【字色： 红 蓝 褐 绿 黑 紫 粉红 深蓝】
【字体:8 7 6 5 4 3 2 1】
题目：Social Influence Analysis for Business Intelligence
报告人： Professor Wenjie Li
邀请人： 张韧弦 副教授
报告人简介：Dr Li is currently an associate professor of the Department of Computing at The Hong Kong Polytechnic University. She received the B.Sc. and M.Sc. degrees from Tianjin University, China, and the Ph.D. degree from the Department of Systems Engineering and Engineering Management at the Chinese University of Hong Kong, Hong Kong. Dr Li’s research interests include natural language processing, text mining, social media analysis, information retrieval, extraction and summarization. She has directed and participated in quite a number of research projects. As a principal investigator, she has received seven fully supported grants from Hong Kong Research Grant Council and a grant from National Natural Science Foundation of China. She has published about 200 papers in major international journals and conference proceedings (including IEEE TKDE, IEEE TNN, IEEE TASLP, ACM TOIS, ACM TALIP, ACM TSLP, CL, and conferences like AAAI, ACL, COLING, WWW, SIGIR, CIKM). Dr Li has served as the information officer of SIGHAN, the associate editor of IJCPOL, etc. She has also served as the publication chairs, tutorial chairs, area chairs and members of organizing and technical committees of many international conferences, including AAAI, ACL, EMNLP, IJCNLP, etc.
内容提要：Social media platform provides people with an effective way to communicate and interact with each other. It is an undisputable fact that people’s influence plays an important role in disseminating information over social network. Social influence also creates opportunities for business companies to conduct online marketing activities. Although all influential users perform influence, it have been verified that the way people use to influence other varies and as a result different kinds of influence produce different kind of effects. We explored multi-view (semi-supervised) clustering approaches for influence role detection. We also studied how to use time-series models to formulate interpersonal influence by tracking user dynamic interactions and opinion changes. We proposed couple Markov chain models and recurrent neural network models to learn how influence emerges during communication. The learned models were then applied to opinion prediction.