Time: 14:30, Oct. 10th (Tuesday), 2017
Venue: 401 Academic Hall, Building of Information, East Campus
Topic: Social Influence and Behavior Prediction
Lecturer: Jie Tang
About the Lecturer: Jie Tang is now an Associate Professor at Tsinghua University, Ph.D. Supervisor, CCF Distinguished Member, and Director of K&I. He Obtained his Doctoral Degree from Department of Computer Science and Technology, Tsinghua University in June, 2006. Tang paid academic visits to Cornell University, Hong Kong University of Science and Technology, University of Southampton, and Catholic University of Louvain. His main research interests include social network analysis, data mining, machine learning and knowledge graph and he has proposed social network influence measurement based on topics, which improved the accuracy of user behavioral prediction and information recommendation by utilizing the measurement results. He has published over 200 including over 70 CCF A-level papers and the papers were cited more than 9000 times. He is now leading the project Arnetminer.org for academic social network analysis and mining, which has attracted millions of independent IP accesses from 220 countries/regions in the world. The core technology was applied to China Ministry of Science and Technology, National Natural Science Foundation, Chinese Academy of Engineering, ACM, American Allen Institute for Artificial Intelligence, Sogou.com, Alibaba, Tencent and so on. He was honored with the CAAI Science& Technology Progress First Prize, Newton Advanced Fellowship, CCF Young Scientist Award, and NSFC Excellent Young Scholar. He serves as Excutive Ecitor of ACM TKDD and Editorial Board Member of IEEE TKDE, ACM TIST, and TBD; Vice Chairman of KDD’18, and PC Co-Chair of international conferences like CIKM’16 and WSDM’15.
About the Lecture: Social networks have been the bridge between real physical world and virtual internet space. People’s online behaviors directly reflect the activities and emotions in the real world. The lecture will introduce how to analyze the interaction influence among users and structural influence based on network topology in large-scale real networks (like Wechat, Weibo, Twitter, AMiner) and predict user behaviors based on influence. The model considered the network structures, user properties, and the preference of network users at the same time and designed parallel learning algorithm for large-scale network, which has been verified in real online social network system.
School of Information Science and Engineering
Oct. 9th, 2017
(Translated by Zhengjie Li)