Analisis Sentimen Ulasan Pengguna Generative AI Menggunakan Naïve Bayes Berbasis Python
DOI:
https://doi.org/10.55123/insologi.v5i3.8050Keywords:
Sentiment Analysis, Generative AI, Naïve Bayes, TF-IDF, Text MiningAbstract
The advancement of Generative Artificial Intelligence (Generative AI) technology has driven increased use of AI-based applications across various sectors, including education, productivity, digital services, and information retrieval. The high intensity of usage generates massive volumes of user reviews on digital platforms, containing valuable information regarding user satisfaction, experience, and perception of system service quality. This study aims to analyze the sentiment of user reviews toward Generative AI applications using a Python-based Naïve Bayes algorithm. The dataset consists of 50,000 user reviews covering five Generative AI applications: ChatGPT, Microsoft Copilot, Google Gemini, Perplexity, and Claude. The research pipeline includes text preprocessing stages of case folding, cleaning, tokenizing, stopword removal, and feature transformation using TF-IDF with unigram and bigram representations. Data are then classified into three sentiment categories (positive, negative, neutral) using three variants of the Naïve Bayes algorithm: Multinomial, Complement, and Bernoulli. Results show a sentiment distribution of 33,695 positive (67.4%), 13,275 negative (26.6%), and 3,030 neutral (6.1%) reviews. Multinomial Naïve Bayes achieved the best performance with an accuracy of 83.07%, precision 77.79%, recall 83.07%, and F1-score 80.29%. Five-fold cross-validation confirmed stable performance with a mean accuracy of 82.31% and a standard deviation of 0.23%.
Downloads
References
Afuan, L., Khanza, M., & Hasyati, A. Z. (2025). Enhancing Sentiment Analysis of the 2024 Indonesian Presidential Inauguration on X Using SMOTE-Optimized Naive Bayes Classifier. JUTIF, 6(1). https://doi.org/10.52436/1.jutif.2025.6.1.4290
Agustin, Y. H., Mulyani, N. C., & Prasetya, W. S. (2025). Analisis Sentimen Opini Publik Menggunakan Algoritma Naive Bayes dan TF-IDF. Jurnal Algoritma, 22(2), 1373–1384. https://doi.org/10.33364/algoritma/v.22-2.2671
Ardi, A., & Kurniawan. (2024). Optimization of Naive Bayes Classifier Method Using TF-IDF Approach for Sentiment Analysis. Journal Scientific and Applied Informatics, 7(3).
Bachtiar, A., Hawali, M. J., Simbolon, N. C., Maulana, D. A., & Anggraini, R. A. (2026). Analisis Sentimen Ulasan Free Fire Menggunakan Naive Bayes Logistic Regression. JOISM, 7(2). https://doi.org/10.24076/joism.2026v7i2.2433
Brawijaya, W., Umam, K., Nur, S., & Handayani, M. R. (2025). Sentiment Analysis on WeTV Application Reviews Using Naïve Bayes : A Study of Preprocessing , Balancing , and Model Performance. JUSIFO, 11(1), 43–52.
Dewi, R., & Santoso, B. (2022). Kombinasi N-Gram dan TF-IDF untuk Peningkatan Akurasi Analisis Sentimen pada Twitter. JTIIK, 9(3), 581–590.
Gerliandeva, A., Chrisnanto, Y. H., & Ashaury, H. (2024). Optimasi Klasifikasi Sentimen pada Komentar Online menggunakan Multinomial Naïve Bayes dan Ekstraksi Fitur TF-IDF serta N-grams Optimization of Sentiment Classification on Online Comments using Multinomial Naïve Bayes and TF-IDF Feature Extraction and N-g. Pekommas, 9(X), 259–272. https://doi.org/10.56873/jpkm.v9i2.5585
Imelda, I., & Kurnianto, A. R. (2026). Naïve Bayes and TF-IDF for Sentiment Analysis of the Covid-19 Booster Vaccine. Jurnal RESTI, 5(158), 1–2.
