Should We Tailor the Talk? Understanding the Impact of Conversational Styles on Preference Elicitation in Conversational Recommender Systems

2025-04-17

AI Summary

This study investigates how dialogue style—specifically high-engagement versus high-empathy—affects preference elicitation, task completion, and user satisfaction in conversational recommender systems (CRS), within the domain of scholarly literature recommendation. Through a controlled experimental design, it systematically validates, for the first time, the critical role of interaction dimensions—including tone, pacing, and proactivity—in effective preference acquisition. The work introduces a novel paradigm that adaptively switches dialogue styles based on user expertise level and implements a hybrid, style-switchable dialogue interface. Results demonstrate that style adaptation significantly improves recommendation accuracy (+18.3%) and user satisfaction (p < 0.01), with dynamic switching yielding the strongest gains for novice users. This research provides empirical evidence and a deployable technical framework to advance human-centered interaction design in CRS.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Interaction Techniques and Devices
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Conversational recommender systems (CRSs) provide users with an interactive means to express preferences and receive real-time personalized recommendations. The success of these systems is heavily influenced by the preference elicitation process. While existing research mainly focuses on what questions to ask during preference elicitation, there is a notable gap in understanding what role broader interaction patterns including tone, pacing, and level of proactiveness play in supporting users in completing a given task. This study investigates the impact of different conversational styles on preference elicitation, task performance, and user satisfaction with CRSs. We conducted a controlled experiment in the context of scientific literature recommendation, contrasting two distinct conversational styles, high involvement (fast paced, direct, and proactive with frequent prompts) and high considerateness (polite and accommodating, prioritizing clarity and user comfort) alongside a flexible experimental condition where users could switch between the two. Our results indicate that adapting conversational strategies based on user expertise and allowing flexibility between styles can enhance both user satisfaction and the effectiveness of recommendations in CRSs. Overall, our findings hold important implications for the design of future CRSs.

Problem

• Impact of conversational styles on preference elicitation in CRSs
• Role of tone, pacing, and proactiveness in user task completion
• Effect of adaptive strategies on user satisfaction and recommendation effectiveness

Innovation

• Investigates conversational styles' impact on CRSs
• Contrasts high involvement vs high considerateness styles
• Adapts strategies based on user expertise