<![CDATA[The Central Statistics Agency (BPS) collects data through censuses and surveys to provide data to the government and the public. This data is obtained from questionnaires containing open and closed questions. One of the open questions asked is about the respondent's occupation, which will later be classified with the assignment of KBLI and KBJI codes. KBLI and KBJI are classifications used by BPS to classify economic activities. BPS uses the Sibaku Mobile application to facilitate officers in filling out KBLI and KBJI codes, but this application has shortcomings for new users. This research aims to develop a chatbot that can provide the correct KBLI/KBJI codes using Large Language Models (LLM). The chatbot development was carried out using the prototyping method. Evaluation of classification objectives showed accuracy, precision, recall, and F1-score values approaching 97%. The RAG robustness evaluation obtained a hallucination rate of 0% and an error rate of 7%. Usability testing showed a chatbot acceptance rate of 87.45%.]]>
Copyrights © 2024
