ETNOVAN: A GROUNDBREAKING CONVERSATIONAL AI FRAMEWORK FOR PRESERVING AND ADVANCING INDIGENOUS ETHNOSCIENCE KNOWLEDGE IN INDONESIA
Fuente:
Zenodo
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2025
|
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866902258820579328 |
|---|---|
| author | ISMAIL, IRFAN ANANDA Festiyed, Festiyed Sulistya, Yuda Insani, Munadia Khairil, Arif |
| author_facet | ISMAIL, IRFAN ANANDA Festiyed, Festiyed Sulistya, Yuda Insani, Munadia Khairil, Arif |
| contents | <p>The rapid pace of globalization threatens the rich tapestry of indigenous knowledge, particularly in the domain of ethnoscience, which is often transmitted orally across generations. To address this challenge, we introduce EtnoVan, a novel conversational AI system designed to preserve, disseminate, and foster engagement with Indonesian ethnoscience. EtnoVan leverages a sophisticated architecture built upon a fine-tuned Large Language Model (LLM), specifically a customized variant of GLM 4.5 Air, to provide an interactive and intuitive educational experience. The system is designed to understand and generate human-like responses to queries about a wide range of ethnoscientific topics, from traditional medicine to indigenous agricultural practices. Our work presents a significant novelty by creating a dedicated AI for cultural heritage preservation, demonstrating high user engagement and a measurable improvement in knowledge retention among users. This paper details the system’s architecture, the methodology for model fine-tuning, and a comprehensive evaluation of its performance and educational impact, positioning EtnoVan as a pioneering tool in the intersection of artificial intelligence and cultural preservation.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17277783 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ETNOVAN: A GROUNDBREAKING CONVERSATIONAL AI FRAMEWORK FOR PRESERVING AND ADVANCING INDIGENOUS ETHNOSCIENCE KNOWLEDGE IN INDONESIA ISMAIL, IRFAN ANANDA Festiyed, Festiyed Sulistya, Yuda Insani, Munadia Khairil, Arif <p>The rapid pace of globalization threatens the rich tapestry of indigenous knowledge, particularly in the domain of ethnoscience, which is often transmitted orally across generations. To address this challenge, we introduce EtnoVan, a novel conversational AI system designed to preserve, disseminate, and foster engagement with Indonesian ethnoscience. EtnoVan leverages a sophisticated architecture built upon a fine-tuned Large Language Model (LLM), specifically a customized variant of GLM 4.5 Air, to provide an interactive and intuitive educational experience. The system is designed to understand and generate human-like responses to queries about a wide range of ethnoscientific topics, from traditional medicine to indigenous agricultural practices. Our work presents a significant novelty by creating a dedicated AI for cultural heritage preservation, demonstrating high user engagement and a measurable improvement in knowledge retention among users. This paper details the system’s architecture, the methodology for model fine-tuning, and a comprehensive evaluation of its performance and educational impact, positioning EtnoVan as a pioneering tool in the intersection of artificial intelligence and cultural preservation.</p> |
| title | ETNOVAN: A GROUNDBREAKING CONVERSATIONAL AI FRAMEWORK FOR PRESERVING AND ADVANCING INDIGENOUS ETHNOSCIENCE KNOWLEDGE IN INDONESIA |
| url | https://doi.org/10.5281/zenodo.17277783 |