Development of an Academic Chatbot Based on Natural Language Processing for Student Information Services at Universitas Bina Darma
DOI:
https://doi.org/10.15294/rji.v4i2.62866Keywords:
Natural Language Processing, Academic Chatbot, Student Information Services, WhatsApp, Dialog flow ESAbstract
Purpose: Repetitive academic inquiries and substantial linguistic variation in informal Indonesian student messages can reduce the consistency and timeliness of university information services. This study develops and evaluates an academic chatbot for student information services at Universitas Bina Darma through WhatsApp.
Methods/Study design/approach: An applied engineering-research approach was employed. An exploratory questionnaire involving 100 active students was used to identify dominant information needs and representative query expressions, while verified institutional documents were used separately to construct controlled service responses. The implemented architecture integrates Baileys as the WhatsApp messaging gateway, Node.js/Express as the orchestration layer, Dialog flow ES for intent and entity recognition, and MySQL for conversation logging and monitoring. The final agent contains 129 custom intents, 22 entities, and 2,572 training-phrase entries. An operational confidence threshold of 0.70 was applied to route uncertain inputs to fallback handling. Evaluation was conducted at four layers: 13 black-box functional scenarios, 24 intent cases representing major service families and out-of-scope input, 15 response-conformity cases, and six end-to-end integration scenarios.
Result/Findings: All black-box scenarios produced the expected outputs. Intent agreement reached 95.83%, response conformity reached 86.67%, and all integration scenarios were successful. The difference between intent agreement and response conformity indicates that correct intent recognition does not necessarily guarantee an equally specific or institutionally appropriate answer when response coverage is incomplete.
Novelty/Originality/Value: The contribution of this study is therefore positioned as applied system engineering rather than a new NLP algorithm. It demonstrates a deployable, confidence-controlled architecture that separates informal-query recognition from verified institutional delivery and evaluates recognition, answer conformity, and technical integration as distinct quality dimensions. Broader intent coverage, human-user evaluation, threshold calibration, load testing, and dynamic integration with institutional information systems remain necessary for wider deployment.
References
[1] [1] H. T. Hien, P.-N. Cuong, L. N. H. Nam, H. L. T. K. Nhung, and L. D. Thang, “Intelligent Assistants in Higher-Education Environments: The FIT-EBot, a Chatbot for Administrative and Learning Support,” in Proc. 9th International Symposium on Information and Communication Technology (SoICT), 2018, pp. 69–76, doi: 10.1145/3287921.3287937.
[2] [2] H. A. Santoso et al., “Dinus Intelligent Assistance (DINA) Chatbot for University Admission Services,” in Proc. 2018 International Seminar on Application for Technology of Information and Communication (iSemantic), 2018, pp. 417–423, doi: 10.1109/ISEMANTIC.2018.8549797.
[3] [3] B. R. Ranoliya, N. Raghuwanshi, and S. Singh, “Chatbot for University Related FAQs,” in Proc. 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017, pp. 1525–1530, doi: 10.1109/ICACCI.2017.8126057.
[4] [4] A. Z. Amrullah, A. S. Anas, and G. Primajati, “Implementasi Chatbot sebagai Virtual Assistant Penerimaan Mahasiswa Baru pada Universitas Bumigora,” Jurnal Bumigora Information Technology (BITe), vol. 4, no. 1, pp. 17–26, 2022, doi: 10.30812/bite.v4i1.1664.
[5] [5] Munawirah, E. Mardjani, and K. Kristian, “Aplikasi Chatbot Berbasis Dialogflow dan NLP untuk Pelayanan Informasi Akademik pada Fakultas Ilmu Komputer Universitas Tomakaka,” Jurnal Ilmiah Multidisiplin Amsir, vol. 3, no. 2, pp. 99–115, 2025. [Online]. Available: https://stieamsir.ac.id/journal/index.php/abrj/article/view/610
[6] [6] D. Saientisna, I. G. A. G. A. Kadyanan, I. B. M. Mahendra, and V. G. A. Pradika, “Chatbot Pelayanan Informasi Kampus,” Jurnal Nasional Teknologi Informasi dan Aplikasinya, vol. 2, no. 1, pp. 251–254, 2023, doi: 10.24843/JNATIA.2023.v02.i01.p29.
[7] [7] B. B. C. Zoraya, S. Mumin, and A. Andhykac, “WhatsApp Chatbot Implementation of New Student Admission Information Service in Universitas Nahdlatul Ulama Sidoarjo,” Informatics, Electrical and Electronics Engineering (Infotron), vol. 5, no. 1, pp. 26–37, 2025, doi: 10.33474/infotron.v5i1.23365.
[8] [8] M. A. Ahwan, N. Abiadhoh, A. B. Kusuma, and U. F. Alam, “Pembangunan WhatsApp Chatbot sebagai Layanan Kecerdasan Buatan di Perpustakaan UIN Walisongo Semarang,” Berkala Ilmu Perpustakaan dan Informasi, vol. 20, no. 1, pp. 119–132, 2024, doi: 10.22146/bip.v20i1.7043.
