Easy Data Augmentation in Sentiment Analysis of Cyberbullying
This work addresses cyberbullying filtering for young Indonesians on social media, but it is incremental as it builds on existing methods with a small performance gain.
The paper tackled cyberbullying detection on Instagram comments using sentiment analysis with SVM and Easy Data Augmentation (EDA), resulting in a 2.52% increase in k-Fold Cross Validation score and 92.5% accuracy, which is 2.5% higher than the existing state-of-the-art.
Instagram, a social media platform, has in the vicinity of 2 billion active users in 2023. The platform allows users to post photos and videos with one another. However, cyberbullying remains a significant problem for about 50% of young Indonesians. To address this issue, sentiment analysis for comment filtering uses a Support Vector Machine (SVM) and Easy Data Augmentation (EDA). EDA will augment the dataset, enabling robust prediction and analysis of cyberbullying by introducing more variation. Based on the tests, SVM combination with EDA results in a 2.52% increase in the k-Fold Cross Validation score. Our proposed approach shows an improved accuracy of 92.5%, 2.5% higher than that of the existing state-of-the-art method. To maintain the reproducibility and replicability of this research, the source code can be accessed at uns.id/eda_svm.