Temporal User Profiling with LLMs: Balancing Short-Term and Long-Term Preferences for Recommendations

TL;DR

This paper introduces LLM-TUP, a novel user profiling method that uses large language models to explicitly model and fuse short-term and long-term user preferences, significantly improving recommendation accuracy.

Contribution

The paper presents a new temporally aware user profiling technique leveraging LLMs and attention mechanisms, capturing nuanced preference dynamics beyond traditional methods.

Findings

LLM-TUP outperforms baseline models on real-world datasets.

Semantic user profiles generated by LLMs enhance recommendation quality.

Explicit modeling of preference dynamics improves personalization accuracy.

Abstract

Accurately modeling user preferences is crucial for improving the performance of content-based recommender systems. Existing approaches often rely on simplistic user profiling methods, such as averaging or concatenating item embeddings, which fail to capture the nuanced nature of user preference dynamics, particularly the interactions between long-term and short-term preferences. In this work, we propose LLM-driven Temporal User Profiling (LLM-TUP), a novel method for user profiling that explicitly models short-term and long-term preferences by leveraging interaction timestamps and generating natural language representations of user histories using a large language model (LLM). These representations are encoded into high-dimensional embeddings using a pre-trained BERT model, and an attention mechanism is applied to dynamically fuse the short-term and long-term embeddings into a comprehensive user profile. Experimental results on real-world datasets demonstrate that LLM-TUP achieves substantial improvements over several baselines, underscoring the effectiveness of our temporally aware user-profiling approach and the use of semantically rich user profiles, generated by LLMs, for personalized content-based recommendation.