# The Effects of Interactive AI Design on User Behavior: An Eye-tracking Study of Fact-checking COVID-19 Claims

arXiv: https://arxiv.org/abs/2202.08901 · HTML: https://mlsanity.com/paper/2202.08901/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Detection and Resolution of Rumours in Social Media: A Survey](https://mlsanity.com/paper/1704.00656/) (2017)
- [NELA-GT-2020: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles](https://mlsanity.com/paper/2102.04567/) (2021)
- [NELA-GT-2019: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles](https://mlsanity.com/paper/2003.08444/) (2020)
- [Machine Learning Explanations to Prevent Overtrust in Fake News Detection](https://mlsanity.com/paper/2007.12358/) (2020)
- [Mix and Match: Collaborative Expert-Crowd Judging for Building Test Collections Accurately and Affordably](https://mlsanity.com/paper/1806.00755/) (2018)

## Built on by (most cited first, 2 of 2)

- [Fact-checking information from large language models can decrease headline discernment](https://mlsanity.com/paper/2308.10800/) (2023)
- [Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification](https://mlsanity.com/paper/2602.11161/) (2025)

## Abstract (arXiv)

We conducted a lab-based eye-tracking study to investigate how the interactivity of an AI-powered fact-checking system affects user interactions, such as dwell time, attention, and mental resources involved in using the system. 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 NASA-TLX. 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.