Do Expressions Change Decisions? Exploring the Impact of AI's Explanation Tone on Decision-Making

TL;DR

This study examines how the tone of AI explanations, such as formal or humorous, affects human decision-making across different AI roles and user attributes, revealing significant influences and user preferences.

Contribution

It is the first to systematically analyze the impact of explanation tone on decision-making in AI systems across multiple scenarios and user characteristics.

Findings

Tone significantly influences decision-making in the second-opinion scenario.

Older users are more affected by explanation tone.

User perceptions and decisions can diverge based on personality traits.

Abstract

Explanatory information helps users to evaluate the suggestions offered by AI-driven decision support systems. With large language models, adjusting explanation expressions has become much easier. However, how these expressions influence human decision-making remains largely unexplored. This study investigated the effect of explanation tone (e.g., formal or humorous) on decision-making, focusing on AI roles and user attributes. We conducted user experiments across three scenarios depending on AI roles (assistant, second-opinion provider, and expert) using datasets designed with varying tones. The results revealed that tone significantly influenced decision-making regardless of user attributes in the second-opinion scenario, whereas its impact varied by user attributes in the assistant and expert scenarios. In addition, older users were more influenced by tone, and highly extroverted users exhibited discrepancies between their perceptions and decisions. Furthermore, open-ended questionnaires highlighted that users expect tone adjustments to enhance their experience while emphasizing the importance of tone consistency and ethical considerations. Our findings provide crucial insights into the design of explanation expressions.