| |
Learning to detect and verify rumors on Twitter
|
Speaker (s):

Wei Gao
Senior Lecturer,
School of Information Management,
Victoria University of Wellington
|
|
Date:
Time:
Venue:
|
|
December 17, 2018, Monday
10:00am - 11:00am
Meeting Room 5.1, Level 5
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
|
|
ABSTRACT
With the deep penetration of social media in our daily lives, large number of news updates disseminated widely can be generated from unreliable or unverified information sources. This renders conventional fact-checking effort increasingly ineffective, evidenced as massive-scale circulation of rumors and fake news online, which has become a serious world-wide issue in recent years. In this talk, I will introduce automatic approaches, techniques and the new development I've been working on for combating online rumors from the perspectives of natural language processing and social network analysis. I will focus on the characterization of rumors, their linguistic, temporal and propagational patterns and dynamics, as well as the effective machine learning models for detecting, tracking and classifying rumorours events on Twitter.
About the Speaker
Dr. Wei Gao is currently a Senior Lecturer in the School of Information Management, Victoria University of Wellington. Previously, he held positions as Scientist in Qatar Computing Research Institute, Research Assistant Professor in the Chinese University of Hong Kong, and Research Fellow in the Institute for Infocomm Research. His research interests include information retrieval, natural language processing, social media analytics, and artificial intelligence. His publications appear in the major international venues including ACL, EMNLP, SIGIR, CIKM, WSDM, IJCAI, ACM TOIS, ACM TIST, SNAM, etc. He is a Senior PC member of AAAI 2019, and also has served as PC member and reviewer of a good number of top conferences and journals. He received PhD from the Chinese University of Hong Kong, and is a member of ACL, ACM, and SIGIR.
|