Speaker: Dr. Chengkai Li, Associate Professor, University of Texas at Arlington
Time：10:00-11:30, October 9, 2015
Venue: Room 310, Third Floor, Office Building, Software Campus
Host: Prof. Shanqing Guo
Title: Enabling Computational Journalism: Automated Fact-Checking and Story-Finding
Abstract: The IDIR Lab at the University of Texas at Arlington has been on the frontier of computational journalism research in the past several years. This talk will discuss two systems developed in the thrust.
(1) ClaimBuster, a fact-checking system, uses machine learning and natural language processing techniques to help journalists find political claims to fact-check. We will use it to find factual statements in the 2016 United States presidential debates that are worth checking, with the goal of expanding its use to other types of discourses, articles, social media, as well as non-political claims. Still under development, a near real-time test during the recent August 6th Republican debate of the 2016 election suggests a statistically significant agreement between ClaimBuster and professional fact-checkers. This talk will discuss the ideas behind ClaimBuster, its data collection process, the experience with the Republican debate, and our quest for the "Holy Grail"---a completely-automated, live fact-checking machine that replaces human fact-checkers. (2) The talk will also briefly discuss FactWatcher, a system that helps journalists identify data-backed, attention-seizing facts which serve as leads to news stories. Given an append-only database, upon the arrival of a new tuple, FactWatcher monitors if the tuple triggers any new facts. Its algorithms efficiently search for facts without exhaustively testing all possible ones. Furthermore, FactWatcher provides multiple features in striving for an end-to-end system, including fact ranking, fact-to-statement translation and keyword-based fact search. In 2014 the system won an Excellent Demonstration Award at VLDB, one of the two most prestigious conferences in the database area.
Bio: Dr. Chengkai Li is an Associate Professor and Director of the Innovative Database and Information Systems Research Laboratory (IDIR) in the Department of Computer Science and Engineering at the University of Texas at Arlington. His research interests are in several areas related to big data and data science, including database, data mining, Web data management, and information retrieval. His papers have appeared in many prestigious conferences and journals on database, data mining and Web. Dr. Li has served in the organizing committee of IEEE IPCCC several times and the program committees of many premier conferences. He has also been a reviewer for multiple prestigious journals, as well as a grant review panelist for the National Science Foundation (NSF). Dr. Li's research has been funded by several NSF grants. He is a recipient of the 2011 and 2012 HP Labs Innovation Research Awards. Dr. Li received his Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2007. He graduated from Nanjing University with an M.Eng. degree and a B.S. degree, both in Computer Science, in 2000 and 1997, respectively