Tackling Faceless Killers: Toxic Comment Detection to Maintain a Healthy Internet Environment

Abstract

According to BBC News, online hate speech increased by 20% during the COVID-19 pandemic. Hate speech from anonymous users can result in psychological harm, including depression and trauma, and can even lead to suicide. Malicious online comments are increasingly becoming a social and cultural problem. It is therefore critical to detect such comments at the national level and detect malicious users at the corporate level. To achieve a healthy and safe Internet environment, studies should focus on institutional and technical topics. The detection of toxic comments can create a safe online environment. In this study, to detect malicious comments, we used approximately 9,400 examples of hate speech from a Korean corpus of entertainment news comments. We developed toxic comment classification models using supervised learning algorithms, including decision trees, random forest, a support vector machine, and K-nearest neighbors. The proposed model uses random forests to classify toxic words, achieving an F1-score of 0.94. We analyzed the trained model using the permutation feature importance, which is an explanatory machine learning method. Our experimental results confirmed that the toxic comment classifier properly classified hate words used in Korea. Using this research methodology, the proposed method can create a healthy Internet environment by detecting malicious comments written in Korean.