Personalized News Recommendation System via LLM Embedding and Co-Occurrence Patterns

TL;DR

This paper introduces LECOP, a novel news recommendation system leveraging fine-tuned LLM embeddings and detailed co-occurrence patterns to enhance user preference modeling and recommendation accuracy.

Contribution

It presents a new approach combining LLM-based news encoding with co-occurrence pattern mining, a novel integration not previously explored in news recommendation.

Findings

Outperforms existing models in recommendation accuracy

Effectively captures user preferences through semantic and collaborative patterns

Demonstrates robustness across large-scale datasets

Abstract

In the past two years, large language models (LLMs) have achieved rapid development and demonstrated remarkable emerging capabilities. Concurrently, with powerful semantic understanding and reasoning capabilities, LLMs have significantly empowered the rapid advancement of the recommendation system field. Specifically, in news recommendation (NR), systems must comprehend and process a vast amount of clicked news text to infer the probability of candidate news clicks. This requirement exceeds the capabilities of traditional NR models but aligns well with the strengths of LLMs. In this paper, we propose a novel NR algorithm to reshape the news model via LLM Embedding and Co-Occurrence Pattern (LECOP). On one hand, we fintuned LLM by contrastive learning using large-scale datasets to encode news, which can fully explore the semantic information of news to thoroughly identify user preferences. On the other hand, we explored multiple co-occurrence patterns to mine collaborative information. Those patterns include news ID co-occurrence, Item-Item keywords co-occurrence and Intra-Item keywords co-occurrence. The keywords mentioned above are all generated by LLM. As far as we know, this is the first time that constructing such detailed Co-Occurrence Patterns via LLM to capture collaboration. Extensive experiments demonstrate the superior performance of our proposed novel method