[9] [9] K. Ralston, Y. Chen, H. Isah, and F. H. Zulkernine, “A Voice Interactive Multilingual Student Support System Using IBM Watson,” in Proc. 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), 2019, pp. 1924–1929, doi: 10.1109/ICMLA.2019.00309.
[10] [10] N. P. Patel, D. R. Parikh, D. A. Patel, and R. R. Patel, “AI and Web-Based Human-Like Interactive University Chatbot (UNIBOT),” in Proc. 2019 3rd International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2019, pp. 148–150, doi: 10.1109/ICECA.2019.8822176.
[11] [11] R. Faurina, D. Revanza, and A. Sopran, “Pengembangan Chatbot Menggunakan Deep Feed-Forward Neural Network sebagai Pusat Layanan Informasi Akademik,” Jurnal Eksplora Informatika, vol. 11, no. 2, pp. 120–129, 2023, doi: 10.30864/eksplora.v11i2.833.
[12] [12] M. M. A. Abdelmoiz, M. M. M. Mostafa, and T. H. A. Soliman, “Developing an Educational Chatbot for Scientific Data Management Course Using DialogFlow,” Appl. Math. Inf. Sci., vol. 18, no. 3, pp. 629–640, 2024, doi: 10.18576/amis/180315.
[13] [13] B. Albab and I. Nuryasin, “Pengembangan Chatbot Berbasis WhatsApp Menggunakan Dialogflow dan NLP untuk Layanan Informasi Toko Fotokopi,” JIKO (Jurnal Informatika dan Komputer), vol. 9, no. 3, pp. 594–605, 2025, doi: 10.26798/jiko.v9i3.2046.
[14] [14] O. Peña-Cáceres, A. Tavara-Ramos, T. Correa-Calle, and T. More-More, “WhatsApp-Based Cloud Service Chatbot Application for Emergencies or Disasters,” J. Adv. Inf. Technol., vol. 15, no. 3, pp. 435–445, 2024, doi: 10.12720/jait.15.3.435-445.
[15] [15] A. Balderas, R. F. García-Mena, M. Huerta, N. Mora, and J. M. Dodero, “Chatbot for Communicating with University Students in Emergency Situation,” Heliyon, vol. 9, no. 9, Art. no. e19517, 2023, doi: 10.1016/j.heliyon.2023.e19517.
[16] [16] R. W. Sugiarto, P. Sokibi, and P. Rizkiyah, “Chatbot Layanan Akademik Calon Mahasiswa UCIC Menggunakan Metode Retrieval-Augmented Generation,” Jurnal Riset Rumpun Ilmu Teknik, vol. 4, no. 3, pp. 246–249, 2025, doi: 10.55606/jurritek.v4i3.6664.
[17] [17] C. W. Okonkwo and A. Ade-Ibijola, “Chatbots Applications in Education: A Systematic Review,” Comput. Educ. Artif. Intell., vol. 2, Art. no. 100033, 2021, doi: 10.1016/j.caeai.2021.100033.
[18] [18] L. Labadze, M. Grigolia, and L. Machaidze, “Role of AI Chatbots in Education: Systematic Literature Review,” Int. J. Educ. Technol. High. Educ., vol. 20, Art. no. 56, 2023, doi: 10.1186/s41239-023-00426-1.
[19] [19] I. Casanueva, T. Temčinas, D. Gerz, M. Henderson, and I. Vulić, “Efficient Intent Detection with Dual Sentence Encoders,” in Proc. 2nd Workshop on Natural Language Processing for Conversational AI, 2020, pp. 38–45, doi: 10.18653/v1/2020.nlp4convai-1.5.
[20] [20] H. Zhang, H. Xu, T.-E. Lin, and R. Lyu, “Discovering New Intents with Deep Aligned Clustering,” Proc. AAAI Conf. Artif. Intell., vol. 35, no. 16, pp. 14365–14373, 2021, doi: 10.1609/aaai.v35i16.17689.
[21] [21] T. Yamane, Statistics: An Introductory Analysis, 2nd ed. New York, NY, USA: Harper & Row, 1967.
[22] [22] Google Cloud, “Intent Matching – Dialogflow ES,” Google Cloud Documentation, 2026. [Online]. Available: https://docs.cloud.google.com/dialogflow/es/docs/intents-matching. Accessed: Sep. 9, 2026.
[23] [23] T. Debets, S. K. Banihashem, D. Joosten-Ten Brinke, T. E. J. Vos, G. Maillette de Buy Wenniger, and G. Camp, “Chatbots in education: A systematic review of objectives, underlying technology and theory, evaluation criteria, and impacts,” Comput. Educ., vol. 234, Art. no. 105323, 2025, doi: 10.1016/j.compedu.2025.105323.
[24] [24] B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” in Proc. 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020, pp. 843–857, doi: 10.18653/v1/2020.aacl-main.85.
[25] [25] S. Larson et al., “An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction,” in Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019, pp. 1311–1316, doi: 10.18653/v1/D19-1131.
[26] [26] J. Deriu, A. Rodrigo, A. Otegi, G. Echegoyen, S. Rosset, E. Agirre, and M. Cieliebak, “Survey on Evaluation Methods for Dialogue Systems,” Artif. Intell. Rev., vol. 54, pp. 755–810, 2021, doi: 10.1007/s10462-020-09866-x.
