CIS Seminar - Towards Automated Fact-checking

CIS Seminar

3:00 PM, Monday March 28 2016
235 Weir Hall

Towards Automated Fact-checking

Abstract: Computational Journalism is a relatively nascent research area which can be defined as the application of computation to journalism activities such as information extraction, verification, engaging data-driven report preparation, dissemination to consumers and so on. In this talk, the focus would be presenting works towards facilitating veracity checking of factual claims.

Politicians and media figures make claims about “facts” all the time. The new army of fact-checkers can often expose claims which are false, exaggerated or half-truths. For example, one of the Republican presidential candidates Donald Trump claimed that Mexico doesn't have birthright citizenship, and Americans are the "only ones" to have it; PolitiFact.com rated this factual claim as “False”. Technology, social media and new forms of journalism have made it easier than ever to disseminate falsehoods and half-truths faster than the fact-checkers can expose them. This “gap” in time and availability limits the effectiveness of fact-checking. We advocated the pursuit of a completely automatic fact-checking platform, investigated the technical challenges we will face in automating fact-checking, and proposed potential solutions. We developed a tool that helps journalists find political claims to fact-check. Now, we are developing an automated live fact-checking platform named ClaimBuster (http://idir.uta.edu/claimbuster). The platform aims to monitor live streams, websites and social media to catch factual claims, detect matches with a curated repository of fact-checks, and deliver the matches instantly to viewers; for professional fact-checkers, ClaimBuster will suggest new claims worth checking and provide computational tools that help the fact-checking process. This project, led by UTA, is a collaboration between computer scientists and journalism experts from UTA, Duke University, Google Research, and Stanford University.

Bio: Naeemul Hassan is a computer science Ph.D. student from the University of Texas at Arlington (UTA). He works in the Innovative Database and Information Systems Research (IDIR) Lab under the supervision of Dr. Chengkai Li. His research interests are in several areas related to Database systems, Data Mining and Data Science. He has published research articles in prestigious venues such as VLDB, CIKM, ICDE and IEEE Transactions on Knowledge and Data Engineering (TKDE). His research has received grants from NSF, Knight Foundation and attracted substantial media attention from NBC, Poynter, New Scientist, Politifact and so on. One of his works won an Excellent Demonstration Award in VLDB 2014. Naeemul has done internships at AT&T and Qatar Computing Research Institute (QCRI). Before starting the Ph.D. program, Naeemul has worked as a lecturer in Daffodil International University after completing B.Sc. from Bangladesh University of Engineering and Technology (BUET).