Sentiment Analysis of Teacher Bullying Discourse in Indonesia Using Naive Bayes, Support Vector Machines, and Random Forest
Keywords:
Sentiment Analysis, X Platform, Teacher Bullying, Naive Bayes, Support Vector Machine, Random Forest, Machine LearningAbstract
Bullying against teachers on social media has become an increasingly discussed issue, particularly on the X platform. This study aims to analyze public sentiment toward teacher bullying in Indonesia using a machine learning approach. Three classification methods are employed, namely Naive Bayes, Support Vector Machine (SVM), and Random Forest. The dataset consists of 3,351 tweets after preprocessing. Sentiment labels (positive, negative, and neutral) are assigned using a rule based approach, relying on a predefined keyword list. Feature extraction is conducted using TF-IDF, and classification performance is evaluated using accuracy, precision, recall, and F1-score metrics. The experimental results show that Naive Bayes achieves an accuracy of 71.83 percent, Support Vector Machine 86.89 percent, and Random Forest 87.48 percent. Based on these findings, Random Forest demonstrates the best performance for classifying sentiment on the issue of teacher bullying on X
References
[1] N. A. Susanti and M. Walid, “Klasifikasi Data Tweet Ujaran Kebencian Di Media Sosial,” vol. 6, no. 2, pp. 538–543, 2022.
[2] A. Andryawan, C. Laurencia, and M. P. T. Putri, “Peran Guru dalam Mencegah dan Mengatasi Terjadinya Perundungan (Bullying) di Lingkungan Sekolah,” Innov. J. Soc. Sci. Res., vol. 3, no. 6, pp. 2837–2850, 2023.
[3] M. F. Rizki, K. Auliasari, and R. Primaswara Prasetya, “Analisis Sentiment Cyberbullying Pada Sosial Media Twitter Menggunakan Metode Support Vector Machine,” JATI (Jurnal Mhs. Tek. Inform., vol. 5, no. 2, pp. 548–556, 2021, doi: 10.36040/jati.v5i2.3808.
[4] S. Adi et al., “ANALISIS SENTIMEN APLIKASI HALO BCA DI GOOGLE PLAY STORE MENGGUNAKAN METODE NAIVE BAYES , SUPPORT VECTOR MACHINE DAN RANDOM FOREST PENDAHULUAN,” vol. 15, no. c, pp. 69–79, 2024.
[5] M. Fachriza and M. Munawar, “Analisis Sentimen Kalimat Depresi Pada Pengguna Twitter Dengan Naive Bayes, Support Vector Machine, Random Forest,” Komputek, vol. 7, no. 2, pp. 49–58, 2023, doi: 10.24269/jkt.v7i2.2218.
[6] A. Zamsuri and Wileks, “Sentiment analysis of Saudi e-commerce using naïve bayes algorithm and support vector machine,” Int. J. Data Netw. Sci., vol. 8, no. 3, pp. 1607–1612, 2024, doi: 10.5267/j.ijdns.2024.3.006.
[7] A. Susanto, I. Agung Dzulkarnain, P. Studi Statistika, and F. Matematika Dan Ilmu Pengetahuan Alam, “Analisis Sentimen Data Twitter Topik Ekonomi Dan Industri Dengan Metode Naive Bayes Dan Random Forest,” J. Ilm. Wahana Pendidikan, Oktober, vol. 2023, no. 20, pp. 59–65, 2023, [Online]. Available: https://doi.org/10.5281/zenodo.8398895
[8] N. Raisa and N. Riza, “Sentimen Analisis Terhadap Opini Masyarakat Mengenai Drama Korea Pada Twitter Menggunakan Metode Naïve Bayes,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 2, pp. 1312–1320, 2023, doi: 10.36040/jati.v7i2.6765.
[9] T. T. Widowati and M. Sadikin, “Analisis Sentimen Twitter terhadap Tokoh Publik dengan Algoritma Naive Bayes dan Support Vector Machine,” Simetris J. Tek. Mesin, Elektro dan Ilmu Komput., vol. 11, no. 2, pp. 626–636, 2021, doi: 10.24176/simet.v11i2.4568.
[10] N. Sidauruk, N. Riza, and R. N. Siti Fatonah, “Penggunaan Metode Svm Dan Random Forest Untuk Analisis Sentimen Ulasan Pengguna Terhadap Kai Access Di Google Playstore,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 3, pp. 1901–1906, 2023, doi: 10.36040/jati.v7i3.6899.
