<![CDATA[Most local tourist destinations in Indonesia still rely on static information systems that are unable to provide real-time responses to visitors, including the Terawang Ecopark Cave in Blora Regency, Central Java. This research developed an intelligent chatbot called Smart Virtual Guide based on the Large Language Model (LLM) which is integrated into the information system of Goa Terawang Ecopark, as well as analyzing the level of user acceptance using the Technology Acceptance Model (TAM). Different from previous tourism chatbot research which is generally based on conventional NLP and only supports one language, the novelty of this research lies in the integration of LLM with the support of Indonesian and Javanese at the same time in local tourist destinations. The development of the system uses the Waterfall method with functional testing through Black Box Testing and data collection from 30 respondents using a Likert scale questionnaire. The results of the Black Box Testing test showed that all features were valid, while the TAM results obtained an average percentage of 80.95% (Good category) on the PEOU, PU, BI, and ATU variables. These findings prove that LLM-based approaches with regional language support are effective in improving the quality of digital tourism information services that are more interactive, inclusive, and adaptive.]]>
Copyrights © 2026
