Research on Social Event Analysis via Collaborative Learning in Cyber-Physical Space
Abstract：With the massive growth of social events in Cyber-Physical Space, it has become more and more difficult to exactly find and organize the interesting events from massive social media data, which is useful to browse, search and monitor social events by users or governments, and obtain the evolutionary trends of social events and generate effective event summary details over time. However, the existing social event computing methods are proposed for single space, physical space or cyberspace, which ignores the collaboration between two spaces. To deal with these issues, we propose a novel social event analysis framework, which includes the following topics: 1) social event representations via collaborative learning; 2) social event co-detection; 3) social event co-tracking and evolution analysis; 4) social event prediction model. Hopefully, this project will advance the theory and algorithm research in collaborative learning and provide technical support to the intelligent analysis, understanding and management of social event data.
Keywords: cross media; cross modality; multimedia analysis; collaborative learning; social event analysis
Contact:
ZHANG Tianzhu
E-mail: tzzhang@gmail.com