<![CDATA[Low public awareness regarding the importance of dental health remains a significant issue in Indonesia. This situation is exacerbated by limited access to consultation services that are easy, fast, affordable, and available at any time. As a result, many dental diseases go undetected at an early stage. Additionally, the tendency to delay dental check-ups is often caused by time constraints and the distance to healthcare facilities, leading many people to avoid consulting with dentists. To address this problem, this research developed a dental health chatbot based on Natural Language Processing (NLP) using IndoBERT. The model was pretrained with the Masked Language Model (MLM) approach and fine-tuned using Next Sentence Prediction (NSP) and intent classification tasks. The dataset was compiled from Indonesian-language dental health articles, symptom–disease sentence pairs, and follow-up questions, all validated by certified dentists. The system was implemented as a web application using React JS for the frontend, Express JS and MySQL for the backend, and integrated with the NLP model through a Flask API. Evaluation results show that the chatbot can provide relevant dental health information, including lightweight consultations to assist in early symptom detection, answer follow-up questions, and generate digital medical records. Expert validation produced an average score of “Good” across the aspects of clarity, relevance, medical accuracy, and completeness, with Likert scale scores ranging from 3.53 to 3.67. This research is expected to contribute as an accessible 24-hour online dental health information service aimed at increasing public knowledge and awareness.]]>
Copyrights © 2025
