Scholarlink

<p>Point-of-interest&#xa0;(POI) recommendation systems play an important role in various location-based services by improving the user experience. Previous research has leveraged large-scale visit records to predict a user’s next visit POI based on the behavior of similar users. However, with the increasing emphasis on privacy preservation, there is a shift towards zero-shot recommendation that does not require training and only uses individual visit history data. As a better alternative to traditional zero-shot recommender systems, this paper proposes a novel zero-shot recommender system leveraging the ability of pre-trained large language models&#xa0;(LLMs) to understand human behavior called <i>ZeroPOIRec</i>. <i>ZeroPOIRec</i> involves a <i>profiler module</i> that enables LLMs to extract individual user preferences from multiple aspects, including spatio-temporal patterns and individual characteristics, and a <i>recommender module</i> that enhances the zero-shot POI recommendation performance via candidate refinement and prioritization. Through experiments using a benchmark dataset and a newly introduced real-world dataset with semantic variables, we demonstrate that, despite <i>ZeroPOIRec</i> being a zero-shot approach, it outperforms state-of-the-art methods in terms of recommendation performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Large language models are zero-shot point-of-interest recommenders

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月6日

查看全文
  • Joeun Kim,
  • Youngjin Seo,
  • Yeonsoo Kim,
  • Junhyeok Kang,
  • Jeeho Shin,
  • Patara Trirat,
  • Jae-Gil Lee

摘要

Point-of-interest (POI) recommendation systems play an important role in various location-based services by improving the user experience. Previous research has leveraged large-scale visit records to predict a user’s next visit POI based on the behavior of similar users. However, with the increasing emphasis on privacy preservation, there is a shift towards zero-shot recommendation that does not require training and only uses individual visit history data. As a better alternative to traditional zero-shot recommender systems, this paper proposes a novel zero-shot recommender system leveraging the ability of pre-trained large language models (LLMs) to understand human behavior called ZeroPOIRec. ZeroPOIRec involves a profiler module that enables LLMs to extract individual user preferences from multiple aspects, including spatio-temporal patterns and individual characteristics, and a recommender module that enhances the zero-shot POI recommendation performance via candidate refinement and prioritization. Through experiments using a benchmark dataset and a newly introduced real-world dataset with semantic variables, we demonstrate that, despite ZeroPOIRec being a zero-shot approach, it outperforms state-of-the-art methods in terms of recommendation performance.