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

2025-08-11

AI Summary

Existing content-based recommender systems typically employ simplistic aggregation strategies (e.g., averaging or concatenation) to model user preferences, failing to capture the dynamic interplay between long- and short-term interests. To address this, we propose a time-aware semantic user profiling framework. First, we leverage large language models to convert raw user behavioral sequences into natural-language descriptions, which are then encoded by BERT into semantically rich embeddings. Second, we design a dual-temporal attention mechanism that separately models long- and short-term preferences and dynamically fuses them. Our approach explicitly distinguishes and jointly models temporal evolution and semantic meaning. Extensive experiments on multiple real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines. Results validate that integrating semantic enhancement with time-sensitive modeling substantially improves recommendation accuracy.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Modeling dynamic user preferences for better recommendations
• Capturing interactions between short-term and long-term preferences
• Generating semantically rich user profiles using LLMs

Innovation

• LLM-driven temporal user profiling
• BERT-encoded natural language representations
• Attention-based dynamic preference fusion