{"ID":2880163,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16657","arxiv_id":"2508.16657","title":"Leveraging Multi-Source Textural UGC for Neighbourhood Housing Quality Assessment: A GPT-Enhanced Framework","abstract":"This study leverages GPT-4o to assess neighbourhood housing quality using multi-source textural user-generated content (UGC) from Dianping, Weibo, and the Government Message Board. The analysis involves filtering relevant texts, extracting structured evaluation units, and conducting sentiment scoring. A refined housing quality assessment system with 46 indicators across 11 categories was developed, highlighting an objective-subjective method gap and platform-specific differences in focus. GPT-4o outperformed rule-based and BERT models, achieving 92.5% accuracy in fine-tuned settings. The findings underscore the value of integrating UGC and GPT-driven analysis for scalable, resident-centric urban assessments, offering practical insights for policymakers and urban planners.","short_abstract":"This study leverages GPT-4o to assess neighbourhood housing quality using multi-source textural user-generated content (UGC) from Dianping, Weibo, and the Government Message Board. The analysis involves filtering relevant texts, extracting structured evaluation units, and conducting sentiment scoring. A refined housing...","url_abs":"https://arxiv.org/abs/2508.16657","url_pdf":"https://arxiv.org/pdf/2508.16657v1","authors":"[\"Qiyuan Hong\",\"Huimin Zhao\",\"Ying Long\"]","published":"2025-08-20T08:29:40Z","proceeding":"cs.CY","tasks":"[\"cs.CY\",\"cs.CL\"]","methods":"[]","has_code":false}