IMPLEMENTATION OF INDOBERT IN AN EXTRACTIVE QUESTION ANSWERING CHATBOT FOR INFORMATION SERVICES AT LAZIS SULTAN AGUNG
Abstract
Advances in AI and Natural Language Processing (NLP) technology have facilitated the use of chatbots as a means of providing automated information in various sectors, including religious and social organizations. LAZIS Sultan Agung still operates its information services manually via WhatsApp and in-person interactions, which limits responsiveness due to time and staff availability. This research aims to create an Extractive Question Answering (EQA)-based information chatbot utilizing the IndoBERT model to automatically assist users in obtaining information about services, programs, zakat, and donations at LAZIS Sultan Agung.
The approach used in this research involves TF-IDF for the context retrieval process and IndoBERT for the answer extraction step. The dataset was obtained from official documents and the LAZIS Sultan Agung knowledge base, which contains service information and frequently asked questions. This web-based system uses Flask and MySQL for data storage.
The evaluation results show that the system achieved an Exact Match (EM) value of 0.5294, Cosine Similarity of 0.7875, Precision of 0.8059, Recall of 0.8244, and F1-Score of 0.8052. Furthermore, black box testing showed that the chatbot was able to provide appropriate answers to user questions and could reject questions outside the scope of the system. Thus, the developed chatbot can accelerate, automate, and improve the efficiency of the information receiving process of LAZIS Sultan Agung.
Keyword : Chatbot, IndoBERT, Extractive Question Answering, TF-IDF, NLP.
References
T. I. Ramadhan, A. Supriatman, dan T. R. Kurniawan, “Evaluasi dan Implementasi Indobert Question Answering (QA) pada Domain Spesifik Menggunakan Mean Reciprocal Rank,” Jurnal Algoritma, vol. 21, no. 1, hlm. 180–188, Mei 2024, doi: 10.33364/algoritma/v.21-1.1542.
A. Rendy Harenza dan A. Dwi Indriyanti, “Pengembangan Layanan Informasi FAQ Berbasis Chatbot di Badan Pendapatan Daerah Kota Surabaya Menggunakan Framework RASA,” Journal of Informatics and Computer Science, vol. 06, 2025.
M. Andika dan J. Juliana, “ZAKAT DIGITALIZATION: TRANSFORMATION OF ZAKAT MANAGEMENT THROUGH SHARIA FINTECH,” 2025.
F. A. Rojak, A. I. Purnamasari, A. Bahtiar, dan E. Wahyudin, “PENGEMBANGAN CHATBOT LAYANAN PUBLIK BERBASIS NATURAL LANGUAGE PROCESSING DI MAL PELAYANAN PUBLIK GARUT”.
V. R. Prasetyo, N. Benarkah, dan V. J. Chrisintha, “Implementasi Natural Language Processing Dalam Pembuatan Chatbot Pada Program Information Technology Universitas Surabaya,” Teknika, vol. 10, no. 2, hlm. 114–121, Jul 2021, doi: 10.34148/teknika.v10i2.370.
T. I. Ramadhan, A. Supriatman, dan T. R. Kurniawan, “Evaluasi dan Implementasi Indobert Question Answering (QA) pada Domain Spesifik Menggunakan Mean Reciprocal Rank,” Jurnal Algoritma, vol. 21, no. 1, hlm. 180–188, Mei 2024, doi: 10.33364/algoritma/v.21-1.1542.
J. Devlin, M.-W. Chang, K. Lee, K. T. Google, dan A. I. Language, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.”
T. I. Ramadhan, A. Supriatman, dan T. R. Kurniawan, “Evaluasi dan Implementasi Indobert Question Answering (QA) pada Domain Spesifik Menggunakan Mean Reciprocal Rank,” Jurnal Algoritma, vol. 21, no. 1, hlm. 180–188, Mei 2024, doi: 10.33364/algoritma/v.21-1.1542.
M. Mustaqim, A. Gunawan, Y. Bagus Pratama, dan I. Zaliman, “PENGEMBANGAN CHATBOT LAYANAN PUBLIK MENGGUNAKAN MACHINE LEARNING DAN NATURAL LANGUANGE PROCESSING,” 2023.
