Multimodal classification of moderated online pro-eating disorder content

Stevie Chancellor, Yannis Kalantidis, Jessica A. Pater, Munmun De Choudhury, David A. Shamma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Social media sites are challenged by both the scale and variety of deviant behavior online. While algorithms can detect spam and obscenity, behaviors that break community guidelines on some sites are difficult because they have multimodal subtleties (images and/or text). Identifying these posts is often regulated to a few moderators. In this paper, we develop a deep learning classifier that jointly models textual and visual characteristics of pro-eating disorder content that violates community guidelines. Using a million Tumblr photo posts, our classifier discovers deviant content efficiently while also maintaining high recall (85%). Our approach uses human sensitivity throughout to guide the creation, curation, and understanding of this approach to challenging, deviant content. We discuss how automation might impact community moderation, and the ethical and social obligations of this area.

Original languageEnglish (US)
Title of host publicationCHI 2017 - Proceedings of the 2017 ACM SIGCHI Conference on Human Factors in Computing Systems
Subtitle of host publicationExplore, Innovate, Inspire
PublisherAssociation for Computing Machinery
Pages3213-3226
Number of pages14
ISBN (Electronic)9781450346559
DOIs
StatePublished - May 2 2017
Externally publishedYes
Event2017 ACM SIGCHI Conference on Human Factors in Computing Systems, CHI 2017 - Denver, United States
Duration: May 6 2017May 11 2017

Publication series

NameConference on Human Factors in Computing Systems - Proceedings
Volume2017-May

Other

Other2017 ACM SIGCHI Conference on Human Factors in Computing Systems, CHI 2017
Country/TerritoryUnited States
CityDenver
Period5/6/175/11/17

Bibliographical note

Publisher Copyright:
© 2017 ACM.

Keywords

  • Computer vision
  • Content moderation
  • Deep learning
  • Deviant behavior
  • Pro-eating disorder
  • Social media
  • Tumblr

Fingerprint

Dive into the research topics of 'Multimodal classification of moderated online pro-eating disorder content'. Together they form a unique fingerprint.

Cite this