DISCLAIMER: This is a research prototype, shared online only to demonstrate a potential user-interface and transparent AI model framework for explainable fact-checking. The results provided by this research prototype may be incorrect, and users are encouraged to consult other resources and services to meet their trusted fact-checking needs.
News Source | Source Reputation (Interactive) | News Article Headline (links) | Stance of Article Towards Claim (Interactive) |
---|---|---|---|
www.umass.edu |
Unreliable
Mixed
Reliable
|
Urgent Research Shows Face Masks Can Be Safely Reused by Pandemic Medical Workers |
Deny
Neutral
Support
|
www.fda.gov |
Unreliable
Mixed
Reliable
|
Shortages of Face Masks, Surgical Masks, and Respirators During the COVID-19 Pandemic |
Deny
Neutral
Support
|
apnews.com |
Unreliable
Mixed
Reliable
|
FDA: N95 masks, now plentiful, should no longer be reused |
Deny
Neutral
Support
|
news.err.ee |
Unreliable
Mixed
Reliable
|
Tartu researchers prove disposable masks can be reused |
Deny
Neutral
Support
|
www.narayanahealth.org |
Unreliable
Mixed
Reliable
|
KNOW ABOUT PROPER USAGE, DISPOSAL AND REUSE OF MASK |
Deny
Neutral
Support
|
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.