UI & Claim ID: A_2013

Interactive Fact-checker Interface (Participant View):

Claim: Hydroxychloroquine can prevent illness and death from COVID-19

News Source Source Reputation (Interactive) News Article Headline (links) Stance of Article Towards Claim (Interactive)
www.cochrane.org
Unreliable
Mixed
Reliable
Value: 0.0
Is chloroquine or hydroxychloroquine useful in treating people with COVID-19, or in preventing infection in people who have been exposed to the virus?
Deny
Neutral
Support
Value: -1.0
victr.vumc.org
Unreliable
Mixed
Reliable
Value: 0.0
COVID-19 FAQ for the Community
Deny
Neutral
Support
Value: -1.0
www.medicalnewstoday.com
Unreliable
Mixed
Reliable
Value: 0.0
WHO 'strongly' against hydroxychloroquine use for COVID-19 prevention
Deny
Neutral
Support
Value: -1.0
www.nih.gov
Unreliable
Mixed
Reliable
Value: 1.0
Hydroxychloroquine doesn't benefit hospitalized COVID-19 patients
Deny
Neutral
Support
Value: -1.0
jamanetwork.com
Unreliable
Mixed
Reliable
Value: 0.0
Misguided Use of Hydroxychloroquine for COVID-19
Deny
Neutral
Support
Value: -1.0

Predicted Correctness

True (0%)
False (0%)



Navigation: Change Interface or See a Different Claim


About


GitHub

Click the link below to access the data used for conducting the user study.

Abstract

We conducted a lab-based eye-tracking study to investigate how interactivity of an AI-powered fact-checking system affects user interactions. A within-subject experiment was conducted, where participants used an interactive and a non-interactive version of a mock AI fact-checking system, and rated their perceived correctness of COVID-19 related claims. We collected web-page interactions, eye-tracking data, and mental workload using NASATLX. We found that the presence of the affordance of interactively manipulating the AI system’s prediction parameters affected users' dwell times, and eye-fixations on AOIs, but not mental workload. In the interactive system, participants spent the most time evaluating claims' correctness, followed by reading news. This promising result shows a positive role of interactivity in a mixed-initiative AI-powered system.

Publications

Previous and current contributors

  • Matthew Lease
  • Anubrata Das
  • Li Shi
  • Nilavra Bhattacharya
  • Jacek Gwizdka
  • Brent Biglin
  • An Thanh Nguyen
  • Aditya Kharosekar
  • Saumyaa Krishnan
  • Siddhesh Krishnan
  • ChiaHui Liu
  • Shravan Ravi
  • Alex Swearingen
  • Elizabeth Tate
  • Jyothi Keshavan Vinjumur
  • Byron Wallace