Semantic FAQ Chatbot Using SBERT (Sentence-BERT) and Cosine Similarity for Academic Services
DOI:
https://doi.org/10.47709/brilliance.v5i2.7027Keywords:
Semantic Chatbot, Sentence-BERT, Cosine Similarity, Frequently Asked Questions, Natural Language ProcessingAbstract
Handling repetitive inquiries in academic environments requires significant time and human resources, potentially delaying service delivery. This study developed a semantic FAQ chatbot using Sentence-BERT (SBERT) and Cosine Similarity to improve efficiency and consistency of academic information services at Universitas Jambi. The system encodes user queries into dense vector embeddings and compares them with FAQ entries using cosine similarity. A dataset of 65 frequently asked questions was collected through interviews and direct observation with students, lecturers, staff, and helpdesk officers. To evaluate semantic understanding, these entries were expanded into 130 question variations using paraphrasing. Model performance was measured with a confusion matrix and standard metrics. At a similarity threshold of 0.5, the system achieved 79.2% accuracy, 81.7% precision, 96.3% recall, and an F1-score of 88.4%. The results show that SBERT effectively identifies semantically similar questions with different wordings, handling both formal and informal Indonesian queries. High recall demonstrates that most relevant questions were successfully retrieved, while precision remains sufficient to ensure reliable responses. This study demonstrates that SBERT-based semantic matching can successfully handle Indonesian academic FAQ with diverse linguistic variations, enabling 24/7 accessibility and consistent service delivery independent of staff availability. Future work should expand the dataset to include emerging queries and conduct pilot deployment to validate operational effectiveness and user satisfaction
References
Ahmed, A., Hassan, A., Aziz, S., Abd-alrazaq, A. A., Ali, N., Alzubaidi, M., Al-Thani, D., Elhusein, B., Siddig, M. A., Ahmed, M., & Househ, M. (2023). Chatbot features for anxiety and depression: A scoping review. Health Informatics Journal, 29(1). https://doi.org/10.1177/14604582221146719
Anbiya, M., Islam, N., Warsito, B., & Nurhayati, O. D. (2024). Ai-Driven Chatbot Implementation for Enhancing Customer Service in Higher Education: a Case Study From Universitas Negeri Semarang. Journal of Theoretical and Applied Information Technology, 31(14), 5690–5701. www.jatit.org
Andika Isma, Rosidah, R., Sigit Sahalik Rahman, Nasrullah, N., Arif Setiawan Syam, & Novita Sari. (2023). Analisis Penggunaan Chatbot Berbasis AI pada Model Hybrid di Jurusan Teknik Informatika dan Komputer. Journal of Vocational, Informatics and Computer Education, 1(2), 79–92. https://doi.org/10.61220/voice.v1i2.20239
Babu, A., & Boddu, S. B. (2024). BERT-Based Medical Chatbot: Enhancing Healthcare Communication through Natural Language Understanding. Exploratory Research in Clinical and Social Pharmacy, 13(December 2023), 100419. https://doi.org/10.1016/j.rcsop.2024.100419
Fiddin, F. Y., Komarudin, A., & Melina, M. (2024). Chatbot Informasi Penerimaan Mahasiswa Baru Menggunakan Metode FastText dan LSTM. Journal of Applied Computer Science and Technology, 5(1), 33–39. https://doi.org/10.52158/jacost.v5i1.648
Hikmah, N., Ariyanti, D., & Pratama, F. A. (2022). Implementasi Chatbot Sebagai Virtual Assistant di Universitas Panca Marga Probolinggo menggunakan Metode TF-IDF. JTIM?: Jurnal Teknologi Informasi Dan Multimedia, 4(2), 133–148. https://doi.org/10.35746/jtim.v4i2.225
Koco?, J., Cichecki, I., Kaszyca, O., Kochanek, M., Szyd?o, D., Baran, J., Bielaniewicz, J., Gruza, M., Janz, A., Kanclerz, K., Koco?, A., Koptyra, B., Mieleszczenko-Kowszewicz, W., Mi?kowski, P., Oleksy, M., Piasecki, M., Radli?ski, ?., Wojtasik, K., Wo?niak, S., & Kazienko, P. (2023). ChatGPT: Jack of all trades, master of none. Information Fusion, 99(May), 101861. https://doi.org/10.1016/j.inffus.2023.101861
