Overview of Abusive Comment Detection in Tamil - ACL 2022

Abstract

The social media is one of the significant digital platforms that create a huge impact in peoples of all levels. The comments posted on social media is powerful enough to even change the political and business scenarios in very few hours. They also tend to attack a particular individual or a group of individuals. This shared task aims at detecting the abusive comments involving, Homophobia, Misandry, Counter-speech, Misogyny, Xenophobia, Transphobic. The hope speech is also identified. A dataset collected from social media tagged with the above said categories in Tamil and Tamil-English code-mixed languages are given to the participants. The participants used different machine learning and deep learning algorithms. This paper presents the overview of this task comprising the dataset details and results of the participants.