AI-Based Chatbot Development for Academic Information Services at Universitas Negeri Medan and an Analysis of Indonesian Language Usage

Muhammad Rafli Wijaya; Alya Namira; Ananda Syafika; Syairal Fahmy Dalimunthe

doi:10.59934/jaiea.v5i3.2376

Authors

Muhammad Rafli Wijaya Universitas Negeri Medan
Alya Namira Universitas Negeri Medan
Ananda Syafika Universitas Negeri Medan
Syairal Fahmy Dalimunthe Universitas Negeri Medan

DOI:

https://doi.org/10.59934/jaiea.v5i3.2376

Keywords:

Information Academic Chatbot, Retrieval-Augmented Generation, Academic Information Service, Llama Chatbot, Artificial Intelligence Based Chatbot

Abstract

The efficiency of academic information services remains a major challenge in higher education institutions, particularly in responding to student inquiries quickly and independently. This study develops an artificial intelligence-based chatbot system for academic information services at Universitas Negeri Medan (UNIMED) by utilizing the LLaMA 3.1 8B Instant Large Language Model (LLM) via the Groq API within a Retrieval-Augmented Generation (RAG) framework. The system was built using a three-tier architecture consisting of a React.js (Vite) frontend, a Node.js with Express backend, and a Supabase (PostgreSQL) database serving as the academic FAQ knowledge base. The Cross-Industry Standard Process for Data Mining (CRISP-DM) was adopted as the research methodology. System evaluation was conducted using Black-Box Testing across four main scenarios: questions available in the FAQ, follow-up questions requiring conversational context, off-topic questions, and reference link validation all of which yielded a pass status. Furthermore, Indonesian language testing demonstrated that the system is capable of understanding diverse student language variations, including formal language, informal expressions, academic abbreviations, and ambiguous queries, while maintaining appropriate academic communication etiquette. The results indicate that the RAG approach is effective in reducing AI hallucination risks, and that this web-based chatbot offers broader accessibility compared to previous messaging platform-based chatbot systems.

Downloads

Download data is not yet available.

References

S. Elysia and Herianto, “Chatbot Berbasis Retrieval Augmented Generation (RAG) untuk Peningkatan Layanan Informasi Sekolah,” Journal TIFDA (Technology Information and Data Analytic), vol. 1, no. 2, pp. 52–58, Dec. 2024, doi: 10.70491/tifda.v1i2.52.

M. Abid Nadzif, Saefurrohman, and R. Soelistijadi, “Penggunaan Teknologi Natural Language Processing dalam Sistem Chatbot Untuk Peningkatan Layanan Informasi Administrasi Publik,” Indonesian Journal of Computer Science Attribution, vol. 13, no. 1, pp. 2024–1227, 2024.

M. Erline and Y. Christian, “A R T I C L E I N F O Web-Based Chatbot with Natural Language Processing and Knuth-Morris-Pratt (Case Study: Universitas Internasional Batam),” Jurnal Sains dan Teknologi, vol. 11, no. 1, pp. 132–141, 2022, doi: 10.23887/jst-undiksha.v11i1.

L. Fan, L. Li, Z. Ma, S. Lee, H. Yu, and L. Hemphill, “A Bibliometric Review of Large Language Models Research from 2017 to 2023,” 2024. doi: https://doi.org/10.1145/3664930.

M. L. Husain, Y. Wibisono, and A. Anisyah, “Development of an Academic Services Chatbot Based on Retrieval-Augmented Generation (RAG),” Brilliance: Research of Artificial Intelligence, vol. 5, no. 2, pp. 727–735, Aug. 2025, doi: 10.47709/brilliance.v5i2.6719.

M. Saddam Heykal Bustomy, M. Alfan Rosid, and H. Setiawan, “Implementasi Chatbot Informasi Akademik Berbasis Retrieval-Augmented Generation (RAG) Menggunakan LLaMA 3.1 [Implementation of an Academic Information Chatbot Based on Retrieval-Augmented Generation (RAG) Using LLaMA 3.1],” 2026. doi: https://doi.org/10.21070/ups.9995.

F. Darmawan, W. Gusdya Purnama, and A. A. Nurcahyo, “Prototipe Sistem Chatbot Panduan Akademik Fakultas Teknik Unpas menggunakan Large Language Model,” Jurnal Sistem dan Informatika, vol. 19, no. 2, 2025.

M. Qalimaturrahmah and D. B. Santoso, “Aplikasi Layanan dan Informasi Akademik Berbasis Chatbot Telegram Menggunakan Natural Language Processing,” Jurnal Teknologi Informasi dan Komunikasi), vol. 8, no. 2, p. 2024, 2024, doi: 10.35870/jti.

M Ikhsan, Dila Marta Putri, Siti Nurjanah, Asde Rahmawati, Fahrizal Fahrizal, and Bastul Wajhi Akramunnas, “Implementasi Teknologi Chatbot sebagai Media Informasi di Universitas Negeri Medan,” Jurnal Teknik Mesin, Industri, Elektro dan Informatika, vol. 4, no. 1, pp. 265–277, Feb. 2025, doi: 10.55606/jtmei.v4i1.4820.

S. H. Bariah #1, W. P. #2, and K. A. N. Imania, “Pengembangan Virtual Assistant Chatbot Berbasis Whatsapp Pada Pusat Layanan Informasi Mahasiswa Institut Pendidikan Indonesia-Garut,” Jurnal PETIK, vol. 8, 2022.

D. Melinda Br Bangun et al., “PT. Media Akademik Publisher DOMINASI BAHASA GAUL DI KALANGAN GEN Z DALAM KONTEKS PRESENTASI AKADEMIK: STUDI DISKRIPTIF PADA MAHASISWA UNIVERSITAS TRUNOJOYO MADURA Aisyah Dwi Anggraini 5 Septian Trio Bagus S 6,” JMA), vol. 2, pp. 3031–5220, 2024, doi: 10.62281.

S. A. Putri, Z. Alpris Wulandari, N. F. Manalu, and A. N. Wulandari, “Interaksi Akademik di Ruang Digital: Analisis Kontak Bahasa dalam Chat WhatsApp Mahasiswa Sastra Indonesia Universitas Negeri Medan,” Journal of Innovative Research, vol. 03, pp. 188–193, 2026, [Online]. Available: https://ziaresearch.or.id/index.php/mesada

M. R. Febriansyah et al., “IMPLEMENTASI CHATBOT SEBAGAI VIRTUAL ASSISTANT : SYSTEMATIC LITERATURE REVIEW,” 2025.

G. Putu Mahendra Putra, A. Tenriawaru, P. Studi Ilmu Komputer, F. Matematika dan Ilmu Pengetahuan Alam, and U. Halu Oleo, “Rancang Bangun Virtual Assistant Chatbot Menggunakan Node.Js pada Layanan Sistem Informasi Akademik,” 2023.