LLM-SC 框架适配活态宗教遗产：以 GPT-4o 提取帕斯帕提那神庙评论的实体、语义网络与人工评估
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
AI 导读
研究将 LLM-Social Computing 框架适配至尼泊尔帕斯帕提那神庙，在 GPT-4o 提取提示词中定义 12 类实体、4 类关系和 9 个方面情感维度，应用于 3,939 条语料中固定随机抽取的 2,500 条 Tripadvisor 英文评论，产出 11,286 条实体记录，其中新增的 8 类神圣遗产类型占 64.8%。
正文 · 原文
Abstract:Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and emotionally mixed experiences at living sacred heritage sites. We adapted the LLM-Social Computing (LLM-SC) framework to Pashupatinath Temple, Nepal, by specifying a 12-type entity taxonomy (four original LLM-SC types plus eight sacred-heritage types), four relation types and nine aspect-sentiment dimensions in a GPT-4o extraction prompt, which was applied to a fixed random sample of 2,500 English-language Tripadvisor reviews from a processed corpus of 3,939. The exports contain 11,286 entity, 6,232 aspect-sentiment and 5,590 relation records, covering 2,485, 2,487 and 2,433 reviews, respectively; the eight added sacred-heritage types account for 64.8% of entity records. Against an adjudicated two-annotator reference for 200 reviews, exact normalized surface-and-type matching gave provisional entity scores of 41.0% precision, 21.8% recall and 28.4% micro-F1. Aspect-presence F1 was 53.6% and end-to-end aspect-plus-polarity F1 was 42.6%. Human adjudication supported 153 of 194 first-listed relation candidates (one per review; 78.9%), a candidate-level rate that does not estimate relation recall or whole-graph precision. The contribution is a culturally grounded, domain-specific adaptation with component-wise human evaluation and explicit reproducibility and generalization limitations.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35685 [cs.CL] |
| (or arXiv:2610.35685v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35685 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hari Sitaula [view email]
[v1]
Mon, 26 Oct 2026 16:20:00 UTC (605 KB)
来源：arXiv cs.AI · arxiv.org