"The explanation makes sense": An Empirical Study on LLM Performance in News Classification and its Influence on Judgment in Human-AI Collaborative Annotation

TL;DR

This study evaluates GPT models' ability to classify U.S. news by political ideology, compares their performance with supervised models, and investigates how explanations influence human judgment and confidence in collaborative annotation.

Contribution

It provides empirical evidence on GPT's classification accuracy, compares explanation types' effects on users, and offers a new dataset for future research in AI-assisted news analysis.

Findings

AI significantly increases user confidence in classification.

Detailed explanations are more persuasive and influence decisions more.

GPT models perform comparably to supervised methods on news classification.

Abstract

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. While large language models (LLMs) can scale classification tasks, concerns remain about their trustworthiness. To advance human-AI collaboration, we investigate the feasibility of using LLMs to classify U.S. news by political ideology and examine their effect on user decision-making. We first compared GPT models with prompt engineering to state-of-the-art supervised machine learning on a 34k public dataset. We then collected 17k news articles and tested GPT-4 predictions with brief and detailed explanations. In a between-subjects study (N=124), we evaluated how LLM-generated explanations influence human annotation, judgment, and confidence. Results show that AI assistance significantly increases confidence ($p<.001$), with detailed explanations more persuasive and more likely to alter decisions. We highlight recommendations for AI explanations through thematic analysis and provide our dataset for further research.