Restricted Research - Award List, Note/Discussion Page

Fiscal Year: 2018

1342  The University of Texas at Arlington  (74847)

Principal Investigator: Chengkai Li

Total Amount of Contract, Award, or Gift (Annual before 2011): $ 320,780

Exceeds $250,000 (Is it flagged?): Yes

Start and End Dates: 9/1/17 - 8/31/20

Restricted Research: YES

Academic Discipline: Department of Computer Science & Engineering

Department, Center, School, or Institute: College of Engineering

Title of Contract, Award, or Gift: III: Small: Collaborative Research: Towards End-to-End Computer-Assisted Fact-Checking

Name of Granting or Contracting Agency/Entity: National Science Foundation (NSF)

Program Title: N/A
CFDA Linked: Computer and Information Science and Engineering


We propose to conduct research towards ClaimBuster, an end-to-end system for computer-assisted fact-checking. ClaimBuster uses database query, data mining, and natural language processing (NLP) techniques to aid fact-checking. It aims to monitor live discourses (e.g., interviews, speeches and debates), social media, and news to catch factual claims, detect matches with a curated repository of fact-checks from professionals, and deliver the matches instantly to readers and viewers (e.g., by displaying a pop-up warning if a presidential candidate makes a false claim during a live debate). For various types of new claims not checked before, ClaimBuster will automatically translate them into queries against knowledge databases and report if they check out. For claims where humans must be brought into the loop, ClaimBuster will provide algorithmic and computational tools to assist lay persons and professionals in understanding and verifying the claims. Its use will be expanded to verify both political and non-political claims in many types of narratives, discourses and documents such as sports news, legal documents, and financial reports.

Discussion: No discussion notes


Close Window