Recommendation-as-Experience: A framework for context-sensitive adaptation in conversational recommender systems

2026-01-12

AI Summary

This work addresses a critical gap in conversational recommender systems, which typically prioritize ranking accuracy while overlooking users’ implicit experiential goals—namely, educational, exploratory, and affective dimensions of interaction. Through multi-domain user studies, the authors quantify the relative priorities of these experiential objectives and propose the Recommendation-as-Experience (RAE) framework. RAE employs Bayesian hierarchical ordinal regression to model both domain-level and individual-level preferences, encoding contextual and user signals into a structured state representation that guides experience-aligned dialogue policies. The architecture is model-agnostic and integrates diverse retrieval, heuristic logic, and controllable generation via large language models. Experiments across multiple domains demonstrate RAE’s effectiveness in jointly optimizing recommendation accuracy and interaction quality, while also revealing, for the first time, the cross-objective stability of user autonomy preferences.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

While Conversational Recommender Systems (CRS) have matured technically, they frequently lack principled methods for encoding latent experiential aims as adaptive state variables. Consequently, contemporary architectures often prioritise ranking accuracy at the expense of nuanced, context-sensitive interaction behaviours. This paper addresses this gap through a comprehensive multi-domain study ($N = 168$) that quantifies the joint prioritisation of three critical interaction aims: educative (to inform and justify), explorative (to diversify and inspire), and affective (to align emotionally and socially). Utilising Bayesian hierarchical ordinal regression, we establish domain profiles and perceived item value as systematic modulators of these priorities. Furthermore, we identify stable user-level preferences for autonomy that persist across distinct interactional goals, suggesting that agency is a fundamental requirement of the conversational experience. Drawing on these empirical foundations, we formalise the Recommendation-as-Experience (RAE) adaptation framework. RAE systematically encodes contextual and individual signals into structured state representations, mapping them to experience-aligned dialogue policies realised through retrieval diversification, heuristic logic, or Large Language Model based controllable generation. As an architecture-agnostic blueprint, RAE facilitates the design of context-sensitive CRS that effectively balance experiential quality with predictive performance.

Problem

• Conversational Recommender Systems
• context-sensitive adaptation
• experiential aims
• user autonomy
• interaction behavior

Innovation

• Conversational Recommender Systems
• Recommendation-as-Experience
• Context-sensitive Adaptation
• Bayesian Hierarchical Ordinal Regression
• User Autonomy