Jurnal
Development of an Academic Chatbot Based on Natural Language Processing for Student Information Services at Universitas Bina Darma
Recursive Journal of Informatics · Vol. 4 No. 2 (2026) · hlm. 113–126
- ISSN
- 2986-6588, 2963-5551
- Terbit
- 2026-09-30
- Penerbit
- Universitas Negeri Semarang
- Bahasa
- eng
Abstrak
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.
Kata kunci
Jaringan kolaborasi para penulis
40 penulis · 74 tautan kepenulisan bersama · menampilkan 40 yang paling banyak terhubung
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
- Universitas Halu Oleo
- Universitas Islam Negeri Ar-Raniry
- Afiliasi tidak diketahui
- Organisasi berbeda
- Organisasi sama
- Afiliasi tidak diketahui
- Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
| Rekan penulis | Organisasi | Artikel bersama |
|---|---|---|
| Dedi Fazriansyah Putra | Afiliasi tidak diketahui | 2 |
| Harun Harun | Universitas Halu Oleo | 2 |
| Wan Siti Adibah Wan Dahalan | Afiliasi tidak diketahui | 2 |
| Muhammad Arsyad | Universitas Halu Oleo | 1 |
| Wardiman Wardiman | Afiliasi tidak diketahui | 1 |
| La Ode Muhammad Elwan | Universitas Halu Oleo | 1 |
| Muhamad Samsul Alam | Afiliasi tidak diketahui | 1 |
| Norimune Kawai | Afiliasi tidak diketahui | 1 |
| Muhammad Khairul Rijal | Afiliasi tidak diketahui | 1 |
| Muhammad Azwar Paramma | Afiliasi tidak diketahui | 1 |
| Syamsu Rijal | Afiliasi tidak diketahui | 1 |
| Nur Fadhillah Muhlis | Afiliasi tidak diketahui | 1 |
| Andi Badli Rompegading | Afiliasi tidak diketahui | 1 |
| Rizal Irfandi | Afiliasi tidak diketahui | 1 |
| Muhammad Arafah | Afiliasi tidak diketahui | 1 |
| Ahmad Yani | Afiliasi tidak diketahui | 1 |
| Lia Hastuti | Afiliasi tidak diketahui | 1 |
| Saida Rasnovi | Afiliasi tidak diketahui | 1 |
| Cut Nanda Devira | Afiliasi tidak diketahui | 1 |
| Mardianti Mardianti | Afiliasi tidak diketahui | 1 |
| Fachruddin Azmi | Afiliasi tidak diketahui | 1 |
| Toni Nasution | Afiliasi tidak diketahui | 1 |
| Khairul Anwar | Afiliasi tidak diketahui | 1 |
| Saiful Akmal | Universitas Islam Negeri Ar-Raniry | 1 |
| Faraha Hamidi | Afiliasi tidak diketahui | 1 |
| Ikhramah Ismed | Afiliasi tidak diketahui | 1 |
| Abd Mujahid Hamdan | Afiliasi tidak diketahui | 1 |
| Ridha Maulana | Afiliasi tidak diketahui | 1 |
| T. Mulkan Safri | Afiliasi tidak diketahui | 1 |
| Fitria Gemasih | Afiliasi tidak diketahui | 1 |
| Juniar Afrida | Afiliasi tidak diketahui | 1 |
| Rian Afkar | Afiliasi tidak diketahui | 1 |
| Rusydi Rusydi | Afiliasi tidak diketahui | 1 |
| Dinda Yulia Darsa | Afiliasi tidak diketahui | 1 |
| Samsul Bahri | Afiliasi tidak diketahui | 1 |
| Cut Maulida Rahmah | Afiliasi tidak diketahui | 1 |
| Meriska Afryani | Afiliasi tidak diketahui | 1 |
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.