Skip to main navigation Skip to search Skip to main content

Evaluating user experience in Conversational Recommender Systems: a systematic review across classical and LLM-powered approaches

Raj Mahmud, Yufeng Wu, Abdullah Bin Sawad, Shlomo Berkovsky, Mukesh Prasad, A. Baki Kocaballi

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Conversational Recommender Systems (CRSs) are receiving growing research attention across domains, yet their user experience (UX) evaluation remains limited. Existing reviews largely overlook empirical UX studies, particularly in adaptive and large language model (LLM)-based CRSs. To address this gap, we conducted a systematic review following PRISMA guidelines, synthesising 23 empirical studies published between 2017 and 2025. We analysed how UX has been conceptualised, measured, and shaped by domain, adaptivity, and LLM. Our findings reveal persistent limitations: post hoc surveys dominate, turn-level affective UX constructs are rarely assessed, and adaptive behaviours are seldom linked to UX outcomes. LLM-based CRSs introduce further challenges, including epistemic opacity and verbosity, yet evaluations infrequently address these issues. We contribute a structured synthesis of UX metrics, a comparative analysis of adaptive and nonadaptive systems, and a forward-looking agenda for LLM-aware UX evaluation. These findings support the development of more transparent, engaging, and user-centred CRS evaluation practices.

Original languageEnglish
Title of host publicationOZCHI 2025
Subtitle of host publicationProceedings of the 37th Australian Conference on Human-Computer Interaction (OzCHI '25)
EditorsJoel Fredericks, Soojeong Yoo, Tram Thi Minh Tran, Nadia Pantidi, Thuong Hoang, Marius Hoggenmueller, Glenda Caldwell, Benjamin Tag, Josh Andres, Hilary Davis, Marie Boden, Howe Zhu, Joel Harman, Jessica Rahman
Place of PublicationSydney
PublisherAssociation for Computing Machinery, Inc
Pages81-93
Number of pages13
ISBN (Electronic)9798400720161
DOIs
Publication statusPublished - 28 Nov 2025
Event37th Australian Conference on Human-Computer Interaction, OZCHI 2025 - Sydney, Australia
Duration: 29 Nov 20253 Dec 2025

Publication series

NameOZCHI: Computer-Human Interaction of Australia - Proceedings
PublisherAssociation for Computing Machinery

Conference

Conference37th Australian Conference on Human-Computer Interaction, OZCHI 2025
Country/TerritoryAustralia
CitySydney
Period29/11/253/12/25

Bibliographical note

Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • Conversational Recommender Systems
  • Systematic Review
  • User Experience Evaluation

Fingerprint

Dive into the research topics of 'Evaluating user experience in Conversational Recommender Systems: a systematic review across classical and LLM-powered approaches'. Together they form a unique fingerprint.

Cite this