Efficient misbehaving user detection in online video chat services

Hanqiang Cheng*, Yu-Li Liang, Xinyu Xing, Xue Liu, Richard Han, Qin Lv, Shivakant Mishra

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

9 Citations (Scopus)

Abstract

Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encoun- tered in such applications is the presence of misbehaving users (\ashers") and obscene content. Automatically filtering out obscene content from these systems in an eficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature ex- traction into multiple stages and flltering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related con- textual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.

Original languageEnglish
Title of host publicationWSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery, Inc
Pages23-32
Number of pages10
ISBN (Print)9781450307475
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event5th ACM International Conference on Web Search and Data Mining, WSDM 2012 - Seattle, WA, United States
Duration: 8 Feb 201212 Feb 2012

Publication series

NameWSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining

Conference

Conference5th ACM International Conference on Web Search and Data Mining, WSDM 2012
CountryUnited States
CitySeattle, WA
Period8/02/1212/02/12

Keywords

  • Algorithms
  • Design
  • Experimentation
  • Performance

Fingerprint

Dive into the research topics of 'Efficient misbehaving user detection in online video chat services'. Together they form a unique fingerprint.

Cite this