TY - GEN
T1 - Understanding user preferences for interaction styles in conversational recommender system
T2 - 37th Australian Conference on Human-Computer Interaction, OZCHI 2025
AU - Mahmud, Raj
AU - Berkovsky, Shlomo
AU - Prasad, Mukesh
AU - Kocaballi, A. Baki
N1 - 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.
PY - 2025/11/28
Y1 - 2025/11/28
N2 - Conversational Recommender Systems (CRSs) deliver personalised recommendations through multi-turn natural language dialogue and increasingly support both task-oriented and exploratory interactions. Yet, the factors shaping user interaction preferences remain underexplored. In this within-subjects study (N = 139), participants experienced two scripted CRS dialogues, rated their experiences, and indicated the importance of eight system qualities. Logistic regression revealed that preference for the exploratory interaction was predicted by enjoyment, usefulness, novelty, and conversational quality. Unexpectedly, perceived effectiveness was also associated with exploratory preference. Clustering uncovered five latent user profiles with distinct dialogue style preferences. Moderation analyses indicated that age, gender, and control preference significantly influenced these choices. These findings integrate affective, cognitive, and trait-level predictors into CRS user modelling and inform autonomy-sensitive, value-adaptive dialogue design. The proposed predictive and adaptive framework applies broadly to conversational AI systems seeking to align dynamically with evolving user needs.
AB - Conversational Recommender Systems (CRSs) deliver personalised recommendations through multi-turn natural language dialogue and increasingly support both task-oriented and exploratory interactions. Yet, the factors shaping user interaction preferences remain underexplored. In this within-subjects study (N = 139), participants experienced two scripted CRS dialogues, rated their experiences, and indicated the importance of eight system qualities. Logistic regression revealed that preference for the exploratory interaction was predicted by enjoyment, usefulness, novelty, and conversational quality. Unexpectedly, perceived effectiveness was also associated with exploratory preference. Clustering uncovered five latent user profiles with distinct dialogue style preferences. Moderation analyses indicated that age, gender, and control preference significantly influenced these choices. These findings integrate affective, cognitive, and trait-level predictors into CRS user modelling and inform autonomy-sensitive, value-adaptive dialogue design. The proposed predictive and adaptive framework applies broadly to conversational AI systems seeking to align dynamically with evolving user needs.
KW - Conversational AI
KW - Conversational Recommender System
KW - User Preference Modelling
UR - https://www.scopus.com/pages/publications/105024898336
U2 - 10.1145/3764687.3764722
DO - 10.1145/3764687.3764722
M3 - Conference proceeding contribution
AN - SCOPUS:105024898336
T3 - OZCHI: Computer-Human Interaction of Australia - Proceedings
SP - 68
EP - 80
BT - OZCHI 2025
A2 - Fredericks, Joel
A2 - Yoo, Soojeong
A2 - Minh Tran, Tram Thi
A2 - Pantidi, Nadia
A2 - Hoang, Thuong
A2 - Hoggenmueller, Marius
A2 - Caldwell, Glenda
A2 - Tag, Benjamin
A2 - Andres, Josh
A2 - Davis, Hilary
A2 - Boden, Marie
A2 - Zhu, Howe
A2 - Harman, Joel
A2 - Rahman, Jessica
PB - Association for Computing Machinery, Inc
CY - Sydney
Y2 - 29 November 2025 through 3 December 2025
ER -