Detecting homophobic and transphobic texts from youtube comments using machine learning models

Abstract

Today's world has witnessed an exponential rise in disseminating degrading and offensive content via social media. A global increase in violence against minorities, such as gun violence, murders, and forced displacement, has been connected to using harsh and derogatory language online. The policies enacted to prevent abusive or derogatory language risk stifling free speech and are applied differently. These languages can affect the mental state of social media users. Homophobic and transphobic expressions are a insulting people's sexuality or character among harsh and disrespectful remarks. To study social media information and discriminate between homophobic and transphobic comments, it is necessary to construct language-based automatic categorization methods. This dataset consists of Tamil YouTube comments collected as part of the Shared Task on Sentiment Analysis and Homophobia detection of YouTube comments in Code-Mixed Dravidian Languages. This study detects and categorises abusive comments using machine learning models such as SVM, Naive Bayes, Logistic regression, and KNN. In comparison to other classifiers, the accuracy of logistic regression is the highest, at 55%.