Data and Technology for Fact-checking (2019-2020)

Background

Our society is struggling with an unprecedented amount of falsehoods, hyperboles and half-truths that do harm to democracy, health, economy and national security. Fact-checking is a vital defense against this onslaught. Despite the rise of fact-checking efforts globally, fact-checkers find themselves increasingly overwhelmed and their messages difficult to reach some segments of the public.

Building on a collaboration between Public Policy and Computer Science at Duke on computational journalism and fact-checking, this project seeks to leverage the power of data and computing to help make fact-checking and dissemination of fact-checks to the public more effective, scalable and sustainable.

Project Description

This Bass Connections project aims to build databases, systems and apps to achieve the following goals:

  1. Make fact-checkers more effective. By monitoring media and data sources and aggregating public interest, the project team hopes to identify important, check-worthy claims automatically and in real-time. This feed will decrease fact-checkers’ response time and guard against any potential bias (or perception thereof) in selecting what to fact-check.
  2. Help media consumers identify misinformation and disinformation faster, and make them feel like stakeholders in fact-checking. The team aims to make it easier for people to search for claims, and better yet, get alerted automatically as soon as they are exposed to misinformation. Usage data and feedback will in turn help identify check-worthy claims and diversify the coverage of fact-checking.
  3. Gain experience and learn lessons on building a sustainable, collaborative and inclusive ecosystem for fact-checking in the long run. The team will design an open data and system infrastructure, smart algorithms and best practices that will continue after the project to facilitate sharing and reuse of fact-checking efforts in the future.
  4. Make students aware of the grave new challenges of misinformation faced by our society today, and train them to become next-generation journalists and computer scientists to tackle these challenges.

Anticipated Outputs

A service that provides fact-checkers with live feeds of check-worthy claims automatically mined from various sources as well as public interest; apps and websites to help fact-checks reach the public; a system with open API access for technologists and journalists to collaborate on fact-checking; new Bass Connections course on computational fact-checking

Timing

Summer 2019 – Spring 2020

  • Summer 2019 (Optional): Through a Code+/CSURF group, tackle the challenge of scaling up the system up to bring live “pop-up” fact-checking to a large number of users simultaneously
  • Fall 2019: Expand data collection efforts to improve accuracy of claim-matching algorithms, deploy end-to-end system and make API publicly available; release apps and website to public; make enhancements to system
  • Spring 2020: Evaluate effectiveness of project’s services, apps and websites in the field; make additional adjustments as needed; offer new Bass Connections course (tentative); disseminate results in academic research venues and to broader public

See earlier related team, Data and Technology for Fact-checking (2018-2019), and a Data+ summer project, Data and Technology for Fact-checking (2018).

 

Image: Video still from Automated Fact-Checking App, by Duke University

Video still from Automated Fact-Checking App, by Duke University.

Team Leaders

  • William Adair, Sanford School of Public Policy-DeWitt Wallace Center for Media and Democracy
  • Pankaj Agarwal, Arts & Sciences-Computer Science
  • Jun Yang, Arts & Sciences-Computer Science

/graduate Team Members

  • Han Yan, Interdisciplinary Data Science - Masters

/undergraduate Team Members

  • Maya Choudhury
  • Hui Er, Computer Science (BS), Public Policy Studies (AB2)
  • Jianchao Geng
  • Mary Gooneratne, Electrical & Computer Egr(BSE), Computer Science (BSE2)
  • Javan Jiang, Economics (BS)
  • Kamran Kara-Pabani
  • Andres Montoya-Aristizabal
  • Dora Pekec
  • Julia Saveliff, Electrical & Computer Egr(BSE), Computer Science (BSE2)
  • Charles Todd, Computer Science (BS)
  • Siyi Xu, Statistical Science (BS), Computer Science (BS2)
  • Seokjun Yoon, Computer Science (BS)