Predicting Student Dependency on ChatGPT for Academic Tasks Using  Naive Bayes Classification

Risha Febrianti; Sul Fitriana; Asrafah; Stephen Amukune

doi:10.66053/aieds.v1i2.23

Authors

Risha Febrianti Universitas Negeri Makassar
Sul Fitriana Universitas Negeri Makassar
Asrafah Universitas Negeri Makassar
Stephen Amukune MATE Institute of Education

DOI:

https://doi.org/10.66053/aieds.v1i2.23

Keywords:

ChatGPT dependency, Educational data mining, higher education decision making, Naive Bayes classification, Student learning independence

Abstract

Purpose – This study aims to predict and classify the level of student dependency on ChatGPT in completing academic tasks using the Naive Bayes algorithm to support data-driven decision making in higher education.
Methods – A quantitative survey approach was employed involving 254 active undergraduate students from the Department of Informatics and Computer Engineering at a public university in Indonesia. Data were collected through a Likert-scale questionnaire measuring five behavioral indicators: purpose of ChatGPT use, interaction frequency and duration, understanding of generated outputs, trust in AI responses, and learning independence. The collected data were cleaned, numerically encoded, and labeled into three dependency categories (low, medium, high). A Naive Bayes classification model was implemented using Orange Data Mining and evaluated under three data split scenarios: 90:10, 80:20, and 70:30.
Findings – The results indicate that the 70:30 data split achieved the highest classification performance, with an AUC value of 0.973, accuracy of 85.3%, F1-score of 0.866, and precision of 0.909. These results demonstrate that the Naive Bayes algorithm is effective in identifying distinct patterns of student dependency on ChatGPT based on multidimensional behavioral data.
Research limitations – This study is limited to a single academic program and relies on self-reported questionnaire data, which may constrain the generalizability of the findings across different educational contexts.
Originality – This study provides empirical evidence on the application of probabilistic classification models to assess student dependency on generative AI, contributing to educational decision sciences by informing institutional policies on balanced and responsible AI use in higher education.

References

Amijoyo, T., & Mumtaza, A. (2023). Implementation Naïve Bayes Method To Prediction Of Student Achievement at Bimbel Sonai West Jakarta. 6(2), 139–144.

Andrea, D., Putri, R., Putri, E., & Winarsih, S. (2025). Hubungan Ketergantungan ChatGPT dengan Kemandirian Akademik Siswa SMPN 198 Jakarta. 6(2), 100–106.

April-september, N. N. E., Indria, L., & Hakim, M. F. (2025). Analisis Ketergantungan Mahasiswa Universitas Merangin terhadap ChatGPT dengan Machine Learning. 7924(September), 35–41.

Atieku-boateng, H., Addo-tara, A., Osei, R. D., Atieku-boateng, B., & Ameko, S. K. (2024). Evaluating ChatGPT’s Effect on Students’ Independent Learning Experiences: The Case of Pentecost University, a Ghanaian Higher Educational Institution. 11, 20–40. https://doi.org/10.63467/red.11.2024.art2

Cahyanto, H. N., Pamungkas, P., & Zulkarnain, O. (2024). Pengaruh Penggunaan ChatGPT Terhadap Kemandirian Mahasiswa Dalam Menyelesaikan Tugas Akademik. PREPOTIF J. Kesehat. Masy., 8(1), 930–935.

Fathony, M. H., Hizraini, A. A., Aulia, R., & Penggunaan, E. (2024). Jurnal Review Pendidikan dan Pengajaran, Volume 7 Nomor 4, 2024 | 16601. 7, 16601–16607.

Hasanein, A. M., & Sobaih, A. E. E. (2023). Drivers and Consequences of ChatGPT Use in Higher Education: Key Stakeholder Perspectives. 2599–2614.

Ijaz, M., & Yadegaridehkordi, E. (2024). ChatGPT in the higher education: A systematic literature review and research challenges. International Journal of Educational Research, 127, 102411. https://doi.org/10.1016/j.ijer.2024.102411

Infortech, J., Wahyudi, N., Putri, D. A., Bina, U., & Informatika, S. (2025). Implementasi algoritma naïve bayes terhadap. 2(16).

Iskandar, A., Retnawati, H., Hadi, S., Utami, L., & Amiruddin, E. G. (2025). Ingénierie des Systèmes d’ Information Naïve Bayes Classifier-Based Intelligent System for Student Academic Performance Assessment. 30(6), 1609–1620.

J. Sistem et al. (2023). Analisis Sentimen Chat GPT sebagai Masa Depan Pekerja pada Media Sosial Youtube menggunakan Algoritma Klasifikasi Naïve Bayes. 14(2), 193–200.

