Metraipolis › archive › dc_7f41f2d6fc60
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews — arXiv:2610.35685
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35685
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:03:22.957Z
- SHA-256 of the archived text
afd8f812bbf3ae98cb30d75aa180a82bbc7b9698ad101f6f89cce0e8acc550b7- Stable URL of this page
https://metraipolis.com/documento/dc_7f41f2d6fc60
How to cite
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews — arXiv:2610.35685 — arXiv (en), https://arxiv.org/abs/2610.35685 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f41f2d6fc60 (Metraipolis archive dc_7f41f2d6fc60, sha256 afd8f812bbf3ae98cb30d75aa180a82bbc7b9698ad101f6f89cce0e8acc550b7)
BibTeX
@misc{dc7f41f2d6fc60,
title = {Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews — arXiv:2610.35685},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35685},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f41f2d6fc60; sha256 afd8f812bbf3ae98cb30d75aa180a82bbc7b9698ad101f6f89cce0e8acc550b7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35685. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.35685 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:31.008Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).