<![CDATA[This research aims to develop a chatbot based on Natural Language Processing (NLP) using the Rasa framework and the DIETClassifier model to classify user intent from historical data about Dewi Durga within the Indonesian cultural context. Dewi Durga’s stories play a significant role in preserving Indonesian heritage, especially as younger generations increasingly disengage from traditional knowledge. This study highlights the importance of digital preservation as a strategy to keep these narratives accessible and relevant. The chatbot is designed to provide interactive, educational conversations about Durga mythology, helping users understand Hindu cultural values through an intuitive and accessible digital platform. The research methodology involves several key stages: data cleaning and preparation, intent labeling, splitting data into training and testing sets, and evaluating model performance using a Confusion Matrix. Metrics such as accuracy, precision, recall, and F1-score are used to assess classification performance. The DIETClassifier model achieved strong results, with an accuracy of 0.94, precision of 0.90, recall of 0.93, and an F1-score of 0.91, indicating high effectiveness in intent classification. Following model training and evaluation, the chatbot was deployed using Flask, allowing real-time user interaction through a responsive web interface. This project contributes to the use of NLP-based chatbot technology in cultural preservation, specifically focusing on Dewi Durga’s mythology in Javanese and Balinese traditions. By digitizing these stories, the study aims to prevent cultural erosion and promote broader engagement with heritage. The approach may also be applied to other domains that require deep cultural understanding.]]>
Copyrights © 2025
