Leveraging Multi-Source Textural UGC for Neighbourhood Housing Quality Assessment: A GPT-Enhanced Framework
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911117301776384 |
|---|---|
| author | Hong, Qiyuan Zhao, Huimin Long, Ying |
| author_facet | Hong, Qiyuan Zhao, Huimin Long, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16657 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Multi-Source Textural UGC for Neighbourhood Housing Quality Assessment: A GPT-Enhanced Framework Hong, Qiyuan Zhao, Huimin Long, Ying Computers and Society Computation and Language I.2.7; K.4.1 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. |
| title | Leveraging Multi-Source Textural UGC for Neighbourhood Housing Quality Assessment: A GPT-Enhanced Framework |
| topic | Computers and Society Computation and Language I.2.7; K.4.1 |
| url | https://arxiv.org/abs/2508.16657 |