Optimizing Hate Speech Detection in Indonesian Social Media: An ADASYN and LSTM-Based Approach

Abstract

Identifying hate speech in Indonesian social media presents considerable difficulties owing to the intricacies of the language and the varied nature of online material. This paper presents a novel method for improving hate speech identification in Indonesia by tackling the significant class imbalance in Indonesian hate speech datasets. The ADASYN oversampling technique proficiently addresses this problem, representing a notable advancement in this study. The FastText method is utilized for word weighting, improving the prediction efficacy of the classification model. The dataset is carefully curated to authentically reflect the language characteristics and cultural circumstances of Indonesian social media conversation. The long short-term memory (LSTM) method is chosen for its capacity to record long-range relationships in sequential data, essential for comprehending the context of hate speech. The assessment of performance using criteria like accuracy, precision, recall, and F1-Score illustrates the efficacy of this method in precisely detecting hate speech. This research markedly enhances hate speech identification technology in Indonesian language processing, offering a viable method to curtail the dissemination of harmful information on internet platforms. The results of this study include practical implications for formulating more effective tactics to combat hate speech on Indonesian social media.