
TERRELL
DARNELL
MARILYNN
TRUDY
SANDI
DOTTIE
SANDY
BONNIE
ELLEN JOAN
MARYANN
ALICE
ANNIE
FLORENCE
GILLES
BENOIT
YANNICK
JESSY
MARIELLE
LUCIE
MANON
MARYSE
SYLVAIN MATHIEU
ETIENNE MAXIME
CHRISTIANE
DANY
MAGALI
ALAIN
ADRIEN ADELINE
AUDREY
ESTELLE
TERRANCE
NAN
DEBBI
GAYLE
KATHY
BETSY
DIANE
JOANN
COLLEEN
MARYBETH
SOPHIE
DESMOND
BOBBIE LORENE
KITTY
MAURICE
POLLY
KAY
VICKI PAM
LYNN
MARGIE
CAROL
KATHLEEN
JEANIE
CONNIE LIBBY
SUSIE
DEBBIE
CATHY
PATTY
MARY
CORRINE
MEG
TABLE III: Ethnicity distribution of Census 2000 data and that of intersected names between the contact list and Census 2000 data. The label information comes from Census 2000.
GORAN
SAT
VCTOR RUBN
JULIN
DARIO
CLAUDINE
CHANTAL
FRANCE EVELYNE
JEANCLAUDE
YVES
RPONDRE
MARCEL
MYRIAM
LULU
ROSY
PATY
MARGOT
ALIX
JULIETTE
CINDY
PENNY GALE
GAIL
BARBARA
EVIE
EILEEN
MARYANNE
MADELEINE NADINE
CAMILLE
SACHA
JEANNIE
DORI DIANN
PHYLLIS
DONNA
LINDA
SUSAN
NANCY
MARILYN
GLENNA
CINDI
BETH
DENICE
MARSHA BETTY
CHERYL
JANET
KAREN
GAY
MERCY SEBASTIN
NICOLS HORACIO
RAL
IGNACIO
SANTIAGO
HERNAN PABLO
HERNN
MATAS EZEQUIEL
YAN
ANETA
SANTA
GONZALO
SILVINA
ARIEL
MARIANO
NICO
JING
ALEKSANDRA
BILJANA
MARCIN
NESTOR
ESTEBAN
FLORENCIA
VANINA
MATIAS
PACO
GINETTE
ODETTE
GENEVIVE
LUC
JEANPAUL
DENIS MICHEL
JOELLE
JOCELYNE
JACQUES
HENRI DIMITRI MIREILLE
JACKY
FANNY
LETY
LUPITA
AIME
ANNEMARIE
HELENE
ELISABETH
LISE
PIERRE SERGE
XAVIER REN
NENA
IMELDA RUBI
NAYELI
SELENE
MONTSERRAT
ROCO
MICHELINE
FRANCOIS
ARLETTE
CHRISTIAN
ROSALINDA
ISELA XOCHITL ITZEL
PEPE
PAULINA
ARMAND
EMILE
GEORGES
AXEL
LUPE
CRISTAL
MARICELA
BETY ARIADNA
GABY
RAMN
IVN
ELIE
CLAUDE
VALENTINE
BERENICE TERE
ANGELES
CORINNE
FRANCINE
JOSETTE
CYRIL
LIONEL
JOHANNE
REMY
ANAIS
LETTY
ELVA
ESMERALDA
PERLA
GUADALUPE
MARICARMEN IRVING
SAUL
URIEL
HCTOR
ALEXIA
ESTELLA
LIZETTE
BERTHA
MINERVA
ELIA
OFELIA
EFREN
RAYMUNDO LALO
ISRAEL
JACOBO
TOMAS
AGUNG
MARIJA
TA
AGNIESZKA
FABIAN
VANESA
ROMINA YAMILA
ANALIA
MAXIMILIANO
ESTUDIO
CARO
MATEO
GUILLERMO
NANA
NORMA
ANGELICA
YAZMIN
ARACELI
NOE GENARO
ULISES
MAVIS
DOMINIQUE
ANTOINE BERNARD
HUBERT
RENE
KAYE
FAYE
ANN
JOYCE
NOREEN
DEXTER
CARROLL
MITZI GAYE
TIANA
JADA
RAVEN
KESHIA
NIA
JASMINE
ISAIAH
SHAY
NELL
JANIE
MARTI
LYNNETTE
KIANA
AYANA
KIA
YAEL ANDI ANETTE Census ContactJOSEF lists ANNIKA2000 TALIA LUKAS ELISSA BERNICE NICOLLE PEARL CO each SARI name toELANA a cluster using gender/ethnicity ground truth, SOPHIA ALBERTA LARS SUSANNE ILANA RUDI ETHEL INA Races Count Percentage Count Percentage ERICH CECELIA RISA JENS DARA EDWINA ANTON STEPHAN ILENE MAYA KERSTIN SELINA BRITTA and created the maps using gvmap [8]. KIKI VIOLA White RA 115,167 0.8593 12,837,406 JRGEN 0.7428 JOHANNES KIMBERLEE HAZEL ROZ LORNA SONJA ADAC ELISHA DAVINA BIRGIT ANYA ANDREAS 544,983 Black 5,262 ANJA 0.0393 0.0315 SVEN ROLF FRITZ RINA RACHEAL ZALANDO RENA CHRISTOPH MARKUS ROLAND ADEL STEFANI ALEX DAPHNE DINAH TANJA FRANZ Figure 2 (left) illustrates the landscape of first names. This KATJA KATRIN APIJOVAN 6,100 0.0455 KATHARINA1,323,888 0.0766 JANA LIZZY NITA WOLFGANG CHERRY TOBIAS RIA JOHANN PHOEBE ALEXANDER MARLENA ELLA ALEXA LJ HANS AIAN 268 0.002 19,272 0.0011 SABINE visualization establishes that the embedding places names of JANEEN RENATE GRETA TATJANA DIETER EDEN BELLE AGATHA AGNES ALEXIS SU SUSANNAH BERND NAOMI MAJA ALEXANDRA 2PRace MARTINA131 0.001 7,934 0.0005WERNER CHER PETRA ANGELIKA PENELOPE KELI male NIKIcolor the same gender close-by. Using Census data, we MATTHIAS KATARINA GERHARD JOHAN ANNABELLE RONA NONA CATE MA Hispanics 7,089 BETTINA0.0529 HEIKE 2,548,329 0.1475 LEA THEA RAINER DIRK MONIKA NINA JESSIKA ELKE names femaleRHODA names pink, and names with unknown ILSE orange, AILEEN MAE DAGMAR17,281,812 KLAUS Total IVA 134,017 SERENA DANICA JASMIN ANNABEL HILDE INGE URSULA CARIN
ARIS
VESNA
NOELIA MICAELA JESICA
CP
JOAQUIN
EDGARDO
CRISTIAN
EDITH
REYNA LILIA
ROCIO ROSARIO
ROGELIO
RUDY
CHANEL
TYRA
DARIUS
DEMETRIUS
GENIE DIXIE
JERRI
SALLIE PATSY
LAURI
SHERYL
BEVERLY CAROLYN
JANICE
JUNE
LENORE
JEANINE
MAUREEN
REBA
GINGER
JONI
JEROME
DIANNE
SUZANNE JEANNINE
DOREEN
CORNELIUS
REGGIE
RUTHIE
DEE
TERRIE
VICKIE SHERRY
CHERI
CARYN DEBI
SHARON
SHIRLEY
LEONA ANNETTE
MARGO FERN
THERESE JOANNE CAROLE JANINE
COOKIE
JERI TERRI
MELODY
RANDI TERI
ALYCE
DARLENE LORETTA JACKIE
CHARLENE ANITA
MIMI
LYNNE
MARIANNE
LORRAINE
MARION
NOLA
DANNA
SHERRIE
SHERRI
DEENA JACKI
MARLA
BECKY
DOROTHY SUZI
LYNDA
MARGARET
CHARLOTTE
COLETTE ELISE
BARBRA
RHONDA
TAMMY
DIANNA
DENA
SHERI
CHERIE
MARCY
GWEN SHARRON
DEBORAH SUZY
SALLY
JANE
ROSEMARY CHRISTINE ANNE
JEAN
MARIE
TONI
SHEILA
LUCINDA
ELEANOR HELEN
CLAIRE CAROLINE CATHERINE
LOUISE
GENEVIEVE
KELVIN
TISH
TAMMIE
LANA
GENA
QUINCY
BONNY
MALINDA
LORRI
MARCIE
MARCI
DEANNE
LAUREL
DEBRA
THERESA
ELYSE
FAY HARRIET
JAYNE
EVE
JUSTINE
JULES
MICKI SHELLY
LINDY JODY
LORI SHARI
LAURIE
TRISH
SUZIE
VIKKI
SHARYN
PAULINE
MARGUERITE
LUCILLE
GERARD
CEDRIC
BRICE GILBERT
ROXANNA
MARISELA
ELVIA ARACELY
DULCE
LUCERO
ARTURO
SALVADOR
OCTAVIO
OMAR
JAZMIN SARAI
ALMA
AZUCENA
REYES
ELISEO ISIDRO
GERARDO
ENRIQUE
LIZBETH
IRMA
BLANCA
AMERICA
CRUZ
BENITO JESUS ELOY
RUBEN
GERMAN
MAXI
DEWI BUDI
DIDI
NIKOLA
SAN
MICA
AGUSTINA
CONSTANZA
PATRICIO
AGUS
PT
JELENA
ING LIC
AMA
INDRA
ATTY
NIA
ARQ
SOLANGE
KATIA TELMA
LEDA
YESENIA
YESSICA
LIZETH
ALONDRA
EFRAIN
ARNULFO FIDEL
CRISTOBAL
JAVIER
JUAN
ARIANA
NANCI
GUY
GEORGINA VIRGINIA DOLORES
GLORIA MARTHA
DENISSE YADIRA
IVONNE MIREYA
ROSALBA
HERIBERTO
JAIME
HECTOR
JUSTINA XIMENA
MACARENA
PAZ YANINA
MELISA
JOSI
MARIBEL
ESPERANZA MARGARITA
SUSY
AMADO
ARMANDO
RAUL
RAMIRO
ANIBAL
MELINA
DANI
DESI
KUYA
TA
MARLY
ILIANA MAYRA
MARISOL
CONSUELO
MARILU
RIGOBERTO
EDGAR
MIGUEL
ERNESTO
EMILIO
DAISY
MARLENE
CELESTE ROXY
DIANA
VALENTINA GENESIS
KARLA
JUANA
ESTRELLA NOEMI
ELDA
JOSUE
ALFONSO
OSCAR DOMINGO
LORE
SOLEDAD
ELVIRA
ANGEL
MANUEL ROLANDO
ANDRS
SOFA
JIMENA
BELEN
ANABELLA FLORES
LIVIA
WEN
LAZADA
DEJAN
ROMERO
LUCI
CRIS
YESICA JULIETA
HERNANDEZ EUGENIA
TORRES
BERTA
LOURDES
ERICK
ALONSO
GREGORIO
LUIS
ANDRES
AGUSTN CATALINA
MONICA VERONICA
EMANUELA
ELEONORA
JOSELYN
YESSENIA
MAGGIE
WENDY
JACQUIE
MARIETTA ANGELIQUE
DAMIEN QUENTIN
PARIS
AL
ALESIA KIARA
ELIJAH SADE
Fig. 2: Visualization of the name embedding for the most frequent 5,000 first names from email contact data, showings a 2D projection view of name embedding (left). The pink color represents male names while orange denotes female names. Gray names have unknown gender. The right figure presents a close view along the male-female border, centered around African-American names.
PAK
MAS
KA
N
GOMEZ
RODRIGUEZ DIAZ
GONZALEZ
HILDA TERESITA
FELIX
VICTOR
JOSE
ALEJANDRO ALEJO
ADRIN
MARIELA
ROSALIA
ANABEL
ISMAEL
AURELIO
IVAN
MARIO
ALFREDO
ALEJANDRA AGUSTIN ESTEFANIA
MARIANELA
TATI
ISABELA
CRISTIANA
LING
CHE
SITI
BU
HMAN
PEREZ
EVELINE
MARCELLE
LIANE
WALLACE
KAK
BOY
MILENE
LIN
ANDRA
SOL
KARINE CAMILLA
RIKA
JUSSARA
ELSA MIRIAM
ROSA
AURORA
LAZARO
RAMON
LEONEL
JORGE ALVARO
VIVIANA
SANCHEZ
JULISSA HIRAM
CHRISTIANA
FLIX ELIO
OSVALDO
ALBERTO
CECI
MIRTA
MARIEL
CARMEN DELIA AMALIA
MARCELINO SANTOS CESAR JULIO LEOPOLDO
EUGENIO
BIBIANA LILIANA
MALENA
CORINA
MOISES LINO
VICENTE
CARLOS HUGO
ROQUE GUILLERMINA
GRACIELA EVANGELINA
MARTINEZ GARCIA
EDMUNDO
FAUSTO FRANCISCO
RODOLFO
ANAHI
CECILIA LUCRECIA
LOPEZ
MISAEL
BRAULIO
OSWALDO CSAR
ROBERTO SERGIO
GUSTAVO
JONATAN
MERCEDES
LUNA
MARCO
HUMBERTO
JOS
ANTONIO
FERNANDO
MAURICIO DIEGO
SUSANA
ESTELA
GISELA
MARITA
LISETTE
YANIRA
LESLY
MIRNA
HAYDEE
FLOR
ROXANA JOSU
EDGARD
HOMERO
PEDRO RICARDO EDUARDO
GABRIEL
PAOLA
MATILDE
JOSEFINA
ELIAS
ISAIAS
GILBERTO
RAFAEL LVARO
EMANUEL
VERNICA
MNICA
MARA
LUCILA
MABEL CAROLA
RAFA
BERNARDO
GILDA ROSSANA
BEATRIZ CAROLINA
LORENA
INES
FAMILIA
LISSETTE
REINA
ELBA
ROSITA
ILEANA
STEFANIA
LUCA
IVETTE
MILAGROS
MIRTHA
NILDA
GIULIANA
MARITZA
ZOILA
GLADYS
ZULMA
DORA
LESLIE
DENISE JO
VAL
ROSEMARIE DOLLY
ELAINE
ROBERTA MARCIA
MARNIE
MICHELE
CLAIR
FLO
ROSALIE MARCELLA
RITA
PAULA
BERNADETTE
MARJORIE
ARLENE
ROSE
REGINA
CARLA
SABRINA PATRICIA
LIZ
LYN
RUTH JUDITH
ARLEEN
LORAINE
ENID
VIVIAN PRISCILLA VANESSA
KIT
RAE
CAREN
MADELYN
BRENDA
JEANNETTE
JACQUELINE
ALICIA
SANDRA
BARBIE
SONDRA CHARLA
AUGUSTINE
TAMI
KARI
JODI DARCY
JILL
COLEEN
WILLIE
DERRICK
ANGIE
CANDY
ROXIE
RONDA
TAMMI LORA
MISSY
KATI GRETCHEN
MINDY
JOLENE
DAWN
LORRIE
ROBIN RENEE
KARYN
VALERIE
LEIGH PAMELA ANGELA
CYNTHIA
MADELINE
EVELYN
IRIS
GERALDINE
AMELIA
ANDREA
ERIKA
HEIDI
DEANNA
KWAME
JENNY
JEANETTE
LORIE NANETTE
TERESA MILLIE DORIS
MILDRED
MYRNA
GINA
KATHERINE ELIZABETH
LAURA
WILMA ELSIE
LILLIAN
VICKY
LILA
DI
STUDIO
GIULIA
CAREY
CATIE
MOLLIE LEEANN
HOLLY KRIS
STACY KELLEY KIM
HOLLI
CYNDI
DANETTE
JANEL
TRISHA
JAMIE
HEATHER
TRACY SHELLEY
JULIE TINA
KERRY
CAMI
ANGI
BECKIE
JACQUE SHELLI
KARRIE
DEEDEE
GAYLA BECKI
SHELLIE CARI
CHRISTY
KERRI
CARRIE
TRICIA
KELLY STACEY
DANA LISA
MELINDA
JENNIE
JULI
LESA
DARLA
TORY
LEANN SHAWNA
KRISTI
KARIE
KRISTIE
SHANNON
AMY
TARA
SHAUNA
JANNA
ROXANNE
KERI
KRISTA
KRISTIN
KATIE
ERIN
JEN
JENNIFER
MICHELLE
CHRISTA
KELLIE
KARA
KRISTEN
MOLLY
JENN
KATHRYN REBECCA MELANIE
MELISSA
CHRISSY
MEGAN
CARA
LAUREN EMILY LEAH
KATY
STEPHANIE
JESSIE
SARA
GLENDA JULIA MELBA LARA
FRANCES
JANETTE
LUCY
BEA
FRANCESCA
ALESSIA CHIARA
DAVIDE FEDERICA
VICTORIA
JOANNA
ANNA
YVONNE
LYDIA ROSIE
IRENE
ANNALISA
MATTEO
RICCARDO STEFANO
ANTONELLA
OLIVIA
MYRA
BELINDA ELLE
SYLVIA
KOFI
EVA
ANGELINA
MASSIMO
FRANCESCO
GIUSEPPE GIORGIO
FABRIZIO
WANDA
SUSANNA
JUANITA ATHENA
NELDA GABBY
GRACIE LOLA
ESTHER ARIANNA
MAURIZIO
GIANNI
LUIGI
STELLA
GIANNA
SALVATORE VINCENZO
PAOLO
GIOVANNI GIOVANNA NYDIA
YOLANDA
CARISSA MARISSA
DESIREE KASSANDRA
DOMINICK
LILLY ROCCO CARMINE
ENRICO
ENZO FIORELLA
ZAIDA MIGDALIA
DAMARIS
THELMA
NELLIE
CECE
CRISTY VINNIE
VINNY
VITO
ANGELO
CARLO
ANNAMARIE
GIGI
JOSIE
SAL
LILY DINO GINO
CARMELA
GIAN
GIANCARLO
UCHE
GLADIS LEONOR
RICO ARIANNE
NINO ROSANNA
LORENZO
RUBY
CARMELITA
LANI
LIZA JAYSON
LOUIE MANNY
ELY
YANET
ZORAIDA
NELLY
LUZ OLGA
VIOLETA
GIA
LEILANI
TESS
LITA
NOEL
MARLYN
REY
CARMELO
DANIA BELKIS
MAGALY
BRENNA
LINDSAY MEGHAN
JACLYN
RACHEL
JANELLE
NICOLE
JESSICA
DANIELLE
JILLIAN
MEAGHAN
SARAH
KIRSTEN
SAMANTHA
NATALIE
ERICA
MICHEAL
SYLVESTER
JACI
RENAE TRACI
DANELLE KELLI
JENI
STACIA
TAMRA
TRACIE
JAMI
MELODIE
DEANA
LYNDSEY
HILLARY
DEANN
JAYME
MANDI
STACIE
KRISSY KRISTY
LINDSEY
KATELYN
JEANA
JOHNNA
STACI
KACIE
SADIE BROOKE MALLORY
KAITLIN
CAITLIN BRIDGET
JULIANNE
JENNI
KRISTINE
RACHELLE
KRISTINA
NOELLE
CHRISTINA
GABRIELLE
KANDI
HOLLIE
JEANNA
CORI
CHRISTIE
BETHANY
REBEKAH
DARCI
CRISTIN
TANA
CHRISTEN
LEXIE
LAYNE
MINDI
JANELL SHELBY
TRISTA
CASSIE
MACKENZIE
KIRSTIN JENNA
CARLY
LYNDSAY
RACHAEL
MANDY
NICKI JODIE
SHAYNE
KATE KAT
LISSA JULIANNA
GENEVA INEZ
KELSIE
JESSI
CARLEY
PAIGE
KAITLYN
MADDIE
CAITLYN
QUINTON
AJA
CIERRA
MYLES
CONRAD
KENDRICK
JARVIS
TERA
MISTI
CHRISTI
KAYLEE
BECCA
BREANNE
JAIMIE
HANNAH SKYE
STEPH
ROBYN
HILARY
ELLIE
MADDY SERENA
YVETTE
ERICKA
KASEY
EMILEE HALEY
KYLEE
TORI
KELSEY
MEAGAN
KRISTYN
WENDI
ANDIE
RHIANNON
TESSA
KERRIE
CATE CARIN
SUZAN
KAYLEIGH
LEANNE
LEEANNE
KATHARINE
CATHRYN SUZANNA
SUSANNAH PENELOPE
KELI
JESSIKA
MINNIE
CORRIE
TRACEY
KYLIE
HAYLEY
CHLOE
ALISON
ADELE
PHOEBE
MARLENA JANEEN NIKI NINA MIA LOLITA
JOCELYN
SHIELA
ROMEO
ROMMEL
DINA DALIA
INDIRA
XIOMARA
CIARA
JADE
KIMBERLEE STEFANI
LIZZY
GRETA
ANNABEL IDA
COLLETTE
SOPHIA
SELINA DAVINA
RACHEAL
JANA
ALEXIS NONA
THEA
JASMIN
RICHELLE
LISBETH
JACKELINE
MARLEN
ELENA
SOFIA
FABIOLA
MOISS
ELIEZER
PALOMA
LETICIA RAQUEL ESTER
ELISA MARIA
CLAUDIA
INS
LILIANE
ROSILENE MARLIA RICA
ANY
ANGLICA
ANA
ANTONIA
ISABEL CELINA
MARCELA
SILVIA
MARTA
VALERIA
NATY
SU
NURUL NOR
MB
FER
KARINA
LUCIA
GABRIELA
MARIANA
MARISA
MONI CARINA
RAISSA
LVIA NGELA
ANGELITA
EDNA
CELIA
SONIA MARI
ELIDA LIDIA
CRISTINA
DANIELA
NATALIA
VALE
EMA
CLARA
FRIDA
REBECA
SOCORRO
CABAAS
WANG YU
NG
LILI
LUIZA
JOANA
GISELLE
NATALI
IVANA
CLAU
IZABELA TNIA
WEI
TATIANA
MARINA
REGIS
AURA
AMPARO
CINTHYA
EVELIN
DALILA
ELOISA
IKE RHEA
MARILOU
FE FERDINAND
REYNALDO TITO
ENA ASTRID
JOHANNA
HEIDY
KATTY NIDIA
ELISHA
DINAH ALEXA
ALEXANDRA
LEA
KIMBERLEY
TANYA
NATASHA
SASHA
ALBERTA
ETHEL
VIOLA
NAOMI
DANICA
CORA
TAMARA
CHANTELLE
NICOLETTE
BETTIE
BESSIE
ERMA CECELIA
SONJA
ALEX ALEXANDER
ELLA
LJ CHER
RHODA
SAUNDRA
BETTYE
FREDA
BLANCHE BERNICE EDWINA
HAZEL
LORNA
DAPHNE
NITA
RONA
ROWENA
JUN
ARNEL
MARICEL ERWIN VIRGILIO
INGRID
SINDY
YULIANA
LINA
LUISA
ALBA KENIA
SORAYA
ALDO
ALE
JOHANA JANETH
ROMY
WILLY
EDDY ELVIN
WILFREDO
WILMER
RONY
FREDY
LEIDY YENNY
MERY
KAYODE
JOSEFA FRANCISCA
TANIA
ISA
VILMA
EMILIA
ADRIANA
MARTINS
MILENA
JOSIANE
ARIANE
FELIPE LILIAN
MAGDA
LIGIA
SILVANA
LAS
GISELE
JANANA
KAMILA
RODRIGO
MIRIAN CINTHIA
MAIRA
ELIANA
ROSANA
LUDMILA
RAFAELLA
ISADORA
AUREA
ANNY AUGUSTO
HELLEN
LEONARDO
CLAUDIO
SAMANTA
DAIANA
FLAVIA BRBARA
DBORA
LUCIO
MAURO
SILVIO FABRICIO
MARCELO
ROSI
CINTIA
CAMILA
NATHALIA
NATLIA
CATARINA
RUI HELENA
LI
LUCIANA FERNANDA
MARCOS
FLAVIO
DANILO
LUCIANO LEANDRO LUCAS FABIANA
RAPHAEL
MARGARETH
FLVIA
JULIANA
LISANDRA
REINALDO
DEISY
MAMIE
ELOISE
ROCHELLE
BONITA
LAVERNE VERNA
PEARL
DARA ROZ
RENA
EDEN
MAE
EVANGELINE
KAYLA HAILEY
LEXI
MIRANDA
BRIANNE
DAYNA
KIRA
LEISA
BRANDIE
HALLIE JENA
OTIS
CLARENCE
CANDI
SHEA
MALIA
PATIENCE
JORDYN
COURTNEY NIKKI
TARYN
SYDNEY
LACY
MACY MISTY
CASSIDY CALLIE
CORTNEY
CHELSEY
KARISSA
NICHOLE
ELAINA
KYRA
ASHLEIGH
KYM
SHANNA
BROOK
LACEY
KACEY
KENDALL
KYLA
SHAYNA
HOPE FAITH JOY
KENDRA
JENIFER
SHAINA
KIMBERLY
JACQUELYN
SHEREE
LYNETTE
JOLIE
JENELLE FARRAH
SHANA
CANDACE
CANDICE KATRINA
ROBBIN
WILFRED
DELORES
DELORIS
HENRIETTA
SYBIL
GERMAINE
ELISSA
RISA
ILENE ANYA
JOJO
MATHIAS
CLEO ELMA
GIL LEO
DANIEL
ELVIS
FREDDY EVER
YANETH
HERNANDO
MONIQUE TALIA
ELANA
CHERRY BELLE
ANNABELLE
AILEEN
FLORIAN
GABRIELE MANUELA
WALTER
EDWIN
CRISTHIAN
JHON
CAMILO
MAXINE PATRICE
SHANI
RABBI
RIA
JOHAN
STEFAN
NADJA
ERVIN
ELMER ORLANDO DARWIN
JHONNY
ALIDA
NUBIA LIDA LEYLA
ISIS ADOLFO
ABRIL ADRI
ARNALDO
VIVI
DIMAS
PERCY MARLON
FRANKLIN
NELSON
EDY
MIRELLA
JAIRO
NATALY DAYANA
AIDA AIDE
MILTON
KATYA WILSON
EDI
EDISON
HERMES
MARIANNA
DANIELLA
ADAN
ZINA YANA
OKSANA
SERGEY
OLEG
ROBINSON
STEFANY
JENIFFER
GABRIELLA ADA
LENA
NATALYA
TATYANA MIKHAIL
YELENA
IRINA LARISA
RONNY
MILA
STEPHANY
KAROL
ADELA
ABELARDO
ALCIDES
KEILA
SUSI
MISHA
ALLA INNA
GALINA
ARA ANI BORIS
VITA
VLADIMIR
EMI
ISABELLA
ABRAHAM
OTTO
INGA
ANASTASIA
ALENA
SVETLANA
VIKTOR
MICHAL
ANDREY
ROMAN
LIA
ADALBERTO
ITALO CIRO
GIOVANI
GERSON
OSMAR
FABIO
MARCELLO RENAN
MAICON
BRUNO
SUELLEN DEBORA
NATHLIA
TULIO
GILMAR
EMEKA
KATERINA ELINA
EWA
ELA
PAVEL
SUNDAY
LIANA
ABEL
PAULETTE
GEORGETTE
KIKI RINA
AGNES
ILSE SHERWIN
HILDE PIETER
MIKAYLA
CASSANDRA
CHANTEL BRIDGETTE
SHEENA
MORGAN
TAMERA
CALVIN
JULIUS
DEDE
SHARLA
KALI
WHITNEY
CHELSIE
MARIAH KRYSTLE
CRYSTAL TIFFANY
SONYA
VALARIE
MICHELL
TEENA
LEANNA SHANDA
CHELSEA
KOURTNEY
KRISTAL
SELENA TRINA
TONYA
TONJA TONIA DEIDRE
LENORA
CHEYENNE
KORI
RIKKI PEYTON
ASHLEE
BREANNA
TABITHA
KRYSTAL
CHRYSTAL
CHRISTAL
CATRINA
LADONNA
VELMA
ASHLY KAMI KEELY
MCKENZIE
TAYLOR
MAKAYLA
TABATHA
CASANDRA
TISHA TIFFANI
CHANDA
DEIDRA DANITA
VONDA SHELIA JOHNNIE
CHARITY PAGE
BREE
SUMMER
MADISON
BRANDY
BRANDI
BRITTANY
BRITTNEY
CHASITY
BRIANNA
DESTINY
BRITTANI SHAYLA
BRIDGETT
KATINA
FELICIA
MATTIE
ERNESTINE
CONSTANCE
JANAE
LELA ANGELIA
FELECIA
SHONDA BENITA
LILLIE
ROSALIND
BRITNEY
BRIANA ARIELLE
TIFFANIE
TIANA
JADA
KENYA
DEMETRIA
LATONYA
LAWANDA
GWENDOLYN
ROSALYN
TASHA
LATASHA
LASHONDA
LATRICE
RENITA
LULA
PORTIA
TIERRA
NAKIA
TANISHA
LATISHA
TIARA
MARQUITA
TOYA
ILANA
ROLAND JOHANN
AGATHA
INGE
LATANYA VALENCIA
JAMILA
ROSLYN MILLICENT
CLAUDETTE IRA
SARI
FRITZ FRANZ
HANS
DIRK
NORBERT
LAKESHA TAMEKA
JEWEL
ANIKA
TAMAR
YAEL
MAYA
ROLF
WERNER GERHARD
RAINER
KLAUS
MANFRED
MOSHE
AVI
STEPHAN
SVEN TOBIAS
DIETER MATTHIAS
RALF
HELGA
JANINA
SHAY
LAKISHA
TAMIKA
LAKEISHA
JOI
LATOYA KEISHA
DIONNE
AVIS
KISHA
EBONY
IMANI
LASHAWN
ROOSEVELT
LAMONT
RAVEN
KESHIA
NIA
KESHA
TERRELL
REGINALD
OCTAVIA AYANNA
SHANTEL
SCARLETT CHANDLER
CRISSY
SAVANNAH
SKYLAR
APRIL
AUDRA
ALYSIA
MARLO
FREDRICK
SAGE
LIZZIE
BRI
REAGAN
ASHLYN
ASHLEY
ALONZO
GUS
GORDON
STEWART
DORIAN
LAMAR
BENNIE
JACINTA
MUM
NICKY
ASHLIE
AUTUMN
BAILEY
AMBER
ALISHA
ADRIANNA
TOSHA
STARR
JASMINE
KATH
EMMA
ASHTON
AUBREY
AMANDA
ALYSHA
ANISSA
JAZMINE KIANA
ISAIAH
LLOYD
TOMMIE
JIMMIE
ALEC
GARTH
LOUISA
ZOE AVA
AVERY ALISSA
ALYSON
ALLISON
ALYSSA
ALYCIA
ALEXANDRIA
FELICITY
ALLAN
HENRY
GEMMA
CLARE
AMIE
ANDY
ALLIE
PRINCE
ALESHA
ALESIA KIARA
CIERRA
AYANA
KIA
ALISA
FIONA
VIVIENNE
LESLEY MOIRA
ALLI
ADRIENNE
ADRIA
ELIJAH SADE
CHANEL
TYRA
DARIUS
DEMETRIUS
DARNELL
TYRONE
LETITIA CHARISSE
MARVA
ANTOINETTE
KEREN
MIKA
NICOLLE
JOHANNES
MARKUS
WOLFGANG
ELKE
DAGMAR
URSULA
ELENI
MAREK
BEATA
PIOTR
KATARZYNA KAROLINA MAGDALENA
ELIZA
BIANCA CLARISSA
ADRIEL YURI
FILIP SABINA
MARCIN
SAT
ADELINA ADRIAN CRISTINE
ABNER
IVO
JRGEN CHRISTOPH
BERND
HEIKE
BETTINA ILONA
DARIA
QUINTON
CORNELIUS
TERRANCE
SUZETTE
SHARLENE
ELLIOT
ELI
RONI
MIKI
ERICH
JENS
BRITTA ANDREAS KATHARINA RENATE
ANGELIKA
MIRA
JOSEF
LUKAS
SUSANNE
BIRGIT KATRIN
ARI
ELLY
PIA
CORINNA
KARIN
LARS KERSTIN
SABINE PETRA
VERONIKA
ANETA KASIA
AGNIESZKA
SANTA BETO
MAIA EDU
LAURO
IGOR
ANSELMO
SANDRO WILLIAN
NETO
MATEUS
VITOR
KELLEN
KAROLINE
MAYARA
JAQUELINE
MARGARIDA
CHIN
JEFERSON
JULIANO
MURILO
VINICIUS
TALITA
LETCIA
LIDIANE
IARA JLIA
TEREZA VANIA
GRAA
TIAGO
THIAGO
NAYARA LARISSA
PRISCILA
LAIS KTIA
CASSIA SORAIA
CLOVIS
MOACIR FLVIO
RENATO
VAGNER
DIOGO
MAIARA
JSSICA
LUANA
THAS
ELISANGELA
RENATA
MARILIA
RAFAELA THAIS
BRUNA
DAYANE CRISTIANE
MRCIA LUCIENE
SUZANA
REJANE
MATHEUS
NARA
ANDREZA
SUELEN
VALRIA JOELMA
CARMEM HELOISA
MRCIO
ROGERIO CRISTIANO
FABIANO
DEJAN
GORAN
ANIA DRA
TIO
LINCOLN
RONAN
ADONIS
JAIR SAULO JUAREZ
EDER
AGATA
HNA
TIA
JUNIOR
GERALDO
HELIO
STEFANIE
MICHAELA
ANNIKA
ANJA KATJA
MONIKA IVA IRENA
ALEKSANDRA
JARVIS
AJA
GARTH GORDON MYLES
CONRAD PARIS
SOLOMON
RACQUEL
CHARMAINE
CARLENE
EZRA
VIOLET
ANGELINE
CHRISTIN
ANETTE
ANTON ADAC TANJA
MARTINA
KATARINA
MARIJA
HAMILTON
JORDANA RAIMUNDO
MARCIO
RUBENS ROGRIO
FABRCIO
TAMIRES
JANAINA
GLAUCIA
CSSIA
MARIZA MARILENE CLUDIA
GUILHERME HENRIQUE
ANDRESSA
PATRCIA
REGIANE
ROSANE MEIRE
APARECIDA
LUZIA LEANDRA
FILIPE FREDERICO
DANIELE ELIS
IZABEL
VANDA
VINCIUS
MARIANE POLIANA
CIBELE
TATIANE
ANDREIA
TEREZINHA
THALITA
ROSANGELA
ROSELI MARISTELA
SUELY SELMA
DAVI
CEZAR GRAZIELA
DAIANE
LUCIANE
ELIANE
MARGARETE JANETE
ELISABETE
SUELI
SAMARA
FABIANE FRANCIELE
VIVIANE ELIETE
DEISE
IVONE CLEIDE
NEIDE
TAIS
GISLAINE
SIMONE
CATIA
CIDA ELZA
JULIANE
JOICE GIOVANA
CLARICE ANDRIA
BETE
NEUSA CLIA
YING
MAURCIO
CASSIO JOSY
ANE NANDA
BIA
IR
YONG
MEI
PAULO RONALDO
CAIO
CLEITON
SRA
DONA
HUDSON
HELDER NEWTON
EVERTON
EDMILSON
JLIO
ALEKSANDAR
ENVIAR
AMIGA
EDMAR
JOAQUIM MANOEL
EDSON
LUIZ CELSO
DARKO
TITI
MI
ABUELA
ABOGADO
AMIGO
WASHINGTON
ROMULO DENILSON
LUS
VALTER
GILSON
NILTON
EVANDRO
VALMIR
CLUDIO
AYO
AMOR BEL
ESC
KLEBER
MRIO JOAO
JOO
ANDI INA RA
JOVAN TATJANA
MAJA SANJA
BILJANA
ADMINISTRACIN
SECRETARA
ESCUELA
JEFFERSON
EMERSON
PRIMA
ADMINISTRACION
DIRECCION
COLEGIO
CB
SD
JONAS
CLEBER
BRENO
ARTUR
TU CONTACTO
RECEPCION
DIRECCIN
CI
CAP
EE
ANTNIO
CLAUDINEI LUAN
NILSON
SRGIO
KRISTIAN
ANDERS
AGUNG RUDI
ZALANDO
BELLA MARKO
TA
ALTHEA
ANNMARIE
BEATRICE
ALONZO
GUS
HENRY STEWART
KENDRICK
TERRENCE VON JERMAINE SHANICE
JONAH
KINGSLEY
HANNA
DIAN
BUDI
NIKO
MIRJANA
JELENA
OTIS
REGGIE RODERICK
DION DEON
KARLENE DAHLIA
FLORA
ARON
EDMUND
IVY
WILLIE
DERRICK
OLLIE
DAMION
ANGELLA
ERROL ISAAC
ASA
JOSEPHINE
CLARENCE
QUINCY
HORACE WINSTON
SAMUEL
GRACE JULIET WINNIE
DEXTER
CARLTON DONOVAN
RUDOLPH
EUNICE
JUDE
EMMY
VIVIEN
OLIVER
DESI INDRA DEWI PT
DIDI
ATTY NIKOLA VESNA
ZORAN
BOJAN
DRAGAN
VENTAS
ASISTENTE GERENCIA
PADRE
WAGNER
SILVA
PETERSON
OLXCOMBR
ROBSON
FBIO
TADEU
CELIO
AMAURI
ANDR ALEXANDRE
ALINE
EL
FACTURACION
CONTABILIDAD
LABORATORIO
PE PR
BOMNEGCIOCOM
WELLINGTON
REGINALDO
EDILSON WANDERSON
ANDRE
ALEXSANDRO
ALMIR
ADRIANO
ALESSANDRO
ADMINISTRAO
CONTABILIDADE ALISSON
ADILSON
ADEMIR
ADELAIDE
LEILA
SOPORTE
TIENDA
RADIO
DISTRIBUIDORA
CLIENTE
DOM
VILLA
COSTA
PROF
ELTON VANDERLEI
FARMACIA
SEGUROS
HOTEL
EM
PROFESSOR SILAS SIDNEI
VALDIR CHICO
OFICINA
CENTRO
HOSPITAL
DEPTO CONDOMINIO
SO
ESCOLA
COLGIO
ANDERSON ZE
CICERO
ALTA
AGENCIA
BIBLIOTECA
DEPARTAMENTO
RESERVAS
CONDOMNIO COORDENAO FALE CAIXA
ADM
CARREFOUR
INSTITUTO
SECRETARIA
CLINICA CLNICA
PEDIDOS COMPRAS
POUSADA
DIRETORIA
FOTO COMERCIAL
SITI
PAK LAZADA
ARIS
BOY KUYA
MILAN
MAMA
DRAGANA
MAMI
WESLEY
DOUGLAS
SIDNEY
KAI
BU
KA
MON ATE TITA
MAM
MA YO
NAT
LALA
TO TE
TAXI DIA COCO LA
MAS
MB FRESHMAN DA
BAL
BB
CL DE
MAY
MICHEAL
DESMOND MAURICE
THEO
EMMANUEL FRANCIS
MARCUS LEI
JING
KELVIN
AUGUSTINE
JEROME
SHELDON
VALENTINE MATILDA SALOME
YAN
JULIUS
SYLVESTER
PATIENCE
MAVIS
NANA
JUSTINA MERCY
AMA
LING
CHE
WARREN LLOYD DORIAN
NICOLA
GILLIAN
JACQUI
DES
ALLY
SIOBHAN
ALANNA
AIMEE ALLYSON
ADRIANNE
ALECIA
SHONA KIRSTY
CLIFTON
REUBEN
DORCAS
MARG GILL
MOSES
DEIRDRE
ANDREW
ALANA AIDAN
ALAINA ADDIE
CARMEL
OWEN BEN
CAM
AIDEN
ABBEY
MJ
AALIYAH DEVON
LEONIE
GARETH
BRONWYN
LIAM
ALEC
AJ
ABBY ABBIE ALDEN JOEY
IAIN GRAEME
SIMON
CONOR
KIERAN ADAM AARON ADDISON
ABIGAIL
ALLEN
DARIAN
LAMAR
ALISTAIR
GEOFFREY
PETER
PAUL
DOMINIC
RJ ALLAN
VINCENT
MERLE
JOHNATHAN
BRYANT
KWAME KOFI
UCHE CHRISTIANA
LIN
WEI
WEN SU
WALLACE
KAK
ADE
MM
SS
AR
CE
SERVICIOS
NA
BR
JB JL
BS
CM
ATENCIN
SERVICIO
ABE
ABI
SP
CV JM AP
SG
LC ATENCION
CR
PRINCE
WILFRED IKE
SUNDAY KAYODE MARTINS
LI WANG
NUR
EMEKA
AYO
CHEN YING
YANG
YU
CT
ABS
GM
CA MG
AT SA
FULL
SANTANDER
CC
AIM
JK
AA
MC
GS
TC RC
VIA
NO
CLUB
CRM
INFO
ADMINISTRADOR
CASA PROGRAMA
GRUPO
MUNDO
POLO
ARTE
GRFICA
ADMINISTRATIVO FINANCEIRO
FATURAMENTO
AC
PC
CS
DM
JA FROM
ACCOR
CRAIGSLIST
GOODGAME
LETS
KEHINDE
ABIOLA JIN
MING YONG
CHONG NURUL NOR
ABANG
SOLOMON KINGSLEY
FEMI
KEMI
TUNDE
AKIN
LAI
WAN
FAVOUR
TAIWO
SEGUN MIN
HAN
CHANG
MEI
CHIN
LIM ONG
AI
ABG
AG
AAA
MEGA
FOR
JUST ME
DUBAI
BUFFALO
KEHINDE
LG
AMIGOS
CASAS
CURSO CURSOS
EVENTOS
GRAFICA
BUFFET
VENDAS
ACADEMIA
RECURSOS GUMTREE SISTEMA REVISTA
LISTA
BAZAR
OLX
CIA ESPAO
CONTATO
RECEPO AGNALDO
DL
CORAL VIRGIN
JC ITS
ASK
CANADA
WWW
NEWS
ABIODUN
REBTEL
CHUNG HO
CHAN
NG TAN
AH BING
JOBSCENTRAL
ABA
DAMON
TOMMIE
JIMMIE BENNIE
CALVIN
PHILIP
STEPHEN
DAVID
ANTHONY
JOSEPH
TONY EDWARD
ALAN
BEVERLEY
CLIVE
NIGEL ANGUS
GRAHAM
IAN
GARRY
ROBERT
GEORGE
AL
LENNY RICHIE
BERYL NEVILLE MALCOLM
DUNCAN
MURRAY
COLIN
BRENDAN
JOE
FRANK
VINCE
LOUIS
ERNIE
ERNEST WILBERT
REG BARRIE
MICK
STUART
ROSS
GAVIN MATHEW
SAM
RICHARD
LOU RALPH
VIC
RAYMOND
HARRY
MILES
LUKE
BRENDON
TREVOR
GEOFF
GRANT
MARC
PATRICK
WILLIAM
TOBY
PETE ROGER RAY
ROD ROY
MEL
RICKEY
DARRYL CLIFTON
REUBEN
FREDRICK
JOHN
RUSSELL
LEE
LES
RIC
LEN
HOWIE
NORMAN ARTHUR
NIC
HAYDEN
JOEL
TRISTAN SHAUN
DARREN
NEIL
RORY GREGORY
MICHAEL
THOMAS
STU
GLEN
SID GERRY
HARVEY EJ
NATHANIEL
VERNON
ERNEST WILBERT
DORCAS
MOSES
NEAL
PHIL
WAYNE
BARRY BURT BERNIE
LEON
THEODORE
FREDERICK
DERICK
SHERMAN
FREDDIE
IRVIN
CLEMENT
GIDEON INNOCENT
GODWIN
TERRY
BRUCE
STAN GLENN
BARNEY
HAROLD ARNIE
EUGENE
HOWARD TERENCE
CLINTON DWAYNE
MELVIN AMOS
BENSON
SAMSON
DENNIS
CHARLIE
CARL ART
GERALD RONALD
LEONARD LAWRENCE
STANLEY CURTIS
VAUGHN
LEROY
JONNY
MAX
EVAN
JONATHAN
QUINN HUGH NICHOLAS
CHRISTOPHER
STEVEN
CLEMENT
JESSE
GABE
ERIK
JARROD
BENJAMIN
ERIC
SEAN
TIMOTHY
JEFFREY
MARK
JAMES
KEITH
AD
DEVON
RJ
DARIAN
ADDIE
MJ
AALIYAH
ALAN
WARREN BRYANT
JOEY
VINCENT
MERLE
JOHNATHAN
JEREMIAH
JOSHUA
SPENCER
ZAK
DEREK
MATTHEW
NICK
KEVIN
ROB
RICH
NOAH
SETH
JUSTIN
JONATHON
RYAN
SHANE
WILL PJ
BRIAN
JAY
CHRIS
STEVE
NED
JACK
RICHIE
DAMON RICKEY
ALDEN
AL
LENNY
MILES
ARTHUR
ABBEY
ABBIE
ALLEN
LOUIS
ERNIE
NORMAN
NATHANIEL
DARRYL
JACOB
JORDAN ZACHARY
NATHAN
JEREMY
JASON
MATT
CRAIG
MIKE DEAN
TOM
KEN
FRED
CLIFF
BERT DONALD
KENNETH
RODNEY
MYRON LUTHER
GODFREY
JUSTICE
PRECIOUS BLESSING
KK KAM SIR
WONG ANG
KC
AGODA SM
AB ALFA
MASTER
MANAGER
VS NEWSMAX
NURSING
HOLIDAYS
NEWSLETTER
BOOKING
GANA
UK
ADMIN
CLARO
MERCADO
TAM
LOJA
EQUIPE
COBRANA
SETOR
GLOBAL
ALL PLENTYOFFISH
LIFE
ADORE
SENIOR
SPECIAL
JOBS
INTERNATIONAL VISA
MARKETING
ACCOUNTS
CASTING TERRA BANCO CLUBE
LIVRARIA
SAC ATENDIMENTO CADASTRO
LO
PEOPLE
VA
AXA
MINI
CASE
ONLINE
INTERNET
LADY
MK
PRINCESS
MAN
CAT
ASIA
AD AE
SUPER
HONEY
LOVELY
LOVE AND
ADULT AM
NICE
AGENT
IDEAL
BABY
MY
BOSS
SWEET
BEE
DAY
WE
ACS AZ
FAST
DIGITAL
DENTAL
HEALTH MEDICAL
SECURITY
INSURANCE
CORPORATE
GROUP
RECRUITMENT
SALES
ACCOUNTING
ROL
RESERVATIONS
BRASIL
SUPORTE
COBRANCA KM
GI
PAI
MEU
EU
BONPRIX CENTRAL
PS
EXTRA
RELACIONAMENTO
RH
RECRUTAMENTO
CLICKON
VIAJAR
RECEPTION
DIRECTOR
LAU DENISA
AMIL
OUVIDORIA VAGAS
PASSARELA
PORTAL
ADY
FATURA RESPONDER
MINISTRIO
GABI AO
CORNELIA
SECRETARY
SKY TEO
MAGAZINE
ADI
LAVINIA
LOJAS
ANAMARIA
RAMONA
MARIAN
RESERVATION
GEO
CATHO
OANA IULIA
ADINA
CAMELIA
GEORGIANA
RN
ALIN
MIHAELA
MADALINA
RODICA
DORINA
MARILENA
MANGO
BEBE
NICOLETA
IULIANA FLORENTINA
TEODORA
SIMONA
OUTLET
NICU
ANDREI
ANCA LUMINITA
DOINA MIRELA
LOREDANA
LIM
ABBY
ABIGAIL
EDWARD
RAYMOND
HARRY
HARVEY
JOSIAH
DYLAN
GARRETT
JAKE JOSH
KYLE
BRYAN JED
JON
GREG
TIM
DAVE
TED
GARY
ED
CLIFFORD
WILLIS
FLOYD
DWIGHT
RANDOLPH
CHARLES
DARYL
LELAND
CLYDE
ALTON
BYRON
COMFORT
GLORY LEX
JUMIA
CECIL
WENDELL
LESTER MARVIN
DIVINE
MAC
TEE
QUEEN
MISS
SEXY
PRETTY
HELLO SHOP
IN
BEAUTY
TOP
DESIGN
SIMPLY
SIS
CHESTER
HERMAN
HERBERT
EVANS
BART
PERRY
VANCE
DARRELL
EARL
ARCHIE
MERLIN
EDMOND
MAXWELL COLLINS
JARED ZACH
ZACK
DREW BRETT SHAWN
MITCH
SCOTT
JEFF DAN
RICK
JIM
BOB
BILL
RON
HAL
BRENNAN REGAN
GIDEON
TJ
CJ
TODD
KARL GREGG
DOUG
NORM
DON
LARRY
IRVIN
ETHAN
MICAH ZAC CONNOR
NATE
KORY
CHAD DANE BRAD
BRET TOD ROBB KURT
LOREN
RUSS
MARTY
CHUCK
JERRY
JEFFERY
LONNIE
VIRGIL
DEWAYNE
ARNOLD
JASPER
KENNEDY
DEA
PEACE
DJ
KING
SISTER
PAPA
HOT
FUN LIVE
PET
CREATIVE PRO
BE
MEDICARE
CENTER
TAX
BUSINESS
IT
LITTLE
COOL
CRAZY
GOOD KIDS
HAIR SPORTS
VIP
SMART
PRIME PRINT
CABLE
ALLSTATE
POST
GENERAL
PROPERTY
EXECUTIVE
WEB
CAREERS
BLACK
HAPPY
MAGIC
DREAM FRESH
CUSTOM
POWER
ATLAS ACTIVE
GET GAME
ENGLISH LAW PROJECT VOLUNTEER
TALENT
ELITE CLASSIC
REAL
ABC
CHURCH
LEASING
LLC USA
TOTAL
ADVANCED
ACTION
ON
AUNTIE AUNTY MOTHER
MOMMY
PHILLIP
RICKY
RONNIE
MACK
ALVIN
ALBERT
ALFRED
ELDER
CHRIST
BRADLEY
BLAIR DARRIN
TAD
SCOT
CHET
DALE
SKIP WALT DICK
DEVIN
COREY
INNOCENT
MICKEY RUSSEL
FRANKIE SONNY
ROYCE SAMMIE
JACKSON
BISHOP
APOSTLE
TEAM
LONDON
BOOK
NEXT
PREMIER
ANIMAL ADVANCE
CASH
CAREER
FRIENDS
SCHOOL
FRONT
HELP
ORDER
PAYROLL
HR
PINK
STAR
DELTA
PHOENIX FREE
AFFORDABLE
DIRECT
DRIVE MAIN
CALL
TEECHIP
SERVICE
ADMISSIONS LEGAL
LYONESS MYBRD
OCHELARIDESEZON
CRISTI
ALEXANDRU ANDREEA IOANA
EMIL
ABIOLA
HOUSE
GUITAR
UBER
SUPPORT
CONTACT
WARRANTY ACCOUNT LOAN
BOUNCE APPROVAL
LUCRUESENTIAL
ALEGERICUCAP
GMAIL
CUSTOMERCARE
ORDERS
CARD
TARGETMAIL
PROMOTII
NAMESPACE
RAZVAN
PURCHASE
FEMI SQUARE
COMMUNITY
CARE
AUTOVIT
RO
BIAPBODY VALI
RALUCA
NICOLAE
IONELA EDUARD
HAN
CHANG CHAN
STUDENT
CLIENT
CHILD
BOGDAN
IULIAN COSMIN LIVIU
FAVOUR
FAMILY NET BETTER
ALLIANCE
ADVANTAGE CAR
FORD MOBILE FARMERS
HUBBY
CHINA
EVERETT
MORRIS
KJ
HOMER
EDDIE
SAMMY
LEWIS
BERRY
DAVIS
GODWIN
JOHNSON
PASTOR
GRAY KANE
TEDDY
BROOKS ELLIS
CAMPBELL WALKER JONES
WILLIAMS
REV
DEACON
THOMPSON
ANT
DRE
DADDY
LUCKY
RED
SUN
SUNSHINE
MBA
SAINT ST
TROY DARIN
DAREN
KIP
VERN RANDY
THOM
CARY
HANK
GENE HERB
LEW
BRENT
WESTON KIRK
KENT CURT
DUANE
GALEN
CHIP
DENNY
WALLY
LOWELL
DANNY REX
LYLE
LON
RODGER
RANDALL
BUD
BUZZ
BUTCH
BOBBY
WIL
JOHNNY
AMOS
RILEY
BRANDEN
SKYLER
CASEY TYLER
CORY
LANCE
CLINT
WES RUSTY
RANDAL
CHARLEY
BUDDY
BILLY
BO
JIMMY
CAMERON
TYSON
BRANDON
BRYCE
BLAKE
TRAVIS BLAINE
TY
STEVIE
KRISTOPHER
DARREL MONTY
THAD
ROBBY
DUSTY ROBBIE
CLAY BJ
BUCK
DONNIE
KENNY
DONNY
BENNY
LANDON
TANNER TRENT
DUSTIN
WADE
LEVI
ABDEL MONTE
JAMEY
MARSHALL
MOORE
BROWN
MURPHY
FR
TEACHER
ABO ABD
ABDALLAH
CLAYTON
PRESTON
ABDOULAYE
DEWEY
DOYLE
GRADY
MITCHELL
JARRETT
COLEMAN
WRIGHT
ADAMS
ATTORNEY
FATHER
CHEF
COUSIN
ABDO
HARLEY
DALTON
ABDOUL
BUBBA
WOODY
MARLIN
ELLIOTT
HARRISON
BENNETT
MILLER
HALL PHD
PRESIDENT
LIL BIG
BC
BOO
GOLDEN
HIGH
UNIQUE
ALPHA
PERFECT
CD YOUR
AMAZING
CHEAP QUALITY
BUDGET
JOB
OFFICE
FREEDOM
PLATINUM GLOBE AIG
USAA
JOBCOM
FHA
HOLIDAY
AUTO
ASIANBEAUTIES
HOME
LYFT
PERSONAL
MEMBER
PUBLIC COMENZI
CATALIN
OVIDIU
RADU
MIHAI
WOMENS
CONSUMER GUEST
CUSTOMER
CLAUDIU DRAGOS
KEMI IONUT
LUCIAN
LAURENTIU
VASILE
MIRCEA
FINANCIAL
PROSPER TUDOR
SC
SILVIU
IOAN
SORIN
POPESCU
WORK
STAFF
ACCEPTANCE
PIZZA
ROCK
BRIGHT
PARTY
URBAN
PURE
CPA CAPTAIN
REP
CONGRESSMAN
AMIRA
AMINE
ABDOU
ADAMA
AMADOU
TREY
TOMMY
WARD
PIERCE
REID
PORTER
RHETT
FORREST
CARSON
COLBY
AUSTIN
CODY
HEATH ROCKY
BRITT
BRADEN
CALEB
BRADY
BROCK
CHASE
CHAZ ALY
BRYON
MASON
COLTON
LOGAN
JT
DENVER
AYA
KALEB
BENSON
BEAU
FREDDIE
AUGUST
CONNER COLE
COLLIN
BRANT
EMAN MAHA ADEL KURTIS
DILLON HUNTER
DRAKE
NOLAN
SAMY MONA WYATT
HEBA
MARWA
ABEER
AMANI
MED
RACHID
KIRBY
SCOTTY
TIMMY
REED
CARTER
BARRETT
GRIFFIN
BAKER
HILL
ESQ
MD
GEN
TARIK
MUSTAPHA
ISSA MOUSSA MAMADOU
JD
CHANCE
JJ MIKEY
CLARK
TUCKER
PARKER
SULLIVAN HARRIS
REALTOR CAPT
CHIEF
BRO
CUZ
YOUSSEF
SAID
KHADIJA
YASMINE
DARBY
ZANE
DEL CAL
OLA
LANE
REESE
LT
COL
JAE
REPRESENTATIVE SENATOR
AUNT
MOMMA
FAT
GOLD
ORANGE
ISLAND
GILT
ANYTIME
SHELL
LOCAL
BEST
SURVIVAL
ESOLAR AMAZON
ALERTS
AGGRESSIONWONTSTAND
HP
NATURAL TRUE
NEWMARKET
EUGEN
FLORIN
CALIN
DORIN
ION
GHEORGHE
VALENTIN
RISE PAYPAL CHOICE
HARP
APP
ANCESTRYCOM
MESSAGE
SQUARETRADE
ACCEPTING
VI
EVERYDAY
GAS
CAMPUS
FAN
ASIAN
ONE
LASIK
METRO
TEA CITY
ADT SOCIAL
BEYOND
SURVEY VENUS
DO
TECH
NOVA
DATING
DROPOX
MILITARYCOM
TIME SWEEPSTAKES
EMAIL
RES
DOMAIN
FACEBOOK
GOOGLE
CORNEL MARIUS
VLAD
TUNDE
GO
PANDA
MAIL
TWITTER
WHATSAPP
RUNESCAPE
VIPRE RENT REPLY
SELECTED UNDISCLOSED COMMUNCIATIONS
MEDIA
ADOBE
GOODREADS
TAGGED
ACT ACTIVISION
EARLY
ROSETTA
AMERICAS SCEN
HUMAN
COLLEGE
JOBRAPIDO
MAILER
AERIA
BEENVERIFIED
POPA DUMITRU
HO
AGE
TASTE
TOYOTA
UNIVERSITY
ELECTRONIC
PCH
EXPERIANDIRECT
CASHNETUSA
POP
AERIAGAMES
YMCA
DEFENDERS
LEAGUE
ACADEMY
TAIWO
HEALTHCAREGOV
SKILLSURVEY
LENDINGCLUB FANDUEL
TRIVIACRACK
LIFEPROOF
FITBIT
COMCAST
CLEVELAND HONDA
WORLD
SEARS
ACCREDITED
HONG
SON LONG
UNCLE
GRANDMA SISSY
OLIVE
FARIDA
MALIKA
BRADFORD MIKEL
RASHAD BABA
TATE
COACH
FOSTER
MANAL NADA
FATMA
AMAL
SAMSON
DALLAS MAT
NIK AN
COOPER
SMITH
DC
DUKE
BROTHER
GMA
GREEN
BLUE
ICE
DAD MOM
GRANDPA
BEAR
SEA SILVER
YOUNG
DADS
MOMS
STONE
RIVER
BAY
SALMA
AMINA
AMARA JAMAL KAREEM
BASIL
MUSA AS VAN
TREND
SHAN
MAJOR
SGT
REEM HANAN HANA FOUAD
KARIM
DAKOTA
MAGDY
SAMEH MINA
NADER
RIMA SAMIR
AZIZ
FATIMA ZAINAB
HOA
TRAN
NGUYEN ANH
NASH
BA
CHU
DOC DOCTOR
SPRING
FOREST
GRAND
EAGLE OCEAN
CO
CELL PA
EAST
FOUR SOUTH
LAKE
MT
MOUNTAIN
PACIFIC ATLANTIC
LAM
CAMP
SPACE WEST
NORTH
GUARANTY
NORTHERN PARK
VALLEY
VILLAGE BELL ATLANTA
BROOKLYN
UBA TRINITY HARMONY SME
LUXURY MIAMI
SOUTHERN HOUSTON
DAILY
AVOYA
ALERT
CIMB
DIAMOND
STERLING ECO
FLORIDA
MICHIGAN FOX
CALIFORNIA ROYAL UNITED
REVOLUTION
HARDER
FASHION BACK
AIR
FNB
LAKESHORE TRAVEL
FOOD DISH
TEXAS
COLORADO
FEDERAL CANADIAN
FORT FIRST
UNION
OHIO COLUMBIA
LIBERTY NATIONAL
AMERICAN
AMAZONCOM
BLACKBERRY
BOTTOM
GOLF
YOUMAIL
FREDERICKS
TICKETMASTER
GAMEFLY
SEGUN
WYNDHAM
ANGIES
ROGERS
BANK
BARACK FINGERHUT
SPEEDYCASH
GROUPON
NG
DOMINIC
TONY
RALPH
VIC
VINCE
HOWIE
EJ
SHERMAN
ROY
MEL
FREDERICK
DERICK
HESHAM
SHERIF
RAMY
YASSER
WALID
RASHA
NABIL
DAR
FARID
AISHA
YASMIN
CH YUSUF
MEHMET MURAT AHMET VU
HOANG
BAO
HAI YEN CHI
MARIAM
SAMIRA SH
OM CHANDRA KALA
DUNG
MINH
CHAU HUNG
THAI TAI TIN AMI
SAMAR
HANY
TAREK WAEL
HISHAM
RANIA
HALA
SAMI
MOE
SALIM
ALIA
SAMIA
LAYLA
NADIA
ELHAM
KAMAL
THANH
NGOC
HIEN QUANG
HUY TUAN
NAM
DRIVER
ACCESS
STATE
HERITAGE
SALEM
ASHFORD
KAPLAN NFL
BOSTON
MANCHESTER
WHITE
MARYAM
MOHSEN
INDIA
PHUONG THU
HA AK
TRI
ALIBABA
MO
ANIS
FARAH
TAMER
HOSSAM
EHAB
EMAD
AYMAN ALAA
KHALED REDA
HANI
RAMI
MAHER
SAMER
AMR
ESSAM OSAMA
WALEED SALAH
YOUSEF BASSAM FADI
HASSAN
NOOR
IMAN LAILA
HADI
KHANH THUY
THAO VINH
AMAN
ADITYA
AARTI
MEHDI
VAHID ALIREZA
OMID
HANH
ASH
MAI
AKASH
ABHISHEK
CITI
DOLLAR
COUNTRY
VANDERBILT
WOODFOREST
THE
SECOND
TINY
FIDELITY
TD
DULUTH
IMOTORS
DEMOCRATIC
KRAFT
TRACTOR
OLD
BOX
US
AIRTRAN
SIERRA
SAMS
GIFT
CREDIT
NEW
GARDENERS
RENWOOD
SELECT
BRITISH
RECRUITER
OIL
STITCH
MONEY
DISCOVER
CHICAGO
HEALTHECAREERS
VERIZON
FRONTIER
CHARTER
ENTERPRISE
MACYS
HIRERIGHT
CASHCENTRAL
ZYNGA
AVANT
KIK
WALMART
EBATES
WISH
XBOX
SHUTTERFLY EA
BH
INTERVAL
QANTAS
DTE
PENN
DESTINATION
MOTHERHOOD
HARBOR
BOOT
INKED
DONT
EXCALIBUR
BODY
OSHKOSH
RUNTASTIC
NORTON
CBS
AVANGATE
ZAZZLE
DISNEY
CRUISE
TOWER
APARTMENT
YAHOO
LOGITECH
LOYAL
GAMELOFT
TAPJOY
BABIES
LL
DAVIDS
ABIODUN
BOVADA
GROOVEBOOK ZULILY
PB
QUICKEN
LANDS
NORWEGIAN
GIRLS
GURNEYS
JP
MATCH
CELEBRITY
LOS
ACE
VIKING NASTY
ABERCROMBIE
CVS
AJC
WAYFAIR MYSPACE
CHAMPS
CLINTON
VERNON
ISLAM
MAHMOUD MOH MOHAMED
FIRAS
SALEH
NASSER
HABIB
MOHAMAD
SAHAR
ARMAN REZA
HUONG
ANTONY LINH
AMAR
AJIT SNAPDEAL
AKSHAY ABHAY
ABHIJIT
VODAFONE SAMSUNG
HASAN
MAHDI HAMID HAMED
MASOUD
TRANG
ROMA
ANJU
SK
ALOK AJAY
FATEMEH
ANISH ANIL
ARJUN
PRASANNA
ADITI
ABHINAV
RELIANCE
HSBC
HOSSEIN
SINA
ARASH NEDA MARJAN
ARUN ANAND
AIRTEL
BAJAJ TATA
ICICI
UNIVERSAL
MUSICIANS
DOONEY
HOTELSCOM LTD
TRANSUNION
LEFTLANE
BABAK
MITRA
BIJU
PRAVIN
AMIT
MAKEMYTRIP WISDOM NAUKRI KOTAK
STANDARD HDFC
FARHAD
AMIR
BABU
RAJU
GANESH
AVINASH
SBI
MANU
VF
WOMAN
KAISER
WESTERN
BOYD
LEUKEMIA
GREAT
IOLO
SIRIUS
DD
ADIDAS
HOLLAND MINDFIELD
PAYLESS
MAHESH ASHWIN
ASHOK
BHARAT ANKUR
ANURAG
JET
BURKES
SHAILESH
EXPRESS
BRONTO SUNTRUST
FEDLOAN
CATO
VALUED
HILTON
HANES
VICTORIAS
PROCTER
CABELAS
TERENCE
DWAYNE
LEROY
MOSTAFA
ENG
ASHRAF AHMED
ZAID
HUSSEIN
KHALIL
ALA
SAYED ANAS AMER
AMMAR IBRAHIM
ABDULRAHMAN
ISMAIL
MUSTAFA
MOHD
ZAHRA
RAHIM
SAEED MAJID
EHSAN
NIMA
SIMA
RAMESH
SATISH
GOPAL
ARVIND
DEVIKA VINAY
RAJENDRA
AMIN
AHMAD
AKRAM
CYRUS
RAJA
BALAJI KISHORE
SURESH
PREM
RAJESH
DINESH GIRISH
BLESSING
PLANNED
BATH PUBLISHERS
SOUTHWEST
HOLLISTER
KK
NILESH VIVID
TARGET
WELLS
CAPITAL PROGRESSIVE
AETNA
HERRSCHNERS
PEPSI
RAM
MOHAN
PRAKASH
PRADEEP
PRAMOD
VINOD
NARENDRA
JAYESH
RAILWAY
KG
ABU
ALI MAHMOOD
AKBAR
AMNA
ENGR SAAD
MUHAMMED
MOHAMMED KHALID
HUSSAIN
MOHAMMAD
ARIF
ABBAS
SIVA SURYA
KUMAR
ZARA
NIDA
ASMA
OSMAN
FAHAD
RANA SAIF
SULTAN
COMFORT
BALA SHANKAR
SAI HARI
HARISH
ROSHAN
DILIP
UMESH
MUKESH KAMLESH
UTSAV
ZACKS
PRAVEEN
RAJAN
VIJAY SHYAM
SANTOSH
MANOJ MAHENDRA PAWAN
JAGDISH
KETAN SCHAEFFERS
PATEL
KRISHNA
ROHAN
NAVEEN
RAVINDRA
NARESH SUDHIR
NITIN
PANKAJ
YOGESH
CHIRAG
LAN
RAJ
KIRAN VIKRAM
SUNIL
SANJAY
SUMIT
RAKESH
HEMANT
ARGOS MOONPIG
HITESH
SAMEER
DEV
VISHAL
CHETAN
REPLACEMENTS AMF VIPUL
SURAJ
RAJEEV
PRASHANT
SACHIN
DEEPAK
MANISH
JITENDRA
MAYUR
PIYUSH ANKIT
HIMANSHU
RAVI
RAMAN RAJIV
RAHUL
ROHIT
SAGAR
MOHIT
GAUTAM
ASHISH
KAPIL
ATUL
RITESH
MEREDITH
NEWEGG
JUMIA
CHUNG
GLORY
GURPREET
RISHI
SANDEEP SANJEEV
VIVEK VIKAS
SAURABH
TARUN
NIKHIL
ANUJ DOW
CHEGG
EASTBAY
VAUGHN
MYRON
MELVIN
GODFREY
AYESHA
SADIA
RABIA
SANA
HAMZA OMER
JAMIL
AMJAD
ANWAR
MANI
PRASAD
PAVAN
JAI
DEEP SUNNY
VARUN NEERAJ
KARAN
NIDHI
GAURAV
SWATI
MANISHA
SHRUTI
VAIBHAV APPLE
SUMAN
RESHMA
RASHMI
POONAM PREETI
SHIVANI
DEEPIKA JYOTI SUSHIL
SHWETA
PRIYANKA
KUNAL
TUSHAR
THINKGEEK
LADY
SEEMA SHILPA
SHEETAL
NEHA
PRECIOUS
KOMAL
ASHUTOSH
SONY
ACER
PALLAVI
POOJA
PINKY
XOOM
MICROSOFT SPEEDDATECOM
SUNITA
SANGEETA
SMITA
NIKITA
LEX
MISS
CURTIS
LUTHER
BIBI
HINA
SABA
MALIK
HAFIZ
JAWAD
FAISAL
ABDULLAH
ABDUL
RASHID
BILAL
NASIR TARIQ
ATIF
ARSHAD
ABDULLA
ADIL
SAIRA
UMAR
YASIR
SYED
ASAD ZAIN
SALEEM
AZHAR
FARHAN
MUHAMMAD
ASIM
ZUBAIR
RIZWAN
SALMAN KHAN
SHAH
ADNAN
DEVI
KARTHIK
VIJAYA
RAMA
SRINIVAS
SHIVA
MADHU
DIVYA KAVITA
SRI MURALI
RADHA
VENKAT SATYA
RADHIKA
SHALINI
VEENA GEETA
LAKSHMI
AFTAB
ABID RANI
UMA
APARNA
REKHA PRIYA REENA NISHA
SARITA
ARCHANA
MIRZA
USMAN
KASHIF
SAJID IMRAN
SHAKEEL WASEEM
ADEEL
AFZAL
ARUNA
GEETHA
SUDHA
ZAHID
JUSTICE
MOHSIN
SHOAIB
IRFAN ASIF
IQBAL ASLAM
AHSAN
VIDYA HEMA USHA
SANDHYA
MANJU
DEEPA
TAHIR
SHAHZAD
SHAHID
NAVEED NADEEM
WONG
LEN
HOWARD
ZEESHAN FAROOQ
NAEEM
JUNAID JAVED
ZIA
AAMIR ANITHA
JAYA ASHA
ANU
MEENA LEENA
SAJJAD
MANSOOR WAQAS
GHULAM
SOHAIL
CESS
RAY
ROD
LEON
THEODORE
LAWRENCE
STANLEY
RODNEY
DWIGHT
RANDOLPH
BYRON
KHURRAM
DIVINE
MAC
EVANS
KAMRAN
ZAFAR
DANISH
SIR
EUGENE
CLIFFORD
WILLIS
FLOYD
ALTON
LESTER MARVIN
COLLINS
CLYDE
WENDELL
HERBERT
MAXWELL
PEACE
DJ
KING
SISTER
CECIL
HERMAN
EDMOND
DEA
CHRIST
KANE
AUNTIE ANT
KAM
CHESTER
MERLIN
KENNEDY
APOSTLE
SAINT
ST
MK
LEONARD
EARL
ARCHIE
JASPER
ELDER
THOMPSON
CUZ
ALFRED
BISHOP
PASTOR
DEACON
CONGRESSMAN
CLE
UNT
WILLIAMS
REV
TABLE II: The five nearest neighbors(NN) of representative male and female names in embedding space, showing how they preserve associations among Asian (Chinese, Korean, Japanese, Vietnamese), British, European (Spanish, Italian), Middle Eastern (Arabic, Hebrew), North American (African-American, Native American, Contemporary), and Corporate/Entity.
REPRESENTATIVE
SENATOR
MIKEY
ELVA
LETTY
REM ANAIS
ELI
G
is a variant of “Daren” and “Darien”, among others. Fig. 3 (left) presents a map of the top 5000 last-names. We color a name according to the dominant racial classification from the Census data. The top 5000 names contain four races: White (pink), African-American (orange), Hispanic (yellow), and Asian (green). Names without a dominant race are colored gray. The three cutouts in Fig. 3 highlight the homogeneity of regions by cultural group. The embedding clearly places White, Hispanic and Asian in large contiguous regions. African-American names are more dispersed. Interestingly, there are two distinct Asian regions in the map. Fig. 4 presents insets for these two regions, revealing that one cluster consists of Chinese names and the other Indian names. Overall, Fig. 2 and Fig. 3 show that our name embeddings capture gender and ethnicity information well.
is the frequency of names in the Contact list. The replacement usage frequency is the frequency of a name in the replacement name population. To measure the popularity dis-similarity, we sample 10k names randomly from the name list, with sampling probability proportional to real name frequency. We record ten nearest neighbors (NN) for each of them. Now the popularity dis-similarity is computed by JensenShannon Divergence using the real name frequency of the sampled names and replacement usage frequency of the nearest neighbor names. Secondly, we measure gender similarity by precision at k, defined as the percentage of the k-nearest neighbors of a name having the same gender as the name itself. Finally, we measure ethnicity similarity by precision at 1. For example, the precision for White names is defined as P (W |W ) = P (1st NN is White|real name is White). Results. We present the evaluation results in Table IV. The table shows that a joint embedding of first and last names are often better than the separate embedding. In addition, the CBOW model generally outperformed the SG model for the majority of the nearest neighbor tests. Given these observations, in this paper by default we use “CBOW joint”.Note that while P (B|B) (35%-59%) is generally much lower than P (W |W ) (92%-94%), considering that a randomly picked name from the contact list has a probability of 74% of being White but only a probability of 3% of being Black, P (B|B) is actually significantly above the probability of a random name being black.
D. Evaluation of Different Word2vec Embeddings The embedding from word2vec is influenced by two factors: the input text, and the word2vec parameter settings. So far we have been using the contact lists unchanged as the input to word2vec. However there are many possible variants. Since certain contact lists are short, and word2vec uses a sliding window, some names from the contact lists of the previous/next persons could be in the same window as that for the current person. One possible solution is to pad stop words in between two contact lists such that a sliding window would never enclose contacts from unrelated persons. Instead of putting both first and last names together in one embedding space, another variant might generate two embeddings, one using only the first names, and another using the last names. In addition to the input text, the second factor that influences the embedding is the different settings of models and parameters, for example, the selection between CBOW model and SG model, the size of sampling window and the size of negative samples. To understand how these two factors influence the embedding, in particular with regard to the quality of the resulting look-alike names, we evaluate the following variants of the word2vec embeddings: • Set the word2vec model to be CBOW or SG. • Generating joint embeddings of first names and last names using the contact lists as they are (“CBOW joint” or “SG joint”). • Generating embedding for first names and last names separately by including only first/last names in the contact lists (“CBOW sep” or “SG sep”). Metrics. To evaluate the quality of the embeddings with regard to look-alike names, we propose three metrics to measure popularity, gender and ethnicity similarities between real and look-alike names. Firstly, we would like the overall frequency of a name in the real contact lists to be similar to that in the look-alike lists. For example, if “Mark” is a more popular name than “Barnabas” in the real contact lists, we would also expect that “Mark” appears more often as a replacement name than “Barnabas”. We define two types of frequencies. The real name frequency
III. P ROPERTIES OF NAME E MBEDDINGS After all the names in the contact lists have been embedded through word2vec, each name is represented by a vector in the high dimensional space. Earlier, in Fig. 2 and Fig. 3, we have provided visual evidence that the embedding is coherent, in the sense that it places names of similar gender and ethnicity close-by. In Section II-D we have also seen aggregate numerical evidence of this coherence. In this section we evaluate the coherence of the name embedding quantitatively and in detail. A. Gender Coherence and Analysis We first examine the gender coherence of a subset of first names and their ten nearest neighbors. This subset of first names is the intersection between contact lists and Census 1990. It contains 1,146 unique male first names and 4,009 unique female first names. All names in the subset are ranked by their popularity as measured in the Census 1990 data. Table V shows the gender coherence results, measured by precision at k, as a function of the population of the names, and k, the number of nearest neighbors. For example, the cell at {≤ 20%, 2} of Table V (left) reads 97. It means that for the top 20% most popular names, 97% of their nearest 2-neighbors have the same gender as them. To save space, we only report the first two significant digits of each precision (e.g., 0.9742 becomes 97). In addition we color the cells of the tables based on the values. Within each table, we use warm colors for high values and cold color for low values. This gives us heat-maps through which it is easier to see the trend of how the precision
4
HAM MORROW
AKERS
CARNES
CHILDRESS WORLEY
THACKER SHEPARD HOLLINGSWORTH FRANKS
MCLAIN BONE
ADAIR
LIVINGSTON
CANTRELL
CARVER
HELM
REEDER
ENGLISH
MARKHAM
BOWER
JARVIS
FAGAN MORLEY HIGGINS
BARNHART
HINKLE
SMYTH
CAVANAUGH BOLAND
SHANAHAN
TOBIN
WHELAN
KEATING
GALVIN
OSHEA
REILLY
MAHER
BRODERICK
DEVINE
FREY
NOVAK
BARTH
DOWD GRADY
CONNELL
HOFFMAN
BOCK
KERN
BERGMAN
BECKER
BAER
SCHREIBER
GRUBER
VON
KOCH
WEBER
REICH
KLEIN
BLUM
ROSEN
ISRAEL
FONTENOT
MORIN GAUTHIER
BROUSSARD
CARON
COLLAZO
LACROIX
CARRIER
MARRERO
BERNIER
GALLANT
POIRIER GAGNON
PAQUETTE
HAMEL
CANTU
3
MARES
ORNELAS
ESQUIVEL
ZARAGOZA
OLVERA
CERVANTES
NAVA
CORONA
CHAVEZ
LEYVA
MONTIEL
CRUZ
OCAMPO
JURADO
BORJA
MIRANDA
AMARO ROQUE
LORENZO
JAVIER
DELACRUZ LUCIO
TOLENTINO
CAMILO
PASCUAL FRIAS
ALCANTARA
TOSCANO
DOMINGO
ABAD
CLEMENTE AQUINO
JULIO
RAFAEL
ANTONIO GREGORIO
GODOY MARIANO
GUSTAVO EDUARDO
LISBOA
MARCIO PAULO
FABIANO
CLAUDIO
EDSON
MAURO AURELIO LUCIANO ADRIANO
LEO
CEZAR
AFONSO
CONOSCO
SERRA SOUTO
PAIVA SIMOES
BENTO
FAGUNDES
OLIVEIRA
FRAGA
CALDAS
QUEIROZ
LACERDA
JARDIM CUNHA
MENEZES
ARSHAD
UL
BILAL
GOULART
BITTENCOURT
ABBASI QURESHI
BHATTI
AKRAM MAHMOOD
PERES DUTRA
BUTT
JAVED NADEEM
SAEED
ASHRAF NAEEM
HAIDER
MEHMOOD
SHAHID SHAHZAD
FAISAL
FATIMA
CORREIA
MEDEIROS FURTADO
CABRAL TURISMO PAES
URBANO ENGENHARIA
COMUNICAO
TAHIR
ASIF TARIQ
RAZA
ANWAR IMRAN NASIR SALMAN AO SAC
REPRESENTAES
VIANNA
NOBRE
LINO
ALBUQUERQUE
GONCALVES CAETANO
GUIMARES
ARAJO
NETO
VITAL
SAMPAIO MOURA
SIQUEIRA
BRANDO
SARAIVA
ARRUDA
GOUVEIA
DANTAS MESQUITA
LUCENA
CERQUEIRA
VASCONCELOS
MORAIS
PEIXOTO
GAMA
ELETRO
TELES
BARROS FIGUEIREDO
MENDONA
SULTAN ANSARI
SIDDIQUI
AKHTAR
FAROOQ
IQBAL
ATENDIMENTO CORRETORA
VENDAS
MACEDO
LOURENO
PIMENTA
RABELO
COELHO
MONTEIRO
IMVEIS
BRASIL FESTAS REZENDE
RAMALHO REIS
AMARAL
MENDES
BRAGA
DAS SINHA ULLAH MIRZA
BANSAL
MISHRA
SHEIKH
BASHIR
KHALID
ASLAM
LINS
BISPO
BEZERRA
PINHEIRO MAGALHES CAVALCANTE
NOGUEIRA
FEITOSA
PONTES
MARINHO AMORIM
MAIA CAVALCANTI VIANA
BANDEIRA GALVO
PESSOA
NEVES
SILVEIRA MORAES
JAIN
SYED
BAIG
MALIK
IMOVEIS SERVIOS
MAIS
RESENDE
DOS DINIZ
ANTUNES
SOARES LEITE
CARVALHO
LIMA
SOUSA
MELO
RAJA
AKBAR ABBAS
DAFITI
CONTABILIDADE
CONSULTORIA
GOYAL
GARG
AGGARWAL
AGARWAL
SHAIKH
SRIVASTAVA
RANA
NAWAZ
AHMAD
JAMIL
GRFICA
FISCAL
FINANCEIRO
CHOPRA GOEL
SAXENA
JHA
KHAN
SALEEM
RASHID ALI HAMEED
NOOR
ARTE
PESSOAL
COMERCIAL
KHANNA
AGRAWAL
GUPTA
TIWARI
ARIF
HUSSAIN
REHMAN
EVENTOS
COMPRAS
ASSESSORIA
RH PORTO
MELLO VIEIRA
LOPES
COSTA
AZEVEDO
CONCEIO
MAGALHAES ALENCAR
CHAVES
SENA
FRANCA
CORRA
GUIMARAES
ALVES
BASTOS
ARAUJO FREIRE
FARIAS
VELOSO MOTTA
BR
BERNARDES
TEIXEIRA
SOUZA
FREITAS NASCIMENTO
BARBOSA LEMOS
MOTA MACIEL
MATTOS
FERREIRA RIBEIRO MARQUES
GOMES
ALMEIDA
SANTOS ROCHA
BRITO
GUEDES MOREIRA
MARTINS
GONALVES
CARNEIRO
SILVA
ANDRADE
ESTEVES
BARRETO
ASSIS
ALVARENGA
RODRIGUES
PIRES BORGES MACHADO
CAMARGO
ABREU
PORTELA
BARROSO
DAMASCENO
FRANA
CORDEIRO
CARDOSO
NUNES
DIAS
BRAZ
BATISTA LOBO BARBOZA
SANTANA MATOS
SALLES
CANDIDO PEREIRA
TAVARES
AGUIAR
TRINDADE PINTO
GONZAGA
FONSECA
SILVESTRE
BUENO MUNIZ
FERRAZ
XAVIER
PASSOS
NERY
HENRIQUES
MAGNO
TEODORO
PRADO
PIMENTEL
BAPTISTA
FERNANDES
VAZ
COUTINHO
JNIOR FILHO JOO
DUARTE GASPAR
DOMINGUES
SATO
VILELA JUNIOR
TADEU GERALDO
HENRIQUE
SABINO
BRUNO
PAULINO CSAR
MATIAS
CORREA
MUNICIPAL
SEGUROS SADE
DA
ARORA
SHETH
PARIKH
SETHI
PANDEY
USMAN
JAMAL
YUSUF
AHMADI
HUMANOS BARATO
REGIONAL
NACIONAL ADM
GRUPO
DO
KAPOOR PAREKH
MORE
MUKHERJEE BHATIA
VERMA
YADAV
RAI SHRESTHA
AMIN
RASHEED
LATIF
AZIZ
MUHAMMAD HABIB
DIGITAL
PARA VIRTUAL
SECRETARIA
MOHAMMED
MOHAMMAD
HASSAN
ABDULLAH MUSTAFA
TAHA TOTAL SOCIAL
EM CONCURSOS
CHAGAS
SAHA
JADHAV
5 SHARMA
ANAND
PRAKASH
KAMAL RAHIM
SALAM HADI
ISMAIL
IBRAHIM
SAAD
SANTO
SANTA CENTRO
NOVA
SO
ABDUL
AMIR MOHAMED
HUSSEIN MOSTAFA SALAH
AR
CIA
SANTANDER
BAHIA
GHOSH
PATIL
SHUKLA
SAINI
SINGH
DAI
AHMED
FASHION
LOOK
INVESTMENTS
SEN
PAL
NAYAK SONI
MEHTA
PATHAK
CHAUDHARY
CHANDRA CHOWDHURY
ISLAM ZAMAN SAYED
MOHD
OSMAN
SALEH
PR
VERDE RJ RIO
TERRA
MONTE
ALAM
HASAN
STUDIOS
YORK
LIFE UNION SKY
KULKARNI
MALHOTRA
THAKUR
KUMAR
MOHAN
MD
MUSA
SALIM
ABU
GAMAL
SEGURO BH
ITA
CONTATO
SP PS
ABD
NASSER
KHALIL
ADEL
VISTA
SC NA NO LOJA
VIDA VALE
BRAZIL
MAHMOUD
AWAD
SAMIR
YOUSSEF
POSTAL
PAI
VIVO NOVO
AP LINHAS
GANDHI
DESAI TRIVEDI
SANDHU
RAJ
LAL CHAND HOSSAIN
HAQUE UDDIN KARIM
HAMID
NAIK
IYER
SHAH
PATEL
VYAS MODI
KAUR
RAM DEVI
RAHMAN
JI
HALIM
SAID
SALEM
SOLIMAN
PC
OI
TIM IRM
FACUL
MODAS
REZA
ABDALLAH FARAH MANSOUR
BIS
PM
ESCOLA
CUNHADA
FACULDADE
SANCHES
PANDYA
CHAUHAN
SHANKAR REDDY
KRISHNA BABU
INDIA SIR
BHAI HAKIM
DUBAI
DIRECT CONNECTION
LIMITED
DUTTA
THAKKAR
PRASAD SONS
JAN UNCLE
SB
CH
SH
PARMAR
RAO RAJU
TRAVELS
VISA
AC
COM
BABA
MAT
AS
ABDEL
HADDAD
TAXI HOTMAIL
CLARO
PRIMO
PRIMA
PROF
FARIA VILA
FERRARI
APARECIDO
LUIZ
ANTNIO VITOR
GUILHERME ROBERTO
ELIAS
DOMINGOS
VEIGA VINICIUS
ROGERIO RENATO
MARCOS
MARCELO
VICENTE
ANGELO
CESAR
BRANCO
JOAO
PEDRO
AUGUSTO
RICARDO
JORGE
JOS
JESUS DE
EVANGELISTA BERNARDO
CARLOS JOSE
FRANCISCO
EUGENIO
DONATO
RODRIGO SERGIO
LEONARDO MIGUEL LUIS
HUGO
EDGAR
AL ISSA
BB
BANCO
AMIGO TIO
TIA
CAROLINE
SIMES
BIN
SRINIVASAN
RAVI MANI
PERSAUD DSOUZA
EDU
RAJAN
KRISHNAN
APPLICATIONS
MAHARAJ
SEQUEIRA
GOV
SM
MOHAMAD
SUBRAMANIAN
CONFIRMATION
DEPARTMENT
US NVC
IMMIGRATION NET
ORG
CA
ENTERPRISE
BINTI
BHATT
NOTIFICATION
BLOCK DEPT
MAILBOX
ADMINISTRATOR OFFICER
GONSALVES CS LAB
ENQUIRIES CO
OMAR
EL ROMANIA
CLIENTE
CASA AMIGA
ALICE ALINE
ROBERTA RENATA
DIRECTOR
TECHNOLOGY AUSTRALIA
MOB
MALAYSIA BT
MEU
MI AMOR
CEL IRMA
FLOR FLAVIA LUIZA
SIMONE
SALA CAMARA
ANCA MARIUS
CRIS
PASTOR
KARLA
PAULA
CARLA MARCIA
CARMO
MOBILE
PHILIPPINES
ORLANDO
COMPANY KARMA
SYSTEMS
TARGET
JOSHI
CRUISES
CARD
RESEARCH
AID
MATHUR
CHARTERED MISTRY
PANCHAL
BENEFITS
INFORMATION
COORDINATOR MANAGER
ASSISTANT
SECRETARY AT OFFICE
DESK CLIENT
WARRANTY
CBN
MAMA
KA
MANAGEMENT
ADMIN STAFF USER ACCOUNTS ACCOUNT DEPOT
ADVISOR
BOUTIQE
CC
MAM
MM
KAMARA
ADRIAN
CLIENTES
TRABAJO MARI
LIVRE
RITA
CLARA LCIA
IONUT
CRISTIAN
NUEVO
SRL LIBRE
CELIA CLAUDIA
CRISTINA HELENA
APARECIDA
ALEXANDRE
ANDR
LEANDRO FELIPE
FERNANDO ALBERTO
EMILIO
OLX
PATRICIO
FELIX
ARGENTINA
ELISA
CAROLINA LUCIA ROSA
REGINA
STEFAN
BIANCA
HIPOTECARIO VIAJES
RAQUEL MARIA
THIAGO
FABIO MAURICIO HUMBERTO
ALFREDO
ADOLFO MATEO
TOMAS POLO
LEAL NERI
MATEUS
RODOLFO
RAMON
FERRER SORIANO
SALVADOR
MARCO
MANUEL
GERARDO
ERNESTO LOBATO
LIRA
ANDREEA ANDREI
CON
EN ADRIANA ANTONIA
BEATRIZ
LUZ
CAMILA JULIANA
REGIS
ANDRE
BOSCO
DIEGO
ENRIQUE
ARTURO
VILLAR
BRIONES
CAMPOS
RANGEL FRANCO
RESPUESTA
VENTAS ANA
LETICIA
KARINA MARA
FERNANDA
CARDOZO
DANIEL GABRIEL
VICTOR
ACCOUNTING SALES
REGISTRATION
CALL
BUSINESS MALL
PRINTER
PA PAPA
PILLAI
BLOUNT
CASH GROUP
CONTROL
INNOVATION
FRESHDESK MENON
NAIR SERVICES
LOAN
WEB PORTAL
USA
CONTACT
AM
FR
RELATIONS ASSISTANCE
DELIVERY
RECORDS
DUKES
MOON
WEATHERS HARDWARE
PTE CREATIVE
ELECTRONICS
MAILER
MORNING
HUNTERS
ALERT
ALERTER
CALLOWAY
ENERGY
REWARDS TODAY
PHOTO COSMETICS MART
SHETTY
REPORTS
LUNDY
LEGGETT
SHOESOURCE
ENTERTAINMENT MARKETPLACE SWEEPSTAKES
GAMES CASINO
CHECK
HELP
PAYROLL
CORPORATE TEAM
ADMINISTRATION
OPERATIONS
CENTER
CAN
VIP
HOTEL HOTELS WORLDWIDE HHONORS
BER
SAMSUNG POP
HR
RECRUITMENT
HELPDESK
CONNECT
NOW
LINE
CENTRE
MAIL
SA MLLER
AG
SORIN IOAN
MARIAN
CONSULTANTS
SOLUTIONS
PLUS
PRO
SOURCE
BALANCE
RENT PREMIUM
NETWORKS
BA ORANGE DIN
ADI
VLAD IOANA
ALL
SPORT SOLAR
YAHOO GMBH
DIALLO
RO
OANA
ALEXANDRU
CATALIN
SHOES
PRINT
GO
GMAIL MILAN MAX
CONSTANTIN
MIHAI
NICOLETA
SHOP
TOUR TOURS
REAL
PERSONAL
GERMANY
FRIDAY
ALEX
GABRIELA ESTER VALERIA
JOEL RENE EMANUEL
HECTOR AGUSTIN
FIT
MED
UNITED CANADA
CONVERSE
POPA
BOGDAN NICOLAE
ALINA
MARTA
EMILIA SUSANA
NATALIA
GIMENEZ
LTDA JESS DAMIAN
SEBASTIAN
CAFE
REPLY
PARIS
FRANCE TOMA IONESCU POPESCU
VASILE
MIHAELA
ION
YOUR IS
STRONG
HILFIGER
QUIZ
ALERTS UK
INQUIRY
EDGE
MILTON
JEFFERSON
MAYO
LYLES
RESOURCE
PAYMENTS
REWARD DEVELOPMENT
SERVICE
RETAIL CARE
BOLDEN
SMALLS
RESOURCES
NETWORK TEST
ONLINE INTERNET
BILLING
SCRIPTS
REN
SUN
MCCRAY
RIGHTS
CYCLES
JOBROYALTY MICROSOFT
POSTMASTER ZENDESK
CAREERS RECRUITING
DIGGS
RUFFIN
BRICE
MELL
XIONG
GAL
NAVY
OPINIONS
LP
NEWSLETTER
ORDER
EMPLOYMENT
ADVANTAGE
HARDY
STEWARD
WASHINGTON
VANG
BOWLING
INTERACTIVE
CUSTOMER
NOREPLY
STAFFING
TRAINING
CAREER
IT
INTERNATIONAL
HUMAN
EARL
HURT
BO
STORE
GAMING
CORPORATION
ATLANTA WEBMASTER
SUPPORT
DARDEN
ALSTON
HOLLIS
THI
PAR
MO
TEE
CRUISE
BGOSH
SEED
CUSTOMERSERVICE TECHNICAL
JOBS TECHNOLOGIES
GLOBAL
MARKETING
LEGAL
CAPITAL
BY FOR
UP
HANDY
AN
LO
LOUIE
TOOMEY
PHARMACY
INVESTMENT
OBAMA
PAYTON
PERSON
ANH
CHI
MAK
GAMBLE
NEWSLETTERS
RECIPIENTS
PROMOTIONS
TRADING
CONSULTING
TV
ON
IN
STUDIO
MASTER
RADU
RAMONA
SIMONA
LAS
GRACIELA
MABEL COLOMBIA
GIRALDO
DUQUE
GARZON
ANDRS
FABIAN RUBEN
DU
ED
TE
MATEI
ILIE GHEORGHE
SI
ROXANA
MARIANA
LOS
NOEMI
JAIRO
BUITRAGO
OSPINA
PATIO ANDRES
MACRI
ARIEL
JUAN OSCAR
PETE
TUDOR STAN
DUMITRU
BELLA DANIELA
LA PLAZA
SILVIA
SOLEDAD
INES
MARINA
SAS GALLEGO
RESTREPO FLOREZ
ARANGO CAICEDO
FEDERICO
INS
FLORIN
CECILIA
DEL
STELLA MILENA
PAEZ MOSQUERA
POSADA
HORACIO
HERNAN
RAUL MARIO
PABLO
SOFIA
MARCELA JOHANNA
PARDO
MESA
DARIO
IGNACIO
LORENA
ANDREA
SARMIENTO
CARDONA
PALACIO QUIROGA PEREYRA MARTN
DIEZ
CAMPO ESTEBAN
ARMANDO
TOLEDO
PACHECO
GUERRA
JAIME
CARRERA CARO
VILLANUEVA TRINIDAD
RAMOS
PANTOJA
ROCIO VIVIANA CIFUENTES
VIVAS SANABRIA BERMUDEZ
REY
ROA ALDANA
CARVAJAL VILLALBA CORONEL
GUILLERMO
ALEJANDRO
SAN
LIDIA
THE ME
DESIGN
TOP
LAZAR ADAM
DANA
DIANA
MAR
GRANDE
VIRGINIA LAURA
NICK DAN
TOM
DAVE
MAS
SONIA
SOL
DELIA
LUISA
BELEN
EUGENIA
BAR ANSWER NAME
KWOK
TSANG
TAM
NOT
ONE
EVENTS
AGENT FINANCE
LOGISTICS
LUI
YEUNG
CASUALTY
FREIGHT
SURVEY
INFO
PICKENS
EPPS
FOREMAN
THANH
AU
DONOTREPLY LIVE
DEALS INSURANCE PARTNER
BYNUM
GAINES
MIMS
STARKS
HAIRSTON
CAO
PARHAM
SMILEY WOODSON
NORWOOD
BATTLE
MINOR
PAIGE
CHANEY
IVY
MA
SOFTWARE
LEISURE
FOOTBALL
NEWS NIGERIA
PARTNERS
HOOKS
BOOKER
LAMAR
SEALS
JAMISON
DOZIER
NICOLE
SU
ASHLEY
FARGO
DEBT MEMBER
MEMBERSHIP MICRO
FACTORY
CLAIMS
TRANSPORT
4 2
PERMANENTE
LIST
OF
TRUST FRIENDS COLLECTION FIRST
SLAUGHTER
WESLEY
TA
BUI
AIRLINES
CLEARING
WITHIN
EVE
OUTLET
NOBLE CORP
SPECIAL
DOAN
DINH
CLAY
RANDLE TERRELL
JOYNER
RANDOLPH
HILLIARD
CLEMONS
HARGROVE MAYS
FIELDS HEARD
MCCLENDON
DONG
LE
LAM
CHEUNG
TSE
KORS
LYMPHOMA
XM
MUSIC
PRODUCTS
LTD
ZONE
AGENCY
ELECTRIC
YIP
KWAN SECRET
FITCH FASHIONS
SERVICING
CLOTHING
PARTS
REPAIR
SAFETY COMPUTER
YOU ART
BOX
EMAIL
COOL
DJ
BOB
BILL
CARLO
ERIKA
NORA OLGA
JULIA
VERONICA
ANGELICA
ELENA
MATHEW
AA
TOPS
VIDEO
ROOM TIME
MAIN
CHAN
FONG KIDS
LOANS
RIVER WIRELESS
COMMUNICATIONS
WILDLIFE TRAVEL VISION
SPORTS
TECH SHIPPING
CAR REALTYTRAC
CREATIONS
CREW
SPA
PHONE
VARGHESE MAC
RON
RANDY JIM
SGT
EVA
OLIVIA MIRIAM CARMEN
LOURDES
DOLORES TERESA MAGDALENA
ROD JIMMY
JOE ROB
JEFF RICK
DOUG
CIV
ANGELA SANDRA
IRENE
IRIS ESTHER
VICTORIA ISABEL ALEJANDRA
LUCA
PAOLA
ESTEVEZ
OVIEDO VERGARA
PRIETO
ALBA
VERA
ZAMBRANO
SOLER
IVAN
CATALINA
LILIANA
TELLO
QUEVEDO
TERAN
NARANJO
GIL
ALFONSO
GERMAN
SAAVEDRA
MANZANO
ALARCON
NARVAEZ GRACIA
JARAMILLO RINCON
URIBE
JULIAN
BUSTAMANTE
CEPEDA
BELTRAN
HURTADO
GARCES
PARRA
CONDE BALLESTEROS
GALVEZ
PALOMINO LEON
ESPINOSA MONTOYA
SALCEDO
CADENA
QUINTERO
BEJARANO
JAIMES
PEREA
VALLEJO HOLGUIN
VILLA
BECERRA PULIDO
TRUJILLO
TOVAR
VALENCIA
ENRIQUEZ
VENTURA
CASTRO MONTENEGRO
PEDRAZA LEDESMA
ROBLEDO
CASAS
MORENO
LOZANO
SERNA
NAVARRETE
ARENAS
VILLEGAS
TAMAYO NIETO
BERNAL
RUBIO
RICO
BAUTISTA
ARTEAGA
GUERRERO BENAVIDES
BARRERA
RENDON CUELLAR
MONROY
VELASCO BARBA
OROZCO
SALAS OCHOA
QUIROZ
AVALOS
YANEZ SOTELO
TELLEZ
NOLASCO
MENDOZA
CARDENAS SALAZAR
ARAGON CERDA VENEGAS IBARRA
GALINDO
ZARATE
MAYA
ROJO
ANGELES
MARVIN
MICHELLE
PAMELA SARA NINA
MARTHA GLORIA
MONICA
ALEXANDRA
VANEGAS PATRICIA
VAL
NORMA
ESTELA ALICIA
MERCEDES
KATHERINE
ESPERANZA
CYNTHIA
MELISSA
ANNA
EDITH
FABIOLA
MARGARITA TATIANA
RUEDA BELLO CORDOBA
TONY
MIKE
KEN
KIMBERLY
JESSICA
EVELYN
ANITA
YOLANDA NELLY VANESSA
ANGEL
OLIVERA
CHRIS GREG
STEVE
JEWELRY
RESTAURANT
RESERVATIONS FREE
NUMBER
ANG CHUA
WING SCOUTS TEEN FOODS
RACING
GOLF MARKET
GAME MAGAZINE
CHOICE TALENT CONSTRUCTION
PAN
HOANG
MAI
FUNG
SIM
IP
INCORPORATED
TIRE
CONSUMER SALE
ENTERPRISES
PRODUCTIONS
AIR AUTO
MOTORS
PHAM
VO
CHOW
LEUNG
WHITNEY
SEATS
KENNEL
FRIENDFINDER PRESS
ASSOCIATES
HEALTHCARE
WORLD
BOUTIQUE
JOB
BABE
PHILIP
SUPPLY
PUBLISHING
DAIRY
CANCER EXPRESS
PROGRAM
ENGINEERING
ACADEMY
RENTAL
GRAPHICS
NATION
SALON
HUBBY
HONEY
JACOB
JON
MATT
DON CARL
TIFFANY
STEPHANIE AMANDA LUCY
SABRINA LILIA
GUADALUPE PEA
CASTAEDA
MUOZ
ALONSO
RIVERO
FERNANDEZ
TAPIA
GINA
CHRISTINA
MARLENE
PIA JUDITH
SUREZ
ROS
IGLESIAS
MERINO
CORTES
RUTH
ELIZABETH
GARCA
GMEZ
PREZ
DAZ
VARELA
CASANOVA
BUSTOS VALDIVIA
ESTRADA
MEZA CARRILLO
OLIVARES
DELGADILLO
COLIN
GALICIA
MENESES
ALONZO
SANTILLAN
MONDRAGON
ROSAS TREJO
HUERTA
ANAYA
BARRAGAN
MEXICO
VIDAL
LIZ
SNCHEZ GUTIRREZ
LPEZ
FERNNDEZ NUEZ
BLANCO PINO
AGUIRRE
GRANADOS
CAMACHO
TENORIO
BRIAN
JERRY ALAN FAMILY
REBECCA
WIFE
ABRAHAM
GEORGE LARRY
ROGER
JENNIFER SARAH
DAUGHTER
SAMUEL
FRED
SEAN GARY
KEVIN
SINGLE END
BIBLE EAGLE
DIABETES
EDUCATION INSTITUTE
MEDICAL
ELITE PRINTING RENTALS
DESIGNS
BODY
PHAN
VU
YUEN
YAP
RIVERS
GASTON
DERRICK
RENEE
TRINH
BRUNSON TOLBERT
RICKS
MCNEAL MCCLAIN
VANN
MACK
MOSES
LU
DAO
LAU
ONG
LOCKHART
LIANG
CHOU
HOLLEY
HAMPTON
COLEMAN
WYNN
RANSOM
COLBERT
LOVELACE
DILLARD
PEOPLES STOVALL
DICKERSON HARDEN DORSEY DANIELS
FRAZIER
SMALLWOOD
WHITFIELD
XU
ZHENG
LI
YAN
CHIANG
NGUYEN
WONG
NG
TAN CHING
APPAREL
RED ASSOCIATION
FOUNDATION
PROPERTY REALTY HOMES PHOTOGRAPHY
FITNESS
BEAUTY HAIR
FOOT
LASER
SOCIETY WATER
PROPERTIES
DANCE
SUPER FUN
HAPPY BABY
HUT
GENERAL
BOARD STUDENT
HEART
TAX SOCCER
COACH
CHILD WITH
GYM LOVE
HUSBAND
UNDERGRADUATE
PRESIDENT
HOUSING MORTGAGE MUTUAL
CASTING
FURNITURE
LINK
ALUMNI
ADMISSIONS
LIBRARY
YOUTH
LEARNING
POOL
BUS QUEEN
CRYSTAL
MARK ANDY
UNIVERSITY FINANCIAL
BOOK
PET
WAREHOUSE
VA
BIG
MOTHER
BOO
SHAWN
RAPHAEL
FIRE
LIVING PARTY
LADY
CAT
SIS BRO
SISTER BROTHER SON
ERIC
EMILY
DEBORAH RACHEL
OLIVA
MARTNEZ HERNNDEZ
GONZLEZ
ROCA
GARAY CEBALLOS
CANO
EMMA
MNDEZ RAMREZ
NEZ
MARIN
BRAVO
QUEZADA
GOMEZ
GAMBOA
JIMENEZ
GUTIERREZ RAMIREZ
VZQUEZ
GUZMN JIMNEZ
RODRGUEZ
JARA CARRASCO
PONCE
HERRERA
CONTRERAS
AVILA
CHVEZ
ACUA
ROJAS ECHEVERRIA
SORIA
CABALLERO
SANCHEZ
ROSALES
BARRAZA CISNEROS
SUSAN
JENNY
DORIS
STEVEN
JUSTIN KENNETH
AMY
YOGA
GIRL
BOSS MOM
WORK CUZ COUSIN
GLEN
RONALD
STACEY HEATHER
WENDY
JANICE
TINA SYLVIA
ABEL LEN
MOYA
HIDALGO
ALTAMIRANO HEREDIA LINARES
CASTILLO
REYES
CARRANZA
FIERRO
CORONADO CASTANEDA
KAREN
JACKIE
SHEILA BARBARA
SAUL
MONTERO ARIAS
PAREDES
PERALTA
INFANTE ROMERO
TEJEDA
ULLOA
CORNEJO
PALACIOS SEGURA
GALLARDO
DOMINGUEZ
MARQUEZ
SANDOVAL
VALENZUELA
LEIVA
MENA
ESCOBAR
BARRIENTOS
RUIZ
MARTINEZ NAVARRO
ESPINOZA
ZAMORA
MACIAS
ZAVALA
ARRIAGA
ROMO
VALADEZ COTA
GARRIDO
VALERIO
SOSA
LOPEZ
GARCIA
HERNANDEZ AGUILAR
ESPINO
PUENTE
CORTEZ
ARELLANO
JUAREZ
BARAJAS
BANDA
PINA
BARRIOS SEGOVIA
ALVAREZ
CALDERON
GUZMAN DURAN
FLORES
ESCALANTE ARANDA LARA
REYNOSO
CARBAJAL
MARY
MICHELE
ELAINE
DIANE
LISA
CATHY
JANET
DENISE
CALDERN ZUIGA
JONATHAN
JILL
CONNIE CHERYL
BRENDA
CAROL
THERESA
MONIQUE
ARAYA
SANTAMARIA
LORI
JULIE
TAMMY
PAM LINDA
CHRISTINE
SOPHIE DANIELLE
ANGULO
DONNA
SALLY HELEN
LAURENCE NATHALIE
MORA
VARGAS
PARADA
ARANA SUAREZ
ACOSTA
GONZALEZ
SOLIS MATA
CORRAL
MUNOZ
MOLINA
BENITEZ CABRERA
PEREZ
ORTEGA MONTES
PADILLA VALDEZ
SAENZ
PORRAS
ARCE
PAZ APARICIO
BETTY
FLORENCE
ISABELLE DES
CALVO
ALFARO
PALMA
AGUILERA
ALAIN
ET
VALVERDE MONGE SOLANO
MADRIGAL
VILLALOBOS
GUEVARA VALLE
ZEPEDA
LUNA
GODINEZ
RODRIGUEZ
FUENTES
NUNEZ
ALCALA ZUNIGA
SALINAS
ELIZONDO
MORALES
MENDEZ
NORIEGA
ESTRELLA PENA MEDRANO GAMEZ
ARREDONDO
ESCOBEDO
DIAZ
VEGA
MEDINA
CARMONA RIOS
ROBLES CUEVAS
MONTANO
GALLEGOS
MAGANA
DELGADO AYALA
TORRES
DAVILA
VAZQUEZ
CASILLAS
MADRID
BACA
OJEDA
SOTO ROLDAN
SERRANO
ARROYO
VELAZQUEZ
PADRON GALAN
DELEON GONZALES
RENTERIA
URBINA TEJADA
QUESADA
MURILLO
FAJARDO
MENENDEZ
VALDES
MILLAN
ORTIZ
MALDONADO OTERO
MERCADO CONCEPCION
VIGIL
ESPARZA
QUINTANA
MOJICA
AVILES
MARTEL LUCERO
LUJAN SALDANA
ESCAMILLA
CORDOVA
FALCON LEFEBVRE
VALENTIN
ALLARD
REYNA YBARRA SAUCEDO
CHAPA
GUILLEN ALEMAN
VASQUEZ
GALARZA
RIVERA
ROMAN
FORTIN
GARZA VILLARREAL
CAVAZOS
QUINTANILLA POLANCO
FIGUEROA
TREMBLAY LEVESQUE
GALVAN HINOJOSA
TREVINO BARRON
SEVILLA
AMAYA
MAN
SCHOOL
EYE PARENTS
GUY
BOY ICE CELL
DAD AUNT
PERERA FRANK
BEN JACK
JASON
LOW
TRAN
CHIU
LAI
LIM
MEDIA
BARN
TU
HUYNH
DANG
ZHOU
WANG
LIU
HUANG
TRUONG
DUONG
BANKS
REESE
TROTTER
HICKS
TILLMAN
BOWIE
ERVIN
BOYKIN
BRYANT
FLOWERS
WINSTON COLEY TYSON LOCKETT YAO
HE
POLK
DUPREE TIMMONS
WARE
MAYES JENKINS
CHERRY BONNER
TINSLEY MCNAIR
GREENE COTTON
SHI
ZHAO
MATHIS
ASKEW LANGSTON WILBURN
BOYD CURRY GRAYSON
STOKES
TOWNSEND
GAO
ZHANG
RUCKER
MEEKS CRENSHAW
MONTGOMERY HOLLOWAY
FORD
DOBBINS
WADE
DALLAS
FAN GUO
ZHU
HU
CHEN
WU
LIN
LUU
NGO
LY HA
TONG
CHONG
KOH
GOH
FRIEND
AUCTIONS
TRIBUNE
ANIMAL
HOSPITAL
TEACHER
CLASS
BEAR
AKA MY
DRIVER
NANA VIA
FAITH
CLINIC
DOCTOR LAST
DOLL
LAWYER MENSAH OWUSU
ISAAC
WILL JOHN
MICHAEL SAM
ROBERT
CHEE
BUY
NATIONAL
FOOD
HUNG
PANG
DAILY GYMBOREE
PUBLIC COLLEGE
POLICE DOG
FROM
DEE
DIZON
SY
TROY
PETER WILLIAM JOSHUA
HOLLY
YEE LEONG
YONG
KEE
HERTZ
VITAMIN
HEALTH
MOTOR COMMUNITY
THAI
ENG CHEW
SEE
FEEDBACK
TALBOTS
COMFORT
RESORT
DENTAL
PIZZA
NEW
FORTUNE
SAMSON
ANDREW MATTHEW
TRACY
DAVID
ANGIE BONNIE
CINDY
FRESH
LAKES LLC CLUB
INN
PLACE
SPORTSMANS
HSU
LUONG
HO
CHIN
CHUN GEE
ORDERS
MATERNITY
WINE
LEASING GRAND
FARM
DADDY
BEE LONDON JOY
STEPHEN DICK
SUE
SHERRY BECKY
CAROLYN
CHRISTOPHER
JEFFREY DAWN FAYE
PATTY
GAIL
KATHY
PAT
RICHARD
PAUL
STACY
AND
ANNE JUNE SHIRLEY
DEB
JUDY SANDY
DEBBIE
PATRICK
BETH
SHEETS
KATE
BARB
PEGGY
SHARON
DELA DONALD
NAGY
DESMOND SHARE
JANE
MARGARET JEN
NANCY MARILYN
EDWARD
ELLEN
KOVACS
WARNER
WINNER RUBY
JOYCE
JOAN
LAURIE ROBIN
YVONNE
GRACE
WAYNE ANTHONY CHRISTY
SZABO
BURDICK DIETRICH RAYMOND MARIE
FRANCES JOANNE
SUZANNE
LOUISE
MARION
AARON
HARRY
MOLNAR TOTH WALTER
VINCENT
ALBERT
REA
LOU
FRANZ
KARL
EDDY COREY
ALFRED
JEANNE
ANNIE
APARTMENTS
TOWN
LOTS
MONEY
JAY
SOUTH
GARDEN ARTS
PEOPLE
BROTHERS
DOE NURSE
LEE LAY
HERITAGE
FLOYD
HOUSTON
GLOVER
GRIER TYLER
KNOX
JIANG YANG
FENG
MONROE
FRANKLIN
BELLAMY
MIDDLETON BETTS
JIN
FU
COATS
BOONE
HINES JACKSON
BUTLER WILLIS
EDMONDS BOSTON
YI
SHEN
TSAI YU
MOSLEY BURKS MCGHEE
GOLDEN
SINGLETON
SIMMONS
BULLOCK
SONG
KANG MIN
LAN
REAVES
JETER
MAYFIELD
BARNES
MYLES
HAN
PENG
FANG TANG
TAI
CHAU
HENLEY GILLIAM
BRANCH
HARRIS
PUGH
MCNEIL
CLOUD
CHU
WILDER GOINS
NEAL
JONES
MCQUEEN
CAMP
CHANG CHENG
YEN
HAYNES
STUBBS AMOS
JOHNS
HWANG
CHAO
MING
WAN HUI
KONG
WEI
AMERICA
PAK
PARK MEI
LING
SPAIN
GIVENS
BASS MOBLEY
SNEED
GIPSON
ROBINSON
HOLMES POLLARD
SYKES
OLIVER
CAVE
SAMPLES
FIX BEAN
BRANDS
WOO
FREECYCLE
CREDIT
THOMAS
PRINCE
COLES
FINNEY ASH
SEARS SFPPDRAFTAUTHORIZATION
GUEST KO
WOODARD
TATE CROWDER
CARTER
HINTON
ALEXANDER
MCRAE
GILES
AMAZON
CARIBBEAN
CHUNG HONG
KROGER
PSYCHICS
JAMES
ADDISON
RIDLEY
DYSON
HARLEY
MILES
TEMPLE PALM
OH
YOON
FORT
ODOM PITTMAN
KEYS
WOODS
WILLIAMS RICHARDSON
LEMON
CRUMP GANT
HERRING
OWENS GARRETT
COPELAND
INGRAM
BROOKS
LEWIS
NORMAN
CUNNINGHAM
STEVENSON
SPEED ROYAL PEACE
FAIR
COUNCIL BRIDAL
SECURITY
WALGREEN
TO
CALIFORNIA
COURT
ROAD
GRILL
BURNER LAW
MAE
BRANDON
BEVERLY
JO
ANN
GROVER
SCHERER
HURD JOSEPH
CATHERINE
WAY
STYLES
FLORA
BELLE
ROSE
HAYWARD
ROWLEY
KAY
DARLING
HILDEBRAND
ROLAND CLAIRE
VALERIE
AJAYI
KINGSLEY
LYN SHANE
NICHOLAS
ROYER
CHARLES
JEROME
CHACON
CHAVARRIA
OSORIO
AREVALO
DENNY
KEYES
AUGUSTINE
DOMINIQUE MARC
PHILIPPE LUC
PASCAL
CASTELLANOS
ALVARADO
VIERA
TIRADO
MELENDEZ
BOUCHER
LAVOIE
BOUDREAU
ALANIZ VELA LONGORIA
CANALES
SIERRA
ACEVEDO
LUGO GIRARD
BELANGER
COTE
BEAULIEU
MEJIA SALGADO
SOLORZANO
LOZADA BERRIOS
BAEZ
MICHAUD
CYR
PERDOMO
PINEDA
VELASQUEZ
RIVAS
MAYORGA BETANCOURT CORDERO
FOURNIER
SANTIAGO
NADEAU BOUCHARD PELLETIER
BONILLA
SEPULVEDA
TORO
RICH
PERRIN
HERMAN KURTZ
EUGENE
JEAN
JULIEN
CLAUDE CHRISTOPHE
MARCEL CORRALES
SIMON
BRENT
BRETT
HODGSON
BEAUCHAMP RAND
BERNARD
GEORGES
LAURENT
MICHEL OLIVIER
SALOMON
CACERES ORDOEZ
LOUIS
ETIENNE
PIERRE
LEROY
MATHIEU
NICOLAS DENIS
ANTON MONCADA
RENNER EMMANUEL
BAPTISTE
MOREL GERARD ROMEO
NAVAS
LAZO
ORELLANA
AUGUSTIN
SAINT FRANCOIS
DURAND
MARIS
HENRIQUEZ BARAHONA
VALLADARES
GIRON
SCHELL
NOE ANTOINE
ALEXIS
LAGOS
DI ANDINO
ARGUETA
ZELAYA
WAGNER
ST
NOEL BERTRAND
COLOMBO
DELLA
RODAS
PORTILLO LEMUS
MONTALVO
CRESPO
LEHMANN
POST
JACQUES
MARTINI DAL BIANCHI
MOSER HAUSER
RING
PETIT
AYRES
BASSO
ROSSI
FONTANA BARBIERI
RICCI
MARROQUIN ESPINAL
AMADOR
BURGOS VELEZ
NIEVES
ROSARIO
DEJESUS
CONTI RINALDI
VIOLA
LOMBARDI
SANTORO
CONTE
TESTA
CENTENO
STEFFEN
SWARTZ HUBERT
ARENA
LEONE MANCINI
VITALE
STARR
MATHIAS
FORTE
ROMANO AMATO GENTILE
PELLEGRINO
PALERMO
ZAPATA
WEIR
POINT
STAR
SLOAN
REDMOND
JOLLY HOLIDAY
HOUSE
CHOI
STEWART
DUNBAR LLOYD
BIGGS
HAYWOOD
MARCH
LABEL
JUNG
CHO
MAG
WORKFORCE
SQUARE CITY
PARADISE
CLAYTON
DONALDSON KEITH
GIBBS RANDALL
SAVAGE TITUS
CHANCE
SOUTHERN
GAS
KIM
SHIN
AUTHORIZED
HOME
AREA
VILLAGE
TREE
MARINE
AMERICAN
VIEW
COAST
POWER
BACK
APPLE
SWEET
PENN
DUDLEY
BROUGHTON
CASE
BOURKE
PULSE
UPDATE
HIGHTOWER RUSH COLLIER
BLACKWELL
BRANTLEY
ELLISON SIMS
DAVIS
PERRY GREEN
GAY
NANCE
SEAY
ECHOLS
KEY MAYBERRY
MEANS
NEWSOME PITTS RHODES LOVETT
JOHNSON
HILL
DIXON SPENCER
CODY BURROUGHS
SCRUGGS
CHAMPION
ARRINGTON
TATUM
BLAND MCCOY
WIGGINS
MCKNIGHT
HOWARD
HENDERSON
BROWN COOPER
WHITEHEAD
CORBIN
FERGUSON
HUGGINS
FARLEY
VACATION
DASH
COUNTRY CENTRAL
POWELL DENNIS
PARROTT
FOY NESBITT
CABLE
BANK
RESORTS
RADIO
RATE CHEVROLET
NORTH
MIDDLE
FISH
SHELL SENIOR
MWANGI
SMART
GODFREY
ALLAN
BEATTIE
MCCALLUM
FORSTER
RALPH
ROBSON GARDINER
PATERSON
TURNBULL GOULD
BRAND
DEAL HS NATHAN
MARSHALL
MERCHANT
AIRWAYS
PREMIER
HONDA NISSAN
TOYOTA
HIGH ELEMENTARY
STREET
CHRISTIAN
FEDERAL
TEXAS
COUNTY
STATE POINTE
BAY
COOKE
HOOKER MADISON
SHORE EAST CHURCH
FLORIDA
FOREST
OAKS VALLEY
HARPER
WALLACE
LAWS
GOODE
SHARPE
LYONS BRISCOE
HEAD BLUE
BAPTIST
CREEK
MOUNTAIN
MCFADDEN
CARRINGTON
STEEL
LODGE LAKE
HILLS
SPRINGS
LAND
HAWTHORNE
THORPE EDWARDS
IRVING
PITT
BRIDGE GROVE LIGHT
BEACH RIDGE
WELLINGTON
ROCK ISLAND
RIDER
DELL
PHILLIP
BENJAMIN
NICHOLLS MILLAR
TAIT
MACKAY
HATCH
GOOD
LAUREN AMBROSE
ISAACS
FELTON AIKEN
MURRAY
BREWSTER
BROWNE
BLACKMAN
JARRETT
DOUGLAS
STOCK KITCHEN WILD
PENNY
LOGAN FOSTER
GREGORY GIBSON
JEFFERS
CARTWRIGHT
SAMPSON
SMALL CHAMBERS
WISDOM
HOPE
BEST
OR
BURRELL
DARBY
BLAIR
BAIN
CUMMINGS
PARRIS
CROOKS SIMMS
DAWKINS GAYLE
STERLING
WHEATLEY
WHITTAKER
ELLIS FLEMING
CHAPMAN
BURNETTE DOBBS
WOMACK ONEAL
JERNIGAN WHITLEY
DUNLAP
GRIFFIN
BELL
WRIGHT
MILLS
RILEY
DAWSON
GRAHAM
SEWELL
HAMILTON LAYNE
BOYCE
MCINTOSH
CHISHOLM
GORDON GRANT
LINTON
SAMUELS
HUTCHINSON
GOLDSMITH BURNETT
DUKE
LAWRENCE
SYLVESTER
HENRY
PLUMMER HYLTON
DALEY
FRANCIS
RODNEY
KAYE
PEARL
HERBERT
JOHNSTONE
HOUGHTON
GOUGH
MCCLELLAND
CLEMENT
SCHMITT
GOODMAN
TOBIAS
MULLER GRECO
RIZZO
LOMBARDO
BARONE BIANCO FIORE
GUIDO
PIZARRO
COLON
NEGRON
FELICIANO OUELLETTE
BOUDREAUX
BOSCH
KRUGER THOM
DEMARCO
RUSSO
LONGO
MAZZA CARRION
APONTE
ROSADO
PAGAN
FONTAINE
PARENT
GUIDRY ROY
CARABALLO
IRIZARRY
CARUSO
CARBONE
SALERNO
MANCUSO
DANGELO CARTAGENA
CINTRON
QUINONES
FERRARA MESSINA
MARTINO
DAMICO
GALLO DUMAS DUVAL
MOREAU
BARNARD
SHELDON
HARDER
TRACEY
PARRY LANCE
DAVIES
BOYER REITER
MUIR GRIFFITHS
THOMSON
MUNRO
DAVEY
HAMMER
HUMMEL
LENZ
DUBE
LAUER
DASILVA
PALUMBO
FERRARO ESPOSITO
MARINO
PARISI CAPUTO
COUTURE
RENAUD
DUBOIS
JONAS
DELUCA
DAGOSTINO
GIORDANO CASTELLANO
PEPE
MERCIER PICARD
DION
DUMONT
MACLEOD
MACDONALD IRVINE
BLANCHARD
SAUER
BURGER
MARX
WILHELM
KOWALSKI
LANDRY
MONACO
DUPONT
ROUSSEAU HEBERT
FINE CORMIER
LEVY
BENEDICT KRAFT
SELL EBERT
MOHR
BACH
MACKENZIE
SCHOFIELD
PEARCE
CHADWICK
HANNA
DREW
DURANT
ARCHER
BRYAN
HINDS
GREY
BLAKE
MCKENZIE
WHYTE
DRUMMOND
ATKINSON
MCAFEE
FOUNTAIN CLEVELAND BLACKMON WILKERSON TALLEY
JORDAN GLENN
PATTERSON
TURNER WALKER
BEASLEY
MELVIN
MOORE PERKINS
MITCHELL
ROSS
TONEY STRICKLAND
RAINEY
HAYES
FREEMAN
WILKINS
WHITE
HUDSON
WILSON
MARTIN BLACK
ROBERSON BULLARD
HASKINS
RODGERS
TERRY
ALLEN
HALL
YOUNG MASON
WESTON
BAILEY
VERNON
SLADE
SPRINGER WALTERS
FORRESTER
DOBSON MCPHERSON
SPENCE FORBES
RICKETTS MALCOLM
CHRISTIE LUCAS
LOWE
CLINTON
SHANNON
STEPHENSON
ROWE
MCFARLANE
ARTHUR
LAING
VALENTINE
FREDERICK
CAMPBELL PALMER
RICHARDS REID
CLARKE
RAMSAY
FRASER
NEIL
TOMLINSON
BARTLEY
WAITE MCLEOD BARCLAY
MCLEAN SALMON
SUTHERLAND
HEWITT
WATT
FORSYTHE
GILCHRIST NICHOLSON
GALE
SINCLAIR
KERR
CAMERON
LESLIE
ELLIOT
CHARLTON
TRAVIS
ALLISON
MCCAULEY GRANGER
HAYDEN
MCMULLEN
BOURNE PRINGLE
LINDSAY HAY
PARKINSON
SIMPSON
ATKINS
CHAPPELL
ASHBY WHARTON
RUSS
WILLOUGHBY
TAYLOR
SCOTT ADAMS
THOMPSON BARROW
REECE
VINSON
AKINS
SANDERS
TUCKER
AUSTIN
MATTHEWS
KING
SMITH
STEPHENS
COLE
GRAY
WATSON HIGGS
HENDRICKS
CRAIG
FLETCHER
MCALLISTER
MCDONALD
ANDERSON
ROACH
MORGAN
BENNETT
BURRIS
SPIVEY
HOGUE DOVE
JOINER
ROLLINS HOLLIDAY
FINCH
MCNEILL ROUSE
CRAWFORD
LOWERY
NEELY LACY
MEDLEY
POPE SPEARS
HUNTER NIXON
CORLEY
HUDDLESTON
GORE HODGES
WATKINS
PRYOR
HOPKINS
WALTON
NELSON
MORRIS HARVEY
WILEY CALHOUN
YANCEY
BYRD
GUNN
HANKINS REEVES
SCARBOROUGH
PICKETT
HORNE
CHESTER
HARRISON
MALLORY
KIRKLAND
VAUGHN MCCAIN
WOOTEN
RICHEY BLEDSOE
CALDWELL MASSEY
SLACK
BURTON
EVANS
ALFORD
COBB
HERNDON CALLAWAY
BRADFORD
REED
SWAIN
SHAW
COLLINS
MAXWELL
ROBERTS
DUNCAN
BINGHAM
CAIN
HAMMOND
ANDREWS
REYNOLDS
MCGILL
OAKES
BRUCE
WALDRON JEFFERY
AGNEW
BURROWS
WILLIAMSON
BRIGHT SALTER
SANDERSON
MORRISON
SAUNDERS ROBBINS LUKE
LACEY
HACKETT
MORSE
BRINK
ENGEL WAHL
HEINZ
BAYER
MAIER
ZIMMERMANN
MARR
FENTON
COTTRELL
THAYER
HOUSER
HAHN
HUTCHISON
SQUIRES
BALL
GREENWOOD
HOOK
TALBOT
BIRCH
MACLEAN
FULLER
CROSS
KENNEDY SANDS
MCKINLEY
WEST RUSSELL CARR
SHEPPARD BRIGGS
WEBSTER
KIRBY
HART BURGESS
HUNT LAMBERT
ORR
HADLEY DUNN
SADLER
WATTS
EASON
COVINGTON
BRITT
GOODSON
MCCOLLUM
PORTER
PARKER
BARNETT
PHILLIPS
HEARN
PRITCHETT BRANNON
STRINGER
DOTSON
FERRELL
BRIDGES
DOWNING
JEFFRIES
LAWSON
GARDNER
CHANDLER
WARREN
GILBERT
NUNN
YARBROUGH
WESTBROOK
HARRELL
BALLARD
MORTON DAVENPORT
WELLS
CURTIS
WARD
BUSH
KNIGHT
TODD
SHEPHERD
BRITTON
VAUGHAN ROPER
HUMPHREYS
WAUGH MAY
BAIRD
NEWELL
MCKAY
ROBB WHITEHOUSE
JAMIESON REES
ASHTON SHERWOOD
ROBINS
FABER VAN
KAISER
DECKER
HEIN
KELSEY
NEUMANN
FRANTZ ABRAMS
SOLOMON
AIRBNB MENARD
BERGERON
BERGER
KAHN
ROSENTHAL STEINBERG
LERNER
LEVI
SHANK BADER
BOURGEOIS
MARCUS MORAN
SCHWARTZ
BERMAN FREEDMAN
KATZ SILVERMAN RUBIN EPSTEIN KAPLAN
METZGER
BARON
ROSENBERG
LEVINE
SHAPIRO COHEN
COHN GUILLORY
ALTMAN
BENOIT CHAMPAGNE DAIGLE
SIEGEL
FRIEDMAN
SEGAL
GARBER LEBLANC
KAUFMAN STEIN
BERNSTEIN
WEINSTEIN GREENBERG
GOLDSTEIN
HOROWITZ
GOLDBERG
KOHN
STRAUSS WEINBERG STERN
FELDMAN
FISHMAN
GILMAN HIRSCH
HELLER
SINGER POLLACK
FORMAN
BRENNER
ACKERMAN
WEISS GROSSMAN
ADLER
GOLD
LEVIN WEINER
GOLDMAN
RICHTER
KRAMER
LEWANDOWSKI SOMMERS
SCHUBERT
WOLFF
SCHWARZ
GROSS
OTTO OSWALD
WENDT FRITZ
VOGT METZ
BERLIN
VOGEL RITTER
FINK
BLOOM
WOLF
KESSLER
SILVER
DIAMOND
GREENFIELD
HYMAN
ERNST
HERMANN SANDER
KRAUS
ROTH
MEIER
ZIMMER
HOFFMANN
STEELE
DALE
READ
MCGREGOR
PRITCHARD
REDMAN
CASTLE ROBERTSON
MOSS
STANFORD
DODD
WEBB
WATERS
MARSH
HOWELL BEAL
ROGERS
HOOD
DYER
WRAY
BURR KEEN
PARISH
HATTON
GODDARD
RITCHIE
HARDING
BARTON
WILLS
WILKINSON
HARTLEY
MCKINNON
MCINTYRE RAE
BARTHOLOMEW
BAXTER
EMERY
OSBORNE
COWAN
HOOPER
HOBSON
DAVIDSON
KYLE LOWRY
LORD KENDALL
DOW WINTER
CROFT MCARTHUR
HILLMAN THURSTON
LAIRD
DAVISON
BARTLETT TEMPLETON
HYDE
WAKEFIELD BROOKE
CLARKSON DICKINSON
WELSH
NAYLOR
SCHULTE
ALBRECHT
BEYER SCHULZ HERRMANN
WERNER GRAF
HERZOG
KUHN
KRAUSE
HAAS
SCHULER
MUELLER SCHMITZ
SCHNEIDER LUDWIG
HARTMANN
KRIEGER
SOMMER
BLANK
GERBER STEINER
KOPP
FUNK SCHMIDT
BAUM WENZEL BRAUN
LAWTON
MAJOR
CROOK
RUTHERFORD
CURRIE
HARWOOD
FORREST
FRY
PRESCOTT
BARBER
WEAVER
BRADLEY
HOLDER
MADDOX
MCKINNEY
FENNELL RAY
LITTLE
GOODWIN
FOWLER
CLARK
MACKEY
BERRY
BOWMAN MCDOWELL
HUMPHREY
BAKER
HAWKINS DICKENS
BRAGG
POOLE
KIDD
HODGE
SUTTON GALLOWAY DEAN
WHITAKER HORTON
CROCKETT CANNON
EVERETT
GLASS
HUGHES
BISHOP
MAYNARD
CARMICHAEL
RADFORD
PEARSON
PEACOCK
BIRD
SUMNER
SHELLEY
DENTON HOUGH
HARE
MARKS
MEAD
PETERS
NASH
BOOTH
PARSONS
SEYMOUR BARKER
WALLIS
WOODWARD
WILDE ASHER
RYDER
LYON
SOMERS
GILL
WEBBER
BULL BURT
SKELTON
FORSYTH
GIBBONS
JANSEN
EASTON
BECKETT
MANN
WHITING
WISEMAN
HARMAN
MEADE
SIMONS
DUTTON
MARTENS
MCKEE
HOWE
IRWIN
OWEN PRATT
BARR
SPRING
ARMOUR
OGDEN
MAURER KRUSE
VANDER JANSSEN
HOFF
LEIGH
OAKLEY
MASTERS
LANGLEY
CHAMBERLAIN
WORTHINGTON
MANSFIELD
MCELROY MILLARD MUNSON
HOYT MOE DEVRIES
HENNING
MANLEY
BROWER
FLINT
BENSON
PETTIT
MINER
AMES
HENDRICKSON SCHAFER
SCHULTZ
ADAMSON PURDY
LEACH
BRADSHAW
WINCHESTER
STUART MCMILLAN
SHORT
BUCHANAN
YATES
GREER
MALONE
BEARD
MCBRIDE
PAYNE
WELCH
HESTER
POSEY
WALLS HOSKINS
RICHMOND
WILCOX PARKS
LOCKE
GARNER
RAINES
GARLAND PATTON
GRAVES
LANE
COX
JENNINGS BATES
ARMSTRONG
LOVELL
DAY
DICKSON
VICKERS
BOLTON
BARLOW
KNOWLES
PEPPER
STEVENS
JOHNSTON WALL
SALISBURY
FOSS KIMBALL SCHROEDER
SORENSEN
HAGEN
IVERSON
KOEHLER
BRANDT
HUBER
WILLEY
WITT
BECK
SWANSON PETERSON HANSON
PFEIFFER
BUSCH
SCHAFFER
FALK
KEMPER
JORGENSEN
JACOBSON CARLSON
LARSON
OLSON
STEARNS
SORENSON
LARSEN RASMUSSEN
GUSTAFSON ERICKSON
SWENSON
LORENZ MOELLER
JACOBS
CONKLIN
DORMAN KINCAID
DAHL
NIELSEN CHRISTENSEN
OLSEN
KNUTSON
KRUEGER
SCHUMACHER
POWERS
SHEARER
HATHAWAY HORNER
MADSEN PETERSEN
JENSEN
LIND
PAULSON
HARMS
BRUNNER
KROLL SCHMID
BINDER
BENDER FISCHER
KOLB
MAYER
ULRICH
UNGER
RUDOLPH
GILLETTE
TUTTLE
DOTY
AMP
JACOBSEN JOHANSEN
HANSEN
CHRISTIANSEN
BAUMAN
ARNDT
LEA SNELL
POTTER
OLDHAM SPEAR
BEATTY
MOSHER
DELONG
PEDERSEN
LUND BACHMAN
SCHAEFER
PEDERSON
MATTSON HECK
BAUMGARTNER
NAGEL
BAUMANN
MEYER ZIEGLER
LANG
STAUFFER
LUTHER
WINSLOW
HAWLEY
COON
BERG
BABCOCK
NOWAK
MOYER
VOSS
SCHWAB
STONER
ANDERSEN GRAFF LUTZ
HESS
KOHLER
OTT
JAEGER FUCHS
GEIGER
STODDARD
SCHAEFFER
KAUFFMAN
BECKMAN
LANGE
SCHUSTER
HOFMANN
URBAN
ELY
HARTMAN
ALDRICH
OSBORN
CLEMENS
GOETZ
CONRAD
CUTLER HAINES
HULL
BORDEN
WILLARD
LOCKWOOD
GROVES
ABBOTT
FRENCH
PAGE
BRAY
RUSHING PERDUE
PRUITT
LEDBETTER KINSEY
MCGEE KIMBLE
LESTER
STAPLES
EASLEY
BUCKNER LANIER
MELTON SHEFFIELD PARRISH
GRIMES
MCCALL
HERRON
KEENE
MEREDITH
BOSWELL
THORNE
BOWEN
HUMPHRIES
GARVIN
WADDELL
HEATH
LAYTON GUTHRIE
STILL
ELLIOTT
FOOTE
ROWLAND
QUICK
SLATER
GRIFFITH
COBURN
SPAULDING
LINCOLN
GATES
MCGRAW
DODGE
CRANE
FERRIS
SPRAGUE
SNYDER
SHULTZ
KOENIG CASPER
LEHMAN DIEHL WETZEL ECKERT
BAUER
SCHRADER
SARGENT
LINDER
SPANGLER
LENTZ
KLINE
ZIMMERMAN
YOST
RAPP
SCHILLING FAUST LANDIS
GRIMM
HAGAN
WISNIEWSKI
KAMINSKI
GLEASON
ALBRIGHT
STARK
KNAPP
GOODRICH
CORNELL
MEYERS STAHL
SEAMAN
HORVATH
FAY
REINHARDT
CALLAHAN
DOWNEY STANTON
ONEIL HANNON
CARY
COSGROVE
NEVILLE
BUCKLEY
PAPPAS
BRADY
DOUGHERTY
FARRELL
MAHON
CONWAY
MULLIN
SHERMAN
DORAN
MC
MCMANUS
DOWLING DEMPSEY
BURKE
GORMAN SCANLON
MCKENNA GILLIS
LYNCH
LARKIN SULLIVAN
MURPHY CONNOR
LAWLER KEANE
DRISCOLL
CONDON
1
GIFFORD
SHAFFER
ROE
HOOVER
ENGLE
PIPER
NEWMAN
DOUGLASS
CHASE
FISHER
EARLY
ALDRIDGE
COURTNEY
EDMONDSON
BURKETT VICK
HUFF
LINDSEY PRATHER
MERRITT
SELLERS
BUTTS
BOND
MCFARLAND
WILKES
BUSBY
HENSON PETTY GUNTER
EUBANKS
SAPP
BREWER STINSON
BURCH
KEMP
HOLLAND
HOLMAN
POTTS
HOLDEN POLLOCK
COATES BALDWIN FARRAR
BASSETT
STARKEY
WHITMORE
ELLSWORTH
BLISS
BRUNER
RHOADS
MURDOCK
WOLFE
WORKMAN
PIKE
STALEY SHAFER
MCGINNIS
YODER
STOREY
TILLEY
WILES
WYLIE
RUDD
MOTT
DAILEY NICKERSON
HOBBS
RANKIN
LANGFORD
DRAPER
TANNER
PRICE
FROST
MERCER
LATHAM WALLER
BOWDEN
COOK HUTTON
LUNSFORD
SHELTON
BRASWELL IVEY
HATCHER RATLIFF THURMAN JUSTICE
LOTT
DODSON PIERCE
NEWTON
SANFORD AVERY
CORNELIUS
WYATT WHEELER
WEEKS
STANLEY
MILLER
WOOD HITCHCOCK
MCCONNELL
HAGER
SAYLOR
RHOADES
SNOW LAMB
CRAVEN
HYATT
PAINTER
SKINNER
CARPENTER
GILLESPIE
STAFFORD
WITHERS
FULTON
SUMMERS
WALDEN
JEWELL
SWANN
MILNER
CARLTON
PRESTON
CHILDS
ARNOLD
GRIGGS
ARNETT
RUTLEDGE FINLEY
COLVIN
GENTRY
MOODY
WISE
EWING
CRAIN
ELMORE OVERTON
CONNER
LEDFORD
THORNTON
BELCHER
GODWIN HANNAH
EMERSON
LONG
NICHOLS
BRYSON
ENGLAND
RICE
KNOTT NORRIS
CALVERT
DALTON NORTON
NYE
ROOT
HOLBROOK
JUDD
WHALEY
DAUGHERTY
KELLER
MEEK
STROUD
PIERSON
BEEBE
SAGE
DURBIN
RADER
KELLOGG FLOOD
KELLY
STACK
FITZGERALD
MAHONEY MCDERMOTT
ROCHE OLEARY
COUGHLIN
COYNE
QUIGLEY
REGAN
BOYLE OKEEFE
DONNELLY
KEEGAN
NEFF
LAUGHLIN
PUTNAM
RUST CLIFFORD
CASSIDY GAFFNEY
SWEENEY
MEEHAN
MCGOVERN DOLAN
SHERIDAN COTTER
MERRILL
MCCARTNEY
MADDEN
WINKLER
STRATTON
CHURCHILL
CLANCY
COONEY
FLYNN
KEENAN
REARDON
CURLEY FLAHERTY
MCCORMACK
MCDONNELL
MCGRATH
OROURKE
HEALY
CONNORS
HENNESSY
OHARA BREEN SHEA
CORRIGAN
FEENEY
GARVEY
MCNAMARA
DUNNE
MCMAHON LEAHY
DONAHUE
RYAN
DWYER OCONNOR KANE
FAHEY MCHUGH
CONROY
SHEEHAN
FLANAGAN FINN
DOYLE
OCONNELL
ODONNELL
MALONEY
GALLAGHER
KELLEHER
MCLAUGHLIN KEEFE
HOGAN
COYLE QUINN
CROWLEY
WALSH
COSTELLO
DOHERTY
MULLIGAN MCNULTY
OREILLY
OBRIEN
TIERNEY BRENNAN
MCDONOUGH
MALLOY
FOLEY
QUINLAN OSULLIVAN
CONNELLY
KEARNEY
OMALLEY
DILLON
MCGOWAN
CORBETT
HANLEY
DALY
CURRAN DONOHUE
MCCARTHY
CONNOLLY
OTOOLE
JUDGE DUGAN LENNON
KENNEY
NOLAN
CRONIN DUFFY FITZPATRICK
BURK
FS
REDDING
EASTMAN
ROBISON
FARR
SWAN
PLATT
YEAGER
CRAMER
HEATON ENNIS
DOOLEY
HARRINGTON
KINNEY
HASTINGS
PURCELL WELLER
MCCORMICK MCCANN
CASEY
GLYNN
MONAHAN PHELAN
EGAN
MASTERSON
SWIFT
KEARNS
MOONEY
MCCABE
ONEILL
DUGGAN
DONOVAN
ROONEY
HORAN
CAHILL
KENNY BARRY
HANLON
DEVLIN
GAVIN
CULLEN
MAGUIRE
MORRISSEY
LEARY
DELANEY HEALEY FALLON
ROWELL
HAND
MCGUIRE
COFFEY
MATHEWS
BILLINGS
PICKERING
PHIPPS
KENT
CECIL
BARRETT
CARROLL
FIELD
FOX
HORN
BOWLES BATEMAN
TRIMBLE BROWNING
GREGG STONE
SNIDER
SHARP KIRK
CROWELL
TRENT CARSON
BACON CROCKER
LYNN
BUCK
CULVER
HOLT
PECK
CONN
GROGAN
CROSBY
MCWILLIAMS
BURNS
BURNHAM
LYLE
LYNNE
WHITMAN
KIRKPATRICK
HUSTON
ALLEY DRAKE
ELDRIDGE
STAPLETON
MCCLURE
MYERS
TOMPKINS
MONK
BENTLEY
MICHAELS
MANNING
CARLIN
HICKEY
BYRNE
CAREY
HURLEY
MCNALLY
NOONAN
KENYON
DUFF
EATON
DIETZ
WHALEN CLEARY
CORCORAN
MULLEN
GANNON
COPE
HUTCHINS
METCALF
PARR
PURVIS ELDER
CULP
JAMESON
PYLE
CORNWELL
HEDRICK
WASHBURN
ANDERS CARNEY
TRIPP
PRIEST CROWE
KELLEY
SHOOK GOFF
HANEY SAWYER
LINN
STILES
CONLEY
LEONARD
CLEMENTS MCCRACKEN ODELL
GAGE
STORM
ATWOOD
DYE
CHEEK
HENDRIX
POE
DURHAM
FAIRCHILD
WHITLOCK ROWAN UPTON
IRVIN
ABERNATHY
STALLINGS
DARNELL
MCDANIEL
BARBOUR
HATFIELD
HAMLIN
PACE
TRIPLETT
DEWITT PRESLEY
COMER NIX
SAMS
VARNER
HURST
HICKMAN HALEY
THOMASON
UNDERWOOD
RUFF
SHIELDS
LANCASTER
KENDRICK
WOODALL
HAWK
TABOR PROCTOR
GILMORE
BUNCH RAMSEY
PHELPS
BENTON
COKER
HARDIN HUBBARD
SPICER HANKS
SELF
REAGAN
BLACKBURN
SPARKS STRANGE
CARLISLE
WOODRUFF
CRABTREE
COULTER
WOODY
CREWS
DOSS YOUNGBLOOD
SIZEMORE
AYERS MORELAND
VANCE
LANDERS
HILTON
HUFFMAN
BROCK
BLANTON
STEEN
CROW
FARMER
COCHRAN
BUTCHER
STOVER
HARMON
DOWNS
HOPPER
CAPPS
MCCARTY
PRATER
WELDON
DICKEY
CROUCH
MAGEE
CUMMINS
CRANDALL
LADD
BYERS
IRELAND
MCCORD
SHOEMAKER
DENT NUGENT
DUNHAM
NAPIER COE
BLANKENSHIP
HELTON
BLEVINS
SHIPMAN
HAMM LILLY
WINTERS NEWBERRY
MCCULLOUGH
PENDLETON
MILLIGAN
RIGGS
BEAM
BAGLEY
MOCK COOLEY
SHIPLEY COOMBS
CRUM
COUCH
KISER
HONEYCUTT
KILPATRICK
WHITTEN HENSLEY
MOSELEY
SHAVER CRAFT
BEAVER
WINN
CLINE
SEXTON
DUVALL
BOGGS
ELKINS
HAYS
PATE
HINSON
TIPTON
TIDWELL ADKINS
COMBS MEADOWS
MULLINS
CATES
PUCKETT
ALLRED
HALE
CHILDERS WHITTINGTON
MESSER GARRISON
HELMS
BOWERS RIDDLE
FRYE
HIGGINBOTHAM
ESTES COMPTON
RAMEY
PADGETT
KILGORE
CAUDILL
PENNINGTON STORY
COFFMAN
CAGLE LACKEY
HUTSON
CORNETT
TEAGUE
STOUT
HANCOCK
MCCLELLAN
FARRIS
ERWIN HOLCOMB
GOSS
INMAN
ELAM PACK
FAULKNER DILL
CLIFTON MAHAN
WORTH
COUTO
FONTES FALCO
BOTELHO
VALENTE FERRO
Fig. 3: Visualization of the name embedding for the top 5000 last names, showings a 2D projection view of the embedding (left). Insets (left to right) highlight British 1 , African-American 2 and Hispanic 3 names. Variation CBOW joint SG joint CBOW sep SG sep
Popularity 0.6434(0.0007) 0.6747(0.0002) 0.6675(0.0003) 0.5776(0.0001)
Gender NN(1) NN(10) 0.9092 0.9360 0.8844 0.9274 0.9162 0.9350 0.8844 0.9205
P (W |W ) 0.9362 0.9461 0.9299 0.9217
Ethnicity (NN(1)) P (B|B) P (A|A) 0.5939 0.7626 0.4561 0.7208 0.4437 0.7167 0.3451 0.6797
P (H|H) 0.7543 0.7543 0.6710 0.6971
TABLE IV: Evaluation of different embedding variants. Popularity is measured by Jensen-Shannon Divergence of frequency distribution, while all other values are precision at k. Top % 1 2 3 4 5 6 7 8 9 10 ≤ 10% 100 99 98 98 98 98 98 98 98 98 ≤ 20% 99 97 96 96 95 95 95 95 95 95 ≤ 30% 96 95 94 93 93 92 93 92 92 91 ≤ 40% 93 93 91 90 90 89 89 89 88 88 ≤ 50% 89 89 86 85 85 84 84 84 83 83 ≤ 60% 86 86 84 83 82 82 82 81 81 80 ≤ 70% 82 81 79 79 78 77 77 76 76 76 ≤ 80% 79 78 76 75 74 74 74 73 73 72 ≤ 90% 76 75 73 73 72 71 71 71 70 70 All 73 72 70 69 69 68 68 67 67 67
varies with popularity of the first name, and the number of neighbors. From Table V, we observe that our proposed name embedding scheme shows strong gender coherence, especially for popular names. As we can see from the tables, the percentage of neighbors that have same gender as the original first name is very high for the top 30% most popular names comparing to a randomly assigned name (50%). On the other hand, the percentage decreases when unpopular names are included, and also decreasing as the number of neighbors increases. A similar coherence analysis was carried out with regard to ethnicity. We found that the top neighbors of a popular
Top % 1 2 3 4 5 6 7 8 9 10 ≤ 10% 97 97 97 96 95 95 95 95 95 95 ≤ 20% 91 91 91 90 89 89 89 89 88 88 ≤ 30% 85 84 84 84 83 83 82 82 82 81 ≤ 40% 80 79 79 78 78 77 77 77 76 76 ≤ 50% 75 74 74 73 73 72 72 72 71 71 ≤ 60% 69 69 68 68 67 67 66 66 66 66 ≤ 70% 66 65 66 65 64 64 63 63 63 63 ≤ 80% 62 61 61 61 60 60 59 59 59 59 ≤ 90% 59 59 59 58 58 57 57 57 57 57 All 57 56 56 56 55 55 55 54 54 54
TABLE V: Gender coherence of the name embedding for males (left) and females (right), as measure by the percentage of k-neighbors being male (left) and female (right). name tend to have a high probability of being in the same ethnicity group. The coherence for an ethnic group correlates positively with the popularity of the group in the contact lists. The coherence for AIAN and 2PRACE are poor, because they only account for 0.1% and 0.05% of the last names in the contact lists. Thus there is too little data to get the embedding correct.
First names Last names
PCC RA RU 0.5813 0.7795 0.2260 0.4454
SCC RA RU 0.5170 0.5402 0.3444 0.3916
TABLE VI: Correlation of real names and replacement names. B. Name Popularity Analysis To measure the popularity preserving of word embedding, we calculate the real name frequency of a name (R), the average real name frequency of its replacement names (ten nearest
Fig. 4: The two distinct Asian clusters. Left: Chinese/South Asian names ( 4 in Fig. 3). Right: Indian names ( 5 Fig. 3).
5
Gender distribution. R-Random,G-Generative
0.35
0.15 T=5 T=5(R) T=10 T=10(R) T=5(G) T=10(G)
Freqeuncy (normalized)
0.3 0.25
T=5 T=10
0.2 0.15 0.1 0.05 0
Difference between contact list and Random contact list
0.1 Frequency difference
neighbors) (A), and its replacement usage frequency (U ). Two measurements, Pearson’s correlation coefficient (PCC) and Spearman’s rank correlation coefficient (SCC), are used to measure how well the popularity is preserved. The results are shown in Table VI. Overall we can see that the correlation between the real name frequency R and the replacement usage frequency U is higher than that for the real name frequency R and its neighbors’ real name frequency A. This indicates that a popular name is very likely to appear in among the nearest neighbors of other names, even though its nearest neighbors are not necessarily popular names.
0.05 0 -0.05 -0.1 -0.15
0
0.1
0.2
0.3
0.4 0.5 0.6 #M/(#M+#F)
0.7
0.8
0.9
1
-0.2
0
0.2
0.4 0.6 #M/(#M+#F)
0.8
1
Fig. 5: Left: the distribution of user’s gender in contact lists data. Distributions with legend “R” are from binomial distribution with probability 0.5. Distributions with legend “G” are from binomial mixture model with parameters inferred using EM algorithm. Other distributions are from observation in the contact lists. Right: deviation from the null hypothesis.
C. Why does the embedding work? Recall that we start from contact lists of millions of users, and embedding the first and last names using word2vec. We have observed visually and though numerical metrics that the embedding captures gender and ethnicity very well. A natural question is: why does it work so well? Our hypothesis is that the population as a whole have a bias toward contacting people of the same ethnicity and gender. This bias drives the embeddings of names of similar ethnicity and gender close to each other, and pushes names of different ethnicity and gender apart. To test this hypothesis, we look at the frequency distribution of percentage of males in our mailing list, and compare with the null hypothesis. In Fig. 5 (left), we divide contact lists by a threshold based on the minimum number T of identifiable genders in the list. E.g., T = 5 means those contact lists with at least five genderidentifiable names. The distributions of the ratio of identifiable males in the contact lists with T = 5 and 10 are seen as the two lower curves. Clearly, the majority of the contact list has around 50% males. However, looking at these distribution along would not tell us whether the distributions have any bias. For this purpose, we need to compare them with the null hypothesis. We generate the null distribution by assigning the gender of a name randomly following the gender distribution of the contact list. Fig. 5 (left) shows that the distributions based on the null hypothesis (the two higher curves) are spikier, with around 30% of the contact lists having 50% of males, compared with the observed 15%. Fig. 5 (right) shows the deviation of the observed distribution from the null hypothesis. It shows a clear bimodal pattern, confirming our hypothesis that contact lists on average exhibit a bias towards either male domination, or female domination, especially the latter. A similar analysis was done with regard to ethnicity, and confirmed a bias for people to contact other people of the same ethnicity. Due to space limition details are ommitted. To further verify the gender bias in observed contact lists, we model the observed number of males in all contact lists as a Binomial mixture model. The mixture model fits the observed data well, and suggests that 47% of the observed contact lists belong to male users and 53% belongs to female users.
IV. C ONCLUSION We propose a new technique for generating look-alike names through distributed name embeddings. By training on millions of email contact lists, our embeddings establish gender and cultural locality among names. The embeddings make possible construction of replacement aliases for any given name that preserve gender and cultural identity. Through large-scale analysis of contact lists, we establish that there is a greater than expected concentration of names of the same gender and race for all major groupings under study. The lookalike name generation technique is currently being deployed as part of soft-challenge pipeline for login challenge and account recovery see Fig. 1). A demostration website for generation look-alike names is available as http://yo/lookalikename. We are current using these embeddings for age and ethnicity classification of names. Gender results are available in the URS datahub and ethnicity results will be in soon. R EFERENCES [1] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in Advances in neural information processing systems, 2013, pp. 3111– 3119. [2] C. Bureau, https://www.census.gov/topics/population/genealogy/data/ 1990 census/1990 census namefiles.html, 1990. [3] ——, https://www.census.gov/topics/population/genealogy/data/2000 surnames.html, 2000. [4] R. Gross and A. Acquisti, “Information revelation and privacy in online social networks,” in Proceedings of the 2005 ACM workshop on Privacy in the electronic society. ACM, 2005, pp. 71–80. [5] open source project, https://code.google.com/archive/p/word2vec/, 2013. [6] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” in Proceedings of Workshop at ICLR, 2013. [7] L. Van Der Maaten, “Accelerating t-sne using tree-based algorithms,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 3221–3245, 2014. [8] Y. Hu, E. Gansner, and S. Kobourov, “Visualizing graphs and clusters as maps,” IEEE Computer Graphics and Applications, vol. 30, pp. 54–66, 2010. [9] M. Campbell, http://www.behindthename.com, 1996.
6