Klimova, B., Bachmann, P., & Frutos-bencze, D. (2025). The use of ChatGPT in academia: Perspectives of higher education students. Cogent Education, 12(1). https://doi.org/10.1080/2331186X.2025.2508216

Kurniasari, P., Mardikaningsih, A., & Sari, R. S. (2025). Dependensi Penggunaan Kecerdasan Buatan AI (Artificial Intelligence) Terhadap Tugas Akademik Mahasiswa. 4(3).

Latief, S. A., Muhsin, M. A., & Hasanah, N. I. (2024). Detection of AI Utilization in Language Learning: A Study on the Implementation of Chat Gpt In Academic Writing Among Indonesian Higher Education Students. 13(4), 1–10.

Maula, S. R., Aprillian, S. D., & Rachman, A. W. (2024). Ketergantungan Mahasiswa Universitas Jember Terhadap Artificial Intelligence (AI). 2(1).

Mehta, S., Info, A., Modeling, P., Graduation, S., Algorithm, N. B., & Data, E. (2023). Playing Smart with Numbers: Predicting Student Graduation Using the Magic of Naïve Bayes. 2(1), 60–75.

Mijwil, M. M., & Mijwil, M. M. (2024). A Comparative Analysis of Machine Learning Algorithms for Classification of Diabetes Utilizing Confusion Matrix Analysis. 21(5).

Mohi, Z. R. (2020). Orange Data Mining as a tool to compare Classification Algorithms. 3, 13–23.

Munggaran, J. P., Alhafidz, A. A., Taqy, M., Aprianti, D., Agustini, R., & Munawir, M. (2023). Sentiment Analysis of Twitter User Opinions Data Regarding the Use of ChatGPT in Education. Journal of Computer Engineering, Electronics and Information Technology (COELITE), 2(2), 75–88.

Nakhipova, V., Kerimbekov, Y., Umarova, Z., Suleimenova, L., & Botayeva, S. (2024). Use of the Naïve Bayes Classifier Algorithm in Machine Learning for Student Performance Prediction. 14(1). https://doi.org/10.18178/ijiet.2024.14.1.2028

Nhu, T., Nguyen, T., Lai, N. V., & Nguyen, Q. T. (2024). Artificial Intelligence (AI) in Education: A Case Study on ChatGPT’s Influence on Student Learning Behaviors. 0901(2), 105–121.

Purbayanto, B., & Suharsono, T. N. (n.d.). Analisis Sentimen Pengguna X terhadap ChatGPT dengan Algoritme Naïve Bayes. 18(2), 63–71.

Rajagukguk, N., Eka, I. P., & Kencana, N. (2024). Application of Term Frequency—Inverse Document Frequency in The Naïve Bayes Algorithm For ChatGPT User Sentiment Analysis. ICAMSAC 2023. https://doi.org/10.2991/978-94-6463-413-6

Ramadhani, T., Hermawan, P., & Dzikrillah, A. R. (2024). Penerapan Metode Naïve Bayes untuk Analisis Sentimen pada Ulasan Pengguna Aplikasi ChatGPT di Google Play Store. 6(1), 430–439. https://doi.org/10.47065/bits.v6i1.5400

Rifaldi, D., Famuji, T. S., Okta, B., Miranda, S., & Purma, F. (2025). Evaluasi Sentimen Pengguna ChatGPT Menggunakan Naïve Bayes: Tinjauan dari Confusion Matrix dan Classification Report. 3(2), 81–89.

Search, I. (2023). Penggunaan ChatGPT dalam Pembelajaran: Persepsi Mahasiswa. 22(1), 254–259.

Setiabudi, D. H., & Sampurno, A. R. (n.d.). Chatbot for Complex Questions in University Admission using Bidirectional Long-Short Term Memory and Convolutional Neural Network.

Sta, U., Id, B. Z., & Id, G. B. (2020). Discretisation of conditions in decision rules induced for continuous data. https://doi.org/10.1371/journal.pone.0231788

Tohir, F. A., Irawan, B., & Bahtiar, A. (2024). Analisis Sentimen Aplikasi ChatGPT Mobile Menggunakan Agoritma Naïve Bayes. 10(2), 179–192.

Trihapningsari, D., Widyasuri, A., Putri, M. A., & Fatihin, A. (2025). Sentiment Analysis of ChatGPT Exploration Based on Opinions on Platform X Using Naïve Bayes Algorithm. 4(July 2024), 94–101.

Xia, Y., Hou, C., Xu, Z., Sun, J., Space, G., & Place, P. C. (2015). Feature Reduction Using Ensemble Approach. 309–318.