TeamX@DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification

TL;DR

This paper compares methods for classifying troll-based memes using text, images, and multimodal data, highlighting the impact of code-mixed text and additional datasets on classification performance.

Contribution

It provides a comprehensive comparative analysis of different modalities for troll-based meme classification, including insights on multimodal and code-mixed text handling.

Findings

Multimodal models outperform unimodal baselines.

Code-mixed text presents unique challenges and opportunities.

Adding external datasets improves classification accuracy.

Abstract

The spread of fake news, propaganda, misinformation, disinformation, and harmful content online raised concerns among social media platforms, government agencies, policymakers, and society as a whole. This is because such harmful or abusive content leads to several consequences to people such as physical, emotional, relational, and financial. Among different harmful content \textit{trolling-based} online content is one of them, where the idea is to post a message that is provocative, offensive, or menacing with an intent to mislead the audience. The content can be textual, visual, a combination of both, or a meme. In this study, we provide a comparative analysis of troll-based memes classification using the textual, visual, and multimodal content. We report several interesting findings in terms of code-mixed text, multimodal setting, and combining an additional dataset, which shows improvements over the majority baseline.