Using LLMs to Capture Users' Temporal Context for Recommendation

TL;DR

This paper systematically investigates how Large Language Models can generate time-aware user profiles that improve recommendation quality by capturing both short-term and long-term preferences, with effectiveness depending on data richness.

Contribution

It provides a detailed analysis of LLMs' ability to model dynamic user contexts and disentangle different temporal preferences for recommendation purposes.

Findings

LLMs produce semantically rich, time-aware user profiles.

Effectiveness varies with dataset density, performing better in dense domains.

Temporal context modeling benefits recommendation accuracy in certain environments.

Abstract

Effective recommender systems demand dynamic user understanding, especially in complex, evolving environments. Traditional user profiling often fails to capture the nuanced, temporal contextual factors of user preferences, such as transient short-term interests and enduring long-term tastes. This paper presents an assessment of Large Language Models (LLMs) for generating semantically rich, time-aware user profiles. We do not propose a novel end-to-end recommendation architecture; instead, the core contribution is a systematic investigation into the degree of LLM effectiveness in capturing the dynamics of user context by disentangling short-term and long-term preferences. This approach, framing temporal preferences as dynamic user contexts for recommendations, adaptively fuses these distinct contextual components into comprehensive user embeddings. The evaluation across Movies&TV and Video Games domains suggests that while LLM-generated profiles offer semantic depth and temporal structure, their effectiveness for context-aware recommendations is notably contingent on the richness of user interaction histories. Significant gains are observed in dense domains (e.g., Movies&TV), whereas improvements are less pronounced in sparse environments (e.g., Video Games). This work highlights LLMs' nuanced potential in enhancing user profiling for adaptive, context-aware recommendations, emphasizing the critical role of dataset characteristics for practical applicability.