Implementasi Chatbot Cuaca Berbasis SBERT dan LLM Gemini Menggunakan OpenWeather API
Article Sidebar
Main Article Content
Abstract
Article Summary
This study discusses the development of a Natural Language Processing (NLP)-based weather chatbot dashboard capable of receiving natural Indonesian language queries and displaying weather information interactively. The system combines Sentence-BERT (SBERT) paraphrase-multilingual-MiniLM-L12-v2 as a text similarity engine, Gemini 2.5-flash Large Language Model (LLM) as a natural language summary generator, and the OpenWeather API as a real-time weather data source. A zero-shot semantic similarity approach is used without fine-tuning, with intent determination based on cosine similarity and a threshold of 0.5 optimized through testing several threshold values. The development method used is the Waterfall model with stages of requirements analysis, architectural design, NLP module implementation and API integration, React dashboard frontend development, as well as functional black-box testing and performance metric evaluation. The test results show that SBERT with a threshold of 0.5 produces an intent classification accuracy of 90% in 20 test scenarios, which increases to 100% after being combined with rule-based auto-adjust and fallback mechanisms. City entity extraction with a 1–3 word sliding window against city.list.json achieved 100% accuracy on 15 city-based queries, while macro metrics yielded a precision of 0.9286, a recall of 0.90, and an F1‑score of 0.8958. The integration of the OpenWeather API and Gemini enables the presentation of natural, informative weather summaries and visualization of real-time weather data in the form of interactive graphs on a React-based dashboard.
Keywords
Article Keywords
Downloads
Article Details
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
License: All articles are licensed under 
Amur, Z. H., Kwang Hooi, Y., Bhanbhro, H., Dahri, K., & Soomro, G. M. (2023). Short-text semantic similarity (STSS): Techniques, challenges and future perspectives. Applied Sciences (Switzerland), 13(6). MDPI. https://doi.org/10.3390/app13063911.
Bharath, D., Dolok Lauro Sitorus, M., Teknologi Informasi, F., & Tarumanagara, U. (2024). Perancangan dashboard sebagai perbandingan visualisasi data iklim BMKG di Jakarta. Journal of Information Technology and Computer Science (INTECOMS), 7(6).
Hardiman, J. P. W., Thio, D. C., Zakiyyah, A. Y., & Meiliana. (2024). AI-powered dialogues and quests generation in role-playing games using Google’s Gemini and Sentence-BERT framework. Procedia Computer Science, 245(C), 1111–1119. https://doi.org/10.1016/j.procs.2024.10.340.
Holis, R. M., Utomo, P. E. P., & Hutabarat, B. F. (2025). Semantic FAQ chatbot using SBERT (Sentence-BERT) and cosine similarity for academic services. Brilliance: Research of Artificial Intelligence, 5(2), 915–922. https://doi.org/10.47709/brilliance.v5i2.7027.
Khadija, M. A., Harjito, B., Saberi, M., Paradhita, A. N., & Nurharjadmo, W. (2025). Generative Indonesian chatbot for university major selection using transformers embedding. IAES International Journal of Artificial Intelligence, 14(4), 3474–3482. https://doi.org/10.11591/ijai.v14.i4.pp3474-3482.
Lee, J. S., & Hsiang, J. (2020). Patent classification by fine-tuning BERT language model. World Patent Information, 61. https://doi.org/10.1016/j.wpi.2020.101965.
Owen, C., & Suhartono, D. (2025). Intent classification in artificial intelligence-based customer service chatbot for e-wallet service providers. International Journal of Computing and Digital Systems, 17(1). https://doi.org/10.12785/ijcds/1571046212.
Peyton, K., & Unnikrishnan, S. (2023). A comparison of chatbot platforms with the state-of-the-art Sentence-BERT for answering online student FAQs. Results in Engineering, 17. https://doi.org/10.1016/j.rineng.2022.100856.
Rashid, H. W., & Ahmed, S. H. (2025). Fine-tuning SBERT for semantic research title classification in trilingual university repository. Kurdistan Journal of Applied Research, 10(2), 119–135. https://doi.org/10.24017/science.2025.2.9.
Rusydi, A. S., Win Afgani, Fatimah, Dian Septaria, Salsabila, & Gebriella Zahira. (2024). Metode penelitian kuantitatif pendekatan ilmiah untuk analisis data. Jurnal Review Pendidikan dan Pengajaran, 7(3), 11279–11289.
Safitri, L., & Erfina, A. (2025). Analisis sentimen perbandingan Lange Language Model study kasus: GPT, Gemini dan Llama menggunakan BERT sentiment analysis. Jurnalnya Orang Pintar Komputer, 14(3). https://doi.org/10.30591/smartcomp.v13i1.8373.
Setiawan, E. I., Purnomo, M. H., & Saputra, D. G. (2024). Pemrograman multiplatform dengan Flutter dilengkapi pengembangan AI chatbot dan retrieval augmented generation dengan Gemini. Deepublish.
Siddik Hasibuan, M., Rifqi Al Fauzan, M., Komputer, I., dan Teknologi, S., & Islam Negeri Sumatera Utara, U. (2024). Kombinasi TF-IDF dan Neural Network untuk pelayanan informasi Al-Qur’an dalam bentuk chatbot. Jurnal Fasilkom, 14(2), 318–324.
Sopyandi, D., Tria Sati, A., Prabowo, A., Maulana Putra Setya, D., Agung Nugroho, F., Studi Teknik Informatika Universitas Pamulang, P., Raya Puspitek, J., Pamulang, K., & Tangerang Selatan, K. (2024). Bangun aplikasi tracking cuaca (Weather App) menggunakan public API berbasis website. Jurnal Ilmiah Wahana Pendidikan, 2024(20), 209–215. https://doi.org/10.5281/zenodo.14274718.
Tat, O., & Aydoğan, İ. (2024). Discovering hidden patterns: Applying topic modeling in qualitative research. Journal of Measurement and Evaluation in Education and Psychology, 15(3), 247–259. https://doi.org/10.21031/epod.1539694.