Scalable misbehavior detection in online video chat services

  • Authors:

  • Xinyu Xing;Yu-li Liang;Sui Huang;Hanqiang Cheng;Richard Han;Qin Lv;Xue Liu;Shivakant Mishra;Yi Zhu

  • Affiliations:

  • Georgia Institute of Technology, Atlanta, USA;University of Colorado at Boulder, Boulder, USA;Ohio State University, Columbus, USA;McGill University, montreal, Canada;University of Colorado at Boulder, Boulder, USA;University of Colorado at Boulder, Boulder, USA;McGill University, Montreal, USA;University of Colorado at Boulder, Boulder, USA;Tsinghua University, Beijing, China

  • Venue:
  • Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The need for highly scalable and accurate detection and filtering of misbehaving users and obscene content in online video chat services has grown as the popularity of these services has exploded in popularity. This is a challenging problem because processing large amounts of video is compute intensive, decisions about whether a user is misbehaving or not must be made online and quickly, and moreover these video chats are characterized by low quality video, poorly lit scenes, diversity of users and their behaviors, diversity of the content, and typically short sessions. This paper presents EMeralD, a highly scalable system for accurately detecting and filtering misbehaving users in online video chat applications. EMeralD substantially improves upon the state-of-the-art filtering mechanisms by achieving much lower computational cost and higher accuracy. We demonstrate EMeralD's improvement via experimental evaluations on real-world data sets obtained from Chatroulette.com.