Analisis Sentimen Publik Terkait Kekerasan Seksual di Indonesia dengan Algoritma Naïve Bayes dan SVM

Semakin meningkatnya kasus kekerasan seksual yang terjadi di Indonesia, dan media sosial merupakan ruang bagi masyarakat Indonesia untuk mengekspresikan pendapat. The increasing number of sexual violence cases in Indonesia, along with the role of social media as a space for the public to express their opinions, forms the basis for this research. The study aims to classify various types of public sentiment expressed on X (formerly Twitter) and Instagram comments by applying two algorithms for comparison: Naïve Bayes and SVM. Several processes carried out, including data collection from social media, data preprocessing, manual labeling, and the implementation of both algorithms on the processed dataset. The data sources utilized are posts written in Indonesian on X (Twitter) and Instagram, focusing on issues of sexual violence in Indonesia. The sentiment analysis results were grouped into three main categories: positive, negative, and neutral. The outcomes show that SVM achieved an accuracy of 82.17% using an 80:20 data split without applying GridSearch for optimization. The SVM results outperformed those of Naïve Bayes, which achieved an accuracy of 78.92%. This investigation leads to the conclusion that SVM is more optimal in analyzing public sentiment related to sexual violence in Indonesia compared to Naïve Bayes. The sentiment analysis results from social media regarding sexual violence in Indonesia show that the majority of sentiments are neutral, with the dataset being dominated by informative content, case reports without emotional expression, and off-topic comments