Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants

2026-06-23

AI Summary

This work addresses the limitations of traditional conversational product search, which often suffers from imprecise preference elicitation, leading to prolonged dialogues, biased recommendations, and user abandonment. To overcome these challenges, the authors propose the Dialogue-to-Discovery (D2D) framework, which innovatively integrates an attribute-aware mechanism with a multi-factor patience model. D2D enables efficient goal discovery through attribute-guided preference elicitation, adaptive query ranking, and dynamic recommendation triggering. Evaluated on a multi-domain conversational dataset constructed from Amazon Reviews, D2D demonstrates significant improvements: in simulated dialogues, it achieves a 22.2–29.9% increase in goal discovery accuracy, reduces average dialogue length by 27.5%, and lowers session abandonment rates by 6.6–16.1%. User studies further confirm that D2D substantially enhances both recommendation efficiency and user satisfaction.

Abstract

Conversational product search assistants offer a more expressive, natural, and interactive alternative to traditional keyword-based product search. With limited screen space, showing only a few items increases the need for precise preference elicitation, which can prolong conversations, leading to user frustration and session abandonment. Conversely, rushing to recommend items without a clear understanding of preferences risks poor matches and a degraded user experience. We present Dialogue to Discovery (D2D), an attribute-oriented preference elicitation framework that dynamically exploits the structure of product attributes to efficiently steer conversations toward the user's desired item. D2D adaptively prioritizes the most informative queries and strategically times product recommendations, reducing premature or off-target suggestions that harm engagement. To evaluate D2D, we curate three datasets from the Amazon Reviews corpus. In simulated conversations modelled using a multi-factor utilitarian patience framework, D2D achieves a 22.2-29.9% improvement in target-finding accuracy, 6.6-16.1% reduction in abandonment, and 27.5% shorter average conversations over the state-of-the-art baselines. A complementary user study further confirms significant gains in both user satisfaction and perceived efficiency.

Problem

• conversational product search
• preference elicitation
• attribute-aware
• user frustration
• session abandonment

Innovation

• attribute-aware preference elicitation
• conversational product search
• dynamic query prioritization
• recommendation timing
• user engagement