KOMPARASI EMPAT ALGORITMA MACHINE LEARNING UNTUK KLASIFIKASI INTENT PADA CHATBOT INFORMASI AKADEMIK

Authors

  • Refaya Septianno Teknik Informatika, Universitas Krisnadwipayana
  • Risanto Darmawan Teknik Informatika, Universitas Krisnadwipayana
  • Elmi Devia Sistem Informasi, Universitas Krisnadwipayana

DOI:

https://doi.org/10.35316/jimi.v11i2.10805

Keywords:

AI chatbot,, Intent Classification, Machine Learning, NLP, Academic Information

Abstract

The development of Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies has driven the utilization of chatbots as an automated academic information service medium. A chatbot's success in understanding user queries is heavily influenced by the model's ability to classify intents. This study focuses on comparing the performance of four machine learning algorithms namely Naive Bayes, Logistic Regression, Support Vector Machine (SVM), and XGBoost in the intent classification task for an Indonesian-language academic information chatbot. The methodological approach employed is CRISP-DM, which encompasses the Business Understanding, Data Understanding, Data Preparation, Modelling, and Evaluation phases. The dataset structure is organized in a JSON format containing intent labels, variations of query patterns, and their corresponding academic responses. The data preparation procedure includes case folding, tokenization, stopword removal, and stemming using the Sastrawi library, followed by TF-IDF-based feature extraction. Model evaluation is performed using accuracy, precision, recall, and F1-score metrics to determine which algorithm delivers optimal performance in accurately classifying intents.

Downloads

Download data is not yet available.

References

[1] Munawirah, M., Mardjani, E., & Kristian, K, “Aplikasi Chatbot Berbasis Dialogflow dan NLP untuk Pelayanan Informasi Akademik pada Fakultas Ilmu Komputer Universitas Tomakaka”, 99–115, 2025.

[2] Hillary, R., Wijaya, A. C., & Susanto, M. W, “Pengembangan Chatbot Analisis Data Mahasiswa dengan Term Frequency - Inverse Document Frequency dan Logistic Regression [ Development of Student Data Analysis Chatbot Using Term Frequency - Inverse Document Frequency and Logistic Regression ]”, 01, 875–885, 2026.

[3] Hidayat, R., Mahdiana, D., & Fergina, A, “Comparative Analysis of Logistic Regression , SVM , Xgboost , and Random Forest Algorithms for Diabetes Classification”, 7(1), 281–291. https://doi.org/10.32493/jtsi.v7i1.38258, 2024.

[4] Armiady, D, “Analisis Algoritma Logistic Regression Dan Support Vector Machine Pada Kasus Klasifikasi Citra Hewan Rawa Dengan Dataset Yang Tidak Seimbang”, Data Sciences Indonesia (DSI), 4(1), 69-77, 2024.

[5] Al Farisi, F. A., Perdana, R. S., & Adikara, P. P, “Klasifikasi Intensi dengan Metode Long Short-Term Memory pada Chatbot Bahasa Indonesia”, Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), 11(5), 1051–1058. https://doi.org/10.25126/jtiik.2024118000, 2024.

[6] Fauzan, M. F., Imanda, R., & Hasbi, M. A, “Designing an Chatbot with NLP Technology in a Website-Based New Student Admission Information System”, 8(2), 358–366, 2024.

[7] Jtik, J., Teknologi, J., Qalimaturrahmah, M., & Santoso, D. B, “Aplikasi Layanan dan Informasi Akademik Berbasis Chatbot Telegram Menggunakan Natural Language Processing”, 8(2), 2024.

[8] Setiyorini, A, “Pengembangan Aplikasi Chatbot Untuk Layanan Penerimaan Mahasiswa Baru Berbasis Natural Language Processing”, Jurnal Informatika: Jurnal Pengembangan IT, 10(4), pp.1115-1126, 2025.

[9] Unisba, F. H., Teks, K., & Akademik, L, “Aplikasi chatbot berbasis nlp untuk layanan akademik studi kasus fakultas hukum unisba”, 20, 89–97, 2025.

[10] Angelina, S. J., Negara, A. B. P., & Muhardi, H, “Analisis pengaruh penerapan stopword removal pada performa klasifikasi sentimen tweet bahasa Indonesia”, Jurnal Aplikasi dan Riset Informatika, 1(2), 165-173, 2023.

[11] Bumigora Information Technology (BITe), “Evaluasi metrik klasifikasi: Accuracy, precision, recall, dan F1-score pada model machine learning”, Jurnal Bumigora Information Technology, 6(1). https://journal.universitasbumigora.ac.id/bite/article/view/4909, 2024.

[12] Carolina, V. P., Utami, E., & Yaqin, A, “Riset Jurnal Literatur: Penggunaan Metode Stemming Pada Bahasa Daerah Melayu-Ambon”, Journal of Electrical Engineering and Computer (JEECOM), 6(1), 186-196, 2024.

[13] Fahmi, M. N, “Implementasi mechine learning menggunakan Python Library: Scikit-Learn (supervised dan unsupervised learning)”, Sains Data Jurnal Studi Matematika dan Teknologi, 1(2), 87-96, 2023.

[14] Gumelar, A., Moeslim, S., Firmansyah, E., & Sutara, B, “Perbandingan Kinerja XGBoost dan IndoBERT untuk Klasifikasi Teks Kesehatan Bahasa Indonesia”, 5(2), 62–72, 2025.

[15] Hakim, L., Sobri, A., Sunardi, L., & Nurdiansyah, D, “Prediksi penyakit jantung berbasis mesin learning dengan menggunakan metode k-nn”, 07(02), 14–20, 2025.

[16] Wardhana, R. G., Wang, G., & Sibuea, F, “Penerapan machine learning dalam prediksi tingkat kasus penyakit di Indonesia”, Journal of Information System Management (JOISM), 5(1), 40-45, 2023.

Published

15-11-2026

How to Cite

Septianno, R., Darmawan, R., & Devia, E. (2026). KOMPARASI EMPAT ALGORITMA MACHINE LEARNING UNTUK KLASIFIKASI INTENT PADA CHATBOT INFORMASI AKADEMIK . Jurnal Ilmiah Informatika, 11(2), 211–220. https://doi.org/10.35316/jimi.v11i2.10805

Similar Articles

<< < 1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.