Lantana, D., Ningsih, S., Waluyo, T., & Winarsih, W. (2023). RANCANG BANGUN CHATBOT BERBASIS RULE-BASED SEBAGAI PUSAT INFORMASI CALON MAHASISWA BARU DI UNIVERSITAS NASIONAL. Jurnal Sistem Informasi Bisnis (JUNSIBI), 4(1 SE-Articles). https://doi.org/10.55122/junsibi.v4i1.695
Larasati, P. D., Irawan, A., Anwar, S., Mulya, M. F., Dewi, M. A., & Nurfatima, I. (2022). Chatbot helpdesk design for digital customer service. Applied Engineering and Technology, 1(3), 138–145. https://doi.org/10.31763/aet.v1i3.684
Maynur, H., Ibrahim, A., & Sudin, S. (2024). Sistem Rekomendasi Topik Penelitian Berbasis Chatbot Whatsapp Menggunakan Algoritma Cosine Similarity (Studi Kasus Prodi Teknik Informatika Universitas Muhammadiyah Maluku Utara ). Jurnal Teknologi Informatika (J-TIFA), 7(2), 56–62. https://doi.org/10.52046/j-tifa.v7i2
Mirza, D., Suryani, L., Latip, L., & Aditiya, V. (2023). Literature Riview: Peran Teknologi Informasi dalam Meningkatkan Efisiensi dan Efektivitas Birokrasi. Jurnal Administrasi Publik Dan Bisnis, 5(1), 51–55. https://doi.org/10.36917/japabis.v5i1.84
Permatasari, D. A., & Maharani, D. A. (2021). Combination of Natural Language Understanding and Reinforcement Learning for Booking Bot. Journal of Electrical, Electronic, Information, and Communication Technology, 3(1), 12. https://doi.org/10.20961/jeeict.3.1.49818
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(December 2022), 100856. https://doi.org/10.1016/j.rineng.2022.100856
Prayoga, T. R., Wibowo, S. A., & Rudhistiar, D. (2024). Rancang Bangun Chatbot Berbasis Web Dengan Menggunakan Metode Text Similarity Pada Layanan Pusat Informasi Pusdiklat Dpr Ri. JATI (Jurnal Mahasiswa Teknik Informatika), 7(5), 2944–2950. https://doi.org/10.36040/jati.v7i5.7566
Purwosunu, A. G., Pujiharsono, H., & Hikmah, I. (2023). Sistem Prediksi Pergantian Infus Berbasis Internet of Things (IoT). Journal of Telecommunication Electronics and Control Engineering (JTECE), 5(2), 86–96. https://doi.org/10.20895/jtece.v5i2.1038
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using siamese BERT-networks. EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference, 3982–3992. https://doi.org/10.18653/v1/d19-1410
Reimers, N., & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. In B. Webber, T. Cohn, Y. He, & Y. Liu (Eds.), Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 4512–4525). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.365
Sentence Transformers. (2025). Paraphrase-multilingual-MiniLM-L12-v2. Hugging Face. https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Solomon, E., & Tilahun, S. L. (2024). Rule based chatbot design methods: A review. Journal of Computational Science & Data Analytics, 1(01 SE-), 75–84. https://doi.org/10.69660/jcsda.01012405
Su, H., Shen, X., Zhao, S., Zhou, X., Hu, P., Zhong, R., Niu, C., & Zhou, J. (2020). Diversifying dialogue generation with non-conversational text. Proceedings of the Annual Meeting of the Association for Computational Linguistics, 7087–7097. https://doi.org/10.18653/v1/2020.acl-main.634
Suherlan, M. R., Asriyanik, A., & Pambudi, A. (2023). UMMIBOT sebagai Media Layanan Informasi Penerimaan Mahasiswa Baru Universitas Muhammadiyah Sukabumi. Jurnal Informatika Terpadu, 9(2), 82–91. https://doi.org/10.54914/jit.v9i2.893
UPA TIK Universitas Jambi. (2025). Unit Penunjang Akademik Teknologi Informasi dan Komunikasi. Upatik Unja. https://upatik.unja.ac.id/
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Rahul Marcellino Holis, Pradita Eko Prasetyo Utomo, Benedika Ferdian Hutabarat
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
info@itscience.org, web: 
