VideolandGPT: A User Study on a Conversational Recommender System
This work addresses improving user experience and fairness in conversational recommender systems for video-on-demand platforms, but it is incremental as it builds on existing ranking models and LLMs.
The paper tackled enhancing conversational recommender systems using LLMs by introducing VideolandGPT for a VOD platform, finding that a personalized version outperformed a non-personalized one in accuracy and user satisfaction, with both versions increasing visibility of less popular items but showing inconsistent fairness due to recommendations of unavailable content.
This paper investigates how large language models (LLMs) can enhance recommender systems, with a specific focus on Conversational Recommender Systems that leverage user preferences and personalised candidate selections from existing ranking models. We introduce VideolandGPT, a recommender system for a Video-on-Demand (VOD) platform, Videoland, which uses ChatGPT to select from a predetermined set of contents, considering the additional context indicated by users' interactions with a chat interface. We evaluate ranking metrics, user experience, and fairness of recommendations, comparing a personalised and a non-personalised version of the system, in a between-subject user study. Our results indicate that the personalised version outperforms the non-personalised in terms of accuracy and general user satisfaction, while both versions increase the visibility of items which are not in the top of the recommendation lists. However, both versions present inconsistent behavior in terms of fairness, as the system may generate recommendations which are not available on Videoland.