Pengembangan Chatbot Informasi Pariwisata di Bali Menggunakan Metode Hybrid RAG
DOI:
https://doi.org/10.46880/jmika.Vol10No2.pp741-751Keywords:
Hybrid Retrieval-Augmented Generation, Gemini, BM25, Bi-Encoder, Cross-EndcoderAbstract
The development of artificial intelligence-based chatbots has enabled the automated delivery of information. However, chatbots still face challenges in generating relevant answers to user queries. In addition, Retrieval-Augmented Generation (RAG) systems that rely on a single retrieval method have limitations in identifying the most relevant documents, which may affect the quality of the generated responses. Therefore, this study aims to implement a Hybrid Retrieval-Augmented Generation (Hybrid RAG) approach by combining BM25, Bi-Encoder, and Cross-Encoder models. The dataset used consists of 200 Bali tourism documents collected from web scraping, the Bali Central Bureau of Statistics (BPS), and Kaggle. The system was developed using BM25 as the initial retrieval stage, Bi-Encoder for semantic retrieval, Cross-Encoder for reranking, and Gemini as the answer generation model. The evaluation was conducted using Recall@k, Precision@k, and nDCG@k metrics to measure retrieval performance, as well as response time testing to evaluate system performance. The results show that the Hybrid RAG approach, utilizing BM25, Bi-Encoder, and Cross-Encoder, improves document retrieval quality through keyword-based matching, semantic similarity analysis, and reranking processes. Based on the findings, the Hybrid RAG approach was successfully implemented in a Bali tourism information chatbot and was able to provide relevant context to support the answer generation process.
References
Abdurrazzaq, M. A., Tjiong, E. L., Fasya, A., Hiu, M., & Tanuwidjaya, J. (2025). An Indonesian Chatbot for Disease Diagnosis Using Retrieval-Augmented Generation. Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng-Seri Informatika), 10(3), 1877-1887. https://doi.org/10.35314/9nnkn955
Agiyola, T., & Indriati, B. R. (2019). Relevance Feedback Pada Sistem Temu Kembali Informasi Dokumen E-Book Berbahasa Indonesia Menggunakan Metode BM25. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer E-ISSN, 2548(5), 964X.
Andina, S. P., Pramukantoro, E. S., & Yahya, W. (2025). Studi Kinerja TF-IDF dan IndoBERT dalam Rekomendasi Resep Berbasis Mobile dengan Arsitektur Microservice. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 9(10).
Aprilio, P., Felix, M., Nugraha, P. S., & Fahmi, H. (2025). Hybrid Feature Combination of TF-IDF and BERT for Enhanced Information Retrieval Accuracy. JISA(Jurnal Informatika Dan Sains), 8(1), 8–15. https://doi.org/10.31326/jisa.v8i1.2179
Bintana, R. R. (2012). Penerapan Model Okapi Bm25 Pada Sistem Temu Kembali Informasi. Seminar Nasional Teknologi Informasi Komunikasi Dan Industri (SNTIKI) 4, 273–279.
Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., & Liu, Z. (2024). M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2318–2335. https://doi.org/10.18653/v1/2024.findings-acl.137
Cuconasu, F., Trappolini, G., Siciliano, F., & Filice, S. (2024). The Power of Noise: Redefining Retrieval for RAG Systems. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’24), July 14â•fi18, 2024, Washington, DC, USA (Vol. 1, Number 1). Association for Computing Machinery. https://doi.org/10.1145/3626772.3657834
Evidently AI. (2026). Normalized Discounted Cumulative Gain (NDCG) explained. https://www.evidentlyai.com/
Fathuddin, M. A. H., Mandyartha, E. P., & Nurlaili, A. L. (2025). Penerapan Sentence-Bert dan Cosine Similarity untuk Pencarian Semantik Dokumen Skripsi dalam Format PDF. Ranah Research: Journal of Multidisciplinary Research and Development, 8(1), 322–337. https://doi.org/10.38035/rrj.v8i1.1865
Helviansyah, T., Harahap, N. S., Irsyad, M., & Negara, B. S. (2025). Sistem Tanya Jawab Berbasis Chatbot Website Menggunakan Gemini Ai Pada Data Fiqih Kontemporer. Journal of Information System Management (JOISM), 7(1), 38–47. https://doi.org/10.24076/joism.2025v7i1.2082
Kasmaee, A. S. (2025). Domain-Specific Text Embedding Models for Information Retrieval.
Lu, M., Chen, C., & Eickhoff, C. (2025). Cross-Encoder Rediscovers a Semantic Variant of BM25.
Luan, Y., Eisenstein, J., Toutanova, K., & Collins, M. (2021). Sparse, dense, and attentional representations for text retrieval. Transactions of the Association for Computational Linguistics, 9, 329–345. https://doi.org/10.1162/tacl_a_00369
Lubis, M. S. Y. (2021, August). Implementasi artificial intelligence pada system manufaktur terpadu. In Prosiding Seminar Nasional Teknik UISU (SEMNASTEK) (Vol. 4, No. 1, pp. 1-7).
Mikael, K., Oz, C., Rashid, T. A., & Nariman, G. S. (2025). A Hybrid Chatbot Model for Enhancing Administrative Support in Education: Comparative Analysis, Integration, and Optimization. IEEE Access, 13(February), 50741–50760. https://doi.org/10.1109/ACCESS.2025.3552501
Pais, S., Cordeiro, J., & Jamil, M. L. (2022). NLP based platform as a service a brief (pp. 1–26).
Sanjaya, R. A., & Winarno, E. (2024). Pengembangan Chatbot Informasi Pariwisata di Kabupaten Pati Menggunakan Metode Natural Language Processing Berbasis Dialogflow. Jutisi : Jurnal Ilmiah Teknik Informatika Dan Sistem Informasi, 13(1), 368. https://doi.org/10.35889/jutisi.v13i1.1828
Situmeang, R. N., Jamaluddin, Purba, E. N., & Gunawati Harianja, E. J. (2023). Designing Chatbot About Tourism Recommendations In North Sumatra. 2023 International Conference of Computer Science and Information Technology (ICOSNIKOM), 1–4. https://doi.org/10.1109/ICoSNIKOM60230.2023.10364534
Su, C., Wen, J., Kang, J., Wang, Y., Pan, H., & Hossain, M. S. (2024). Hybrid rag-empowered multi-modal llm for secure healthcare data management: A diffusion-based contract theory approach. arXiv preprint arXiv:2407.00978.
Syah, M. P., Wardani, A. P., Idhom, M., & Trimono, T. (2025). Perbandingan representasi teks TF-IDF dan BERT terhadap akurasi cosine similarity dalam penilaian otomatis jawaban berbasis teks. Data Sciences Indonesia (DSI), 5(1), 47-59. https://doi.org/10.47709/dsi.v5i1.6021
Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., & Gurevych, I. (2021). BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. Advances in Neural Information Processing Systems. https://doi.org/10.48550/arXiv.2104.08663
Trung, Q. H., Hoang, L. T., & Phuc, N. V. H. (2024). Optimizing Multi-Stage Language Models for Effective Text Retrieval.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 I Kadek Dwi Pratama, Ni Wayan Wisswani, Gde Brahupadhya Subiksa
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
