AI-Enabled Chatbot for Preserving and Promoting Kuching Cultural Heritage
JOIV : International Journal on Informatics Visualization · 31.05.2026 · 10 (3) · 1176
DOI: 10.62527/joiv.10.3.4557 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 31.05.2026. Verfasst von Wai Shiang Cheah und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
This paper presents BazaarBot, an AI-powered chatbot developed to preserve and promote the cultural heritage of the Kuching Old Bazaar (KOB). KOB is a cultural heritage in Sarawak, Malaysia which was a well-known 200-year-old Chinatown and former trading hub from the Brooke era now. Many are unaware of the history this place has despite its rich historical significance. This is most likely due to limited information, slow and inefficient retrieval from online sources. The proposed system integrates a fine-tuned large language model (Flan-T5) with a knowledge graph to produce interactive, accurate, and context-aware responses. A custom dataset of question-and-answer pairs was generated using the KOB documentation via the Gemini API. This dataset was then used to fine tune the model. Additionally, a knowledge graph was constructed by extracting structured data from the same documentation, enhancing response depth and precision. The chatbot was evaluated across three methodologies which was language model only, knowledge graph only, and a combined approach. The system is a hybrid combination of Graph Retrieval-Augmented Generation (RAG) technique using Neo4j knowledge graph and fine-tuned Flan T5 (Encoder-Decoder) model to understand user query and reply with relevant context and continuity. From the testing and evaluation, this hybrid combination boasts a higher percentage (96.5%) at displaying accurate and relevant information to the user compared to only using the encoder-decoder model (81%) and knowledge graph (85%) independently. Further research includes voice and image recognition, lesser dependencies on Gemini API call and propose a distributed chatbot system.
Zitieren
APA
Cheah, W. S., Yeow, L. Z., Boer, V. D., Sadok, B. Y., Lu, M., & Chai, K. S. (2026). AI-Enabled Chatbot for Preserving and Promoting Kuching Cultural Heritage. JOIV : International Journal on Informatics Visualization, 10(3), 1176. https://doi.org/10.62527/joiv.10.3.4557
Vancouver
Cheah WS, Yeow LZ, Boer VD, Sadok BY, Lu M, Chai KS. AI-Enabled Chatbot for Preserving and Promoting Kuching Cultural Heritage. JOIV : International Journal on Informatics Visualization. 2026;10(3):1176. doi:10.62527/joiv.10.3.4557
BibTeX
@article{Cheah2026,
author = {Cheah, Wai Shiang and Yeow, Lik Zen and Boer, Victor De and Sadok, Ben Yahia and Lu, Marlene and Chai, Kit Siang},
title = {AI-Enabled Chatbot for Preserving and Promoting Kuching Cultural Heritage},
journal = {JOIV : International Journal on Informatics Visualization},
year = {2026},
volume = {10},
number = {3},
pages = {1176},
doi = {10.62527/joiv.10.3.4557}
}
EUVIMED