Juliana, N. K. A., & Raharja, M. A. (2024). Analisis Sentimen pada Ulasan Aplikasi myIM3 Menggunakan Multinomial Naive Bayes dengan TF-IDF. Jurnal Nasional Teknologi Informasi Dan Aplikasinya, 2(3), 649–656. https://doi.org/10.24843/JNATIA.2024.v02.i03.p25
Kachhia, J. (2026). The Generative AI Ecosystem – 50k User Reviews 2026. Kaggle. https://www.kaggle.com/datasets/jahnavikachhia23/the-generative-ai-ecosystem-50k-user-reviews-2026
Khinsa Fairuz Zahirah, Benny Irawan, E. Y. (2025). PREPARING AI SUPER USERS THROUGH GENERATIVE AI INTEGRATION IN EDUCATION. Jurnal Ilmu Pengetahuan, 5(2), 559–570. https://jurnalp4i.com/index.php/cendekia
Khoerunnisa, S., Shiddiq, D. F., & Nurhayati, D. (2025). Application of the Naive Bayes Algorithm with TF-IDF and Cross Validation Techniques for Sentiment Analysis Towards Starlink Penerapan Algoritma Naive Bayes dengan Teknik TF-IDF dan Cross Validation untuk Analisis Sentimen Terhadap Starlink. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(April), 566–577.
Lestari, V. B., & Hutagalung, C. A. (2025). Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis. J-KOMA, 8(1), 36–44.
Madjid, M. F., Ratnawati, D. E., & Rahayudi, B. (2023). Sentiment Analysis on App Reviews Using Support Vector Machine and Naïve Bayes Classification. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 7(1), 556–562. https://doi.org/https://doi.org/10.33395/sinkron.v8i1.12161 e-ISSN
Muzaki, M., Kurniawan, R., Ali, I., & Anwar, S. (2026). ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI CHATGPT MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DAN NAIVE BAYES BERBASIS PYTHON. JATI (Jurnal Mahasiswa Teknik Informatika), 10(2), 3087–3094.
Nasution, Y. R., Suhardi, S., & Satrio, I. H. (2024). Penerapan Algoritma Klasifikasi Naïve Bayes Untuk Analisis Sentimen Tentang Pemilu 2024. ELKOM, 17(2), 495–502. https://doi.org/10.51903/elkom.v17i2.2053
Nugroho, A., Stiawan, D., & Heryadi, Y. (2022). Perbandingan Multinomial dan Complement Naive Bayes untuk Klasifikasi Sentimen Ulasan Aplikasi Perbankan Digital. Jurnal Sistem Informasi, 14(2), 74–84.
Nurfauzi, O. M., Hilabi, S. S., Nurapriani, F., & Huda, B. (2025). Analisis Sentimen Grab Indonesia pada Ulasan Google Play Store menggunakan Algoritma Naive Bayes dan Support Vector Machine. SMARTICS Journal, 11(1), 8–13.
Purnomo, A., Kusumadewi, S., & Al Fatta, H. (2022). Validasi Model Naive Bayes Menggunakan K-Fold Cross Validation pada Analisis Sentimen Ulasan E-Learning. IJCIT, 7(1), 53–61.
Saputra, R. (2025). Generative AI Image Sentiment Analysis on Social Media X using TF-IDF and FastText. JAIC.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rizky Nurhasanah, Victor Asido Elyakim
This work is licensed under a Creative Commons Attribution 4.0 International License.
Hak cipta pada setiap artikel adalah milik penulis.
Penulis mengakui bahwa INSOLOGI (Jurnal Sains dan Teknologi) sebagai publisher yang mempublikasikan pertama kali dengan lisensi Creative Commons Attribution 4.0 International License.
Penulis dapat memasukan tulisan secara terpisah, mengatur distribusi non-ekskulif dari naskah yang telah terbit di jurnal ini kedalam versi yang lain, seperti: dikirim ke respository institusi penulis, publikasi kedalam buku, dan lain-lain. Dengan mengakui bahwa naskah telah terbit pertama kali pada INSOLOGI (Jurnal Sains dan Teknologi).
