Developing Successful Shared Tasks on Offensive Language Identification for Dravidian Languages

TL;DR

This paper introduces shared tasks for offensive language detection in under-resourced Dravidian languages, providing data, task definitions, and system evaluations to advance research in this area.

Contribution

It establishes evaluation frameworks and datasets for offensive language identification in Malayalam, Tamil, and Kannada, facilitating comparison of different approaches.

Findings

Multiple systems participated in the evaluation.

The datasets enabled benchmarking of offensive language detection.

The paper discusses various methods used by participants.

Abstract

With the fast growth of mobile computing and Web technologies, offensive language has become more prevalent on social networking platforms. Since offensive language identification in local languages is essential to moderate the social media content, in this paper we work with three Dravidian languages, namely Malayalam, Tamil, and Kannada, that are under-resourced. We present an evaluation task at FIRE 2020- HASOC-DravidianCodeMix and DravidianLangTech at EACL 2021, designed to provide a framework for comparing different approaches to this problem. This paper describes the data creation, defines the task, lists the participating systems, and discusses various methods.