Machine Learning Explanations to Prevent Overtrust in Fake News Detection

TL;DR

This paper explores how explainable AI can help users better understand fake news detection tools, reducing overtrust and improving trust calibration through user studies and interpretability techniques.

Contribution

It introduces a news review interface with interpretable fake news detection algorithms and analyzes how explanations influence user trust and mental models.

Findings

Explanations improved users' mental models of AI systems.

Participants adjusted their trust based on explanations and model limitations.

The study provides insights into human-AI interaction in fake news detection.

Abstract

Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale propagation of false and fabricated information with users being exposed to algorithmically selected false content. Our research investigates the effects of an Explainable AI assistant embedded in news review platforms for combating the propagation of fake news. We design a news reviewing and sharing interface, create a dataset of news stories, and train four interpretable fake news detection algorithms to study the effects of algorithmic transparency on end-users. We present evaluation results and analysis from multiple controlled crowdsourced studies. For a deeper understanding of Explainable AI systems, we discuss interactions between user engagement, mental model, trust, and performance measures in the process of explaining. The study results indicate that explanations helped participants to build appropriate mental models of the intelligent assistants in different conditions and adjust their trust accordingly for model limitations.