Hypers at ComMA@ICON: Modelling Aggressiveness, Gender Bias and Communal Bias Identification

TL;DR

This paper describes a system for classifying aggression, gender bias, and communal bias in social media sentences using pretrained models, achieving competitive rankings across multiple languages.

Contribution

It introduces a multilingual approach utilizing pretrained models with attention and pooling for bias and aggression detection in social media text.

Findings

Achieved top rankings in multiple language datasets

Utilized pretrained models with attention and mean pooling

Demonstrated effectiveness across diverse languages

Abstract

Due to the exponentially increasing reach of social media, it is essential to focus on its negative aspects as it can potentially divide society and incite people into violence. In this paper, we present our system description of work on the shared task ComMA@ICON, where we have to classify how aggressive the sentence is and if the sentence is gender-biased or communal biased. These three could be the primary reasons to cause significant problems in society. As team Hypers we have proposed an approach that utilizes different pretrained models with Attention and mean pooling methods. We were able to get Rank 3 with 0.223 Instance F1 score on Bengali, Rank 2 with 0.322 Instance F1 score on Multi-lingual set, Rank 4 with 0.129 Instance F1 score on Meitei and Rank 5 with 0.336 Instance F1 score on Hindi. The source code and the pretrained models of this work can be found here.