Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations

TL;DR

This paper introduces MultiBully-Ex, a benchmark dataset for multimodal explanations of cyberbullying memes, and proposes a CLIP-based model that improves interpretability and detection accuracy of offensive memes.

Contribution

It presents the first benchmark dataset for multimodal explanation of cyberbullying memes and a novel CLIP-based approach that enhances explainability and detection performance.

Findings

Training with multimodal explanations improves textual justification quality.

The proposed model more accurately identifies visual evidence supporting cyberbullying.

Experimental results show performance improvements in detection and explanation tasks.

Abstract

Internet memes have gained significant influence in communicating political, psychological, and sociocultural ideas. While memes are often humorous, there has been a rise in the use of memes for trolling and cyberbullying. Although a wide variety of effective deep learning-based models have been developed for detecting offensive multimodal memes, only a few works have been done on explainability aspect. Recent laws like "right to explanations" of General Data Protection Regulation, have spurred research in developing interpretable models rather than only focusing on performance. Motivated by this, we introduce {\em MultiBully-Ex}, the first benchmark dataset for multimodal explanation from code-mixed cyberbullying memes. Here, both visual and textual modalities are highlighted to explain why a given meme is cyberbullying. A Contrastive Language-Image Pretraining (CLIP) projection-based multimodal shared-private multitask approach has been proposed for visual and textual explanation of a meme. Experimental results demonstrate that training with multimodal explanations improves performance in generating textual justifications and more accurately identifying the visual evidