Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

An Analytic System for User Gender Identification through User Shared Images

An Analytic System for User Gender Identification through User Shared Images Many social media applications, such as recommendation, virality prediction, and marketing, make use of user gender, which may not be explicitly specified or kept privately. Meanwhile, advanced mobile devices have become part of our lives and a huge amount of content is being generated by users every day, especially user shared images shared by individuals in social networks. This particular form of user generated content is widely accessible to others due to the sharing nature. When user gender is only accessible to exclusive parties, these user shared images are proved to be an easier way to identify user gender. This work investigated 3,152,344 images by 7,450 users from Fotolog and Flickr, two image-oriented social networks. It is observed that users who share visually similar images are more likely to have the same gender. A multimedia big data system that utilizes this phenomenon is proposed for user gender identification with 79% accuracy. These findings are useful for information or services in any social network with intensive image sharing. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) Association for Computing Machinery

An Analytic System for User Gender Identification through User Shared Images

Download PDF
20 pages

Loading next page...
 
/lp/association-for-computing-machinery/an-analytic-system-for-user-gender-identification-through-user-shared-kul8bpN0jb
Publisher
Association for Computing Machinery
Copyright
Copyright © 2017 ACM
ISSN
1551-6857
eISSN
1551-6865
DOI
10.1145/3095077
Publisher site
See Article on Publisher Site

Abstract

Many social media applications, such as recommendation, virality prediction, and marketing, make use of user gender, which may not be explicitly specified or kept privately. Meanwhile, advanced mobile devices have become part of our lives and a huge amount of content is being generated by users every day, especially user shared images shared by individuals in social networks. This particular form of user generated content is widely accessible to others due to the sharing nature. When user gender is only accessible to exclusive parties, these user shared images are proved to be an easier way to identify user gender. This work investigated 3,152,344 images by 7,450 users from Fotolog and Flickr, two image-oriented social networks. It is observed that users who share visually similar images are more likely to have the same gender. A multimedia big data system that utilizes this phenomenon is proposed for user gender identification with 79% accuracy. These findings are useful for information or services in any social network with intensive image sharing.

Journal

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) – Association for Computing Machinery

Published: Jun 28, 2017

Keywords: Big data

References

  • Empirical evaluation of profile characteristics for gender classification on Twitter
    Alowibdi, Jalal S.; Buy, Ugo; Yu, Paul
  • Language independent gender classification on Twitter
    Alowibdi, Jalal S.; Buy, Ugo; Yu, Paul
  • Automatically profiling the author of an anonymous text
    Argamon, Shlomo; Koppel, Moshe; Pennebaker, James W.; Schler, Jonathan
  • k-means++: The advantages of careful seeding
    Arthur, David; Vassilvitskii, Sergei
  • Discriminating gender on Twitter
    Burger, John D.; Henderson, John; Kim, George; Zarrella, Guido
  • Return of the devil in the details: Delving deep into convolutional nets
    Chatfield, Ken; Simonyan, Karen; Vedaldi, Andrea; Zisserman, Andrew
  • Bag-of-features tagging approach for a better recommendation with social big data
    Cheung, Ming; She, James
  • Evaluating the privacy risk of user shared images
    Cheung, Ming; She, James
  • Connection discovery using big data of user-shared images in social media
    Cheung, Ming; She, James; Jie, Zhanming
  • Non-user generated annotation on user shared images for connection discovery
    Cheung, Ming; She, James; Xiaopeng, Li
  • Mean shift: A robust approach toward feature space analysis
    Comaniciu, Dorin; Meer, Peter
  • A multiple resampling method for learning from imbalanced data sets
    Estabrooks, Andrew; Jo, Taeho; Japkowicz, Nathalie
  • Stylometric analysis of bloggers’ age and gender
    Goswami, Sumit; Sarkar, Sudeshna; Rustagi, Mayur
  • A picture is worth a thousand words: A content analysis of Facebook profile photographs
    Hum, Noelle J.; Chamberlin, Perrin E.; Hambright, Brittany L.; Portwood, Anne C.; Schat, Amanda C.; Bevan, Jennifer L.
  • A cloud-assisted framework for bag-of-features tagging in social networks
    Jie, Zhanming; Cheung, Ming; She, James
  • Creating efficient codebooks for visual recognition
    Jurie, Frederic; Triggs, Bill
  • Saliency, scale and image description
    Kadir, Timor; Brady, Michael
  • Active learning with Gaussian processes for object categorization
    Kapoor, Ashish; Grauman, Kristen; Urtasun, Raquel; Darrell, Trevor
  • How Flickr helps us make sense of the world: Context and content in community-contributed media collections
    Kennedy, Lyndon; Naaman, Mor; Ahern, Shane; Nair, Rahul; Rattenbury, Tye
  • Tag-based social interest discovery
    Li, Xin; Guo, Lei; Zhao, Yihong E.
  • An algorithm for vector quantizer design
    Linde, Yoseph; Buzo, Andres; Gray, Robert M.
  • What’s in a name? Using first names as features for gender inference in Twitter
    Liu, Wendy; Ruths, Derek
  • Frazzled by Facebook? An exploratory study of gender differences in social network communication among undergraduate men and women
    LOUGHEED., ERIC
  • Distinctive image features from scale-invariant keypoints
    Lowe, David G.
  • Efficient clustering of high-dimensional data sets with application to reference matching
    McCallum, Andrew; Nigam, Kamal; Ungar, Lyle H.
  • Online facility location
    Meyerson, Adam
  • Not all tags are created equal: Learning Flickr tag semantics for global annotation
    Moxley, Emily; Kleban, Jim; Xu, Jiejun; Manjunath, B. S.
  • Improving gender classification of blog authors
    Mukherjee, Arjun; Liu, Bing
  • Make new friends or keep the old: Gender and personality differences in social networking use
    Muscanell, Nicole L.; Guadagno, Rosanna E.
  • Predicting age and gender in online social networks
    Peersman, Claudia; Daelemans, Walter; Van Vaerenbergh, Leona
  • Classifying latent user attributes in Twitter
    Rao, Delip; Yarowsky, David; Shreevats, Abhishek; Gupta, Manaswi
  • Face it: The impact of gender on social media images
    Rose, Jessica; Mackey-Kallis, Susan; Shyles, Len; Barry, Kelly; Biagini, Danielle; Hart, Colleen; Jack, Lauren
  • User-aware image tag refinement via ternary semantic analysis
    Sang, Jitao; Xu, Changsheng; Liu, Jing
  • Personality, gender, and age in the language of social media: The open-vocabulary approach
    Schwartz, H. A.; Eichstaedt, Johannes C.; Kern, Margaret L.; Dziurzynski, Lukasz; Ramones, Stephanie M.; Agrawal, Megha; Shah, Achal; Kosinski, Michal; Stillwell, David; Seligman, Martin E.
  • Personalized recommendation in social tagging systems using hierarchical clustering
    Shepitsen, Andriy; Gemmell, Jonathan; Mobasher, Bamshad; Burke, Robin
  • Flickr tag recommendation based on collective knowledge
    Sigurbjrnsson, Brkur; Van Zwol, Roelof
  • User descriptions and interpretations of self-presentation through Facebook profile images
    Strano, Michele M.
  • Joint social and content recommendation for user-generated videos in online social network
    Wang, Zhi; Sun, Lifeng; Zhu, Wenwu; Yang, Shiqiang; Li, Hongzhi; Wu, Dapeng
  • The eyes of the beholder: Gender prediction using images posted in online social networks
    You, Quanzeng; Bhatia, Sumit; Sun, Tong; Luo, Jiebo
  • Tagging images by merging multiple features in a integrated manner
    Zhang, Xiaoming; Li, Zhoujun; Chao, Wenhan
  • Social image tagging using graph-based reinforcement on multi-type interrelated objects
    Zhang, Xiaoming; Zhao, Xiaojian; Li, Zhoujun; Xia, Jiali; Jain, Ramesh; Chao, Wenhan
  • UserRec: A user recommendation framework in social tagging systems
    Zhou, Tom C.; Ma, Hao; Lyu, Michael R.; King, Irwin