Public sentiment analysis on facebook towards information security using the albert model with data augmentation
Keywords:
Sentiment Analysis, ALBERT, Data Augmentation, Back Translation, Information Security, NLPAbstract
Information security has become a strategic issue in the digital era, particularly with the increasing risks of data breaches and privacy threats on social media platforms. This study aims to analyze public sentiment on Facebook comments related to information security by leveraging ALBERT (A Lite BERT) combined with Back Translation data augmentation to overcome class imbalance. The dataset consists of 1,000 comments categorized into negative, neutral, and positive sentiments, processed through text pre-processing, augmentation, and classification stages. The experimental setup employed a stratified data split of 80% training, 10% validation, and 10% testing to ensure balanced class distribution. Evaluation using accuracy, precision, recall, and F1-score demonstrates that the proposed model achieves 81% accuracy with a macro F1-score of 0.80, where the neutral class shows the most stable performance. The findings indicate that ALBERT with data augmentation effectively improves sentiment classification performance. This research contributes to the development of adaptive sentiment analysis systems to support policymakers in formulating strategies related to digital information security.
References
Aldean, P., et al. (2021). Analisis sentimen masyarakat terhadap vaksinasi Covid-19 di Twitter menggunakan metode random forest classifier (studi kasus: vaksin Sinovac). Dalam Prosiding Seminar Nasional Teknologi dan Rekayasa. Surabaya, Indonesia.
We Are Social, & Kepios. (2023). Digital 2023: Indonesia. We Are Social.
Badan Litbang dan Diklat Kementerian Agama RI. (2019). Al-Qur’an dan terjemahannya. Kementerian Agama RI.
Putranta, Y. S. V., Rachmad, B., & Prasetyo, W. (2023). Analisis sentimen masyarakat terhadap kebijakan penghapusan subsidi BBM pada media sosial Twitter menggunakan algoritma naïve Bayes classifier dengan ekstraksi fitur n-gram TF-IDF. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer (J-PTIIK).
Syahriani, I., Yusuf, A. A., & Yulianto, T. S. (2010). Sentiment analysis of Facebook comments on Indonesian presidential candidates using naïve Bayes with feature selection. Dalam Journal of Physics: Conference Series.
Lan, Z., et al. (2020). ALBERT: A lite BERT for self-supervised learning of language representations. Dalam Proceedings of the International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia.
Kharisudin, I., & Putra, M. I. (2022). Analisis sentimen pengguna aplikasi marketplace Tokopedia pada situs Google Play menggunakan metode support vector machine (SVM), naïve Bayes, dan logistic regression. Dalam PRISMA (Prosiding Ilmiah Mahasiswa) Universitas Negeri Semarang.
Julianto, M. R., & Wibowo, Y. A. T. (2024). Analisis sentimen respon publik terhadap program internet gratis di platform X melalui pendekatan algoritma naïve Bayes. Jurnal Indonesia: Manajemen Informatika dan Komunikasi (JIMIK), 5(3).
Witanti, A., & Dian, H. (2022). Analisis sentimen masyarakat terhadap vaksinasi COVID-19 pada media sosial Twitter menggunakan algoritma support vector machine (SVM). Jurnal Sistem Informasi dan Informatika (Simika), 5(1).
Maulidiana, D. R., Hidayat, M. F., & Ramadhan, D. G. P. D. (2024). Comparative analysis of SVM and NB algorithms in evaluating public sentiment on Supreme Court rulings. Jurnal Sisfokom, 13(2).
Widyadhana, F. K., Sari, N. Y., & Rachmad, B. (2023). Sentiment analysis pada opini masyarakat terhadap pelayanan publik Polres Ponorogo menggunakan metode support vector machine. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer (J-PTIIIK), 7(7).
Liu, B. (2012). Sentiment analysis and opinion mining. Morgan & Claypool Publishers.
Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1113. https://doi.org/10.1016/j.asej.2014.04.011
Hadikristanto, W., & Tri, A. (2023). Implementasi algoritma naïve Bayes dan support vector machine tentang pembobolan dan kebocoran data di Twitter. BIT Jurnal: Jurnal Teknologi Informasi, 5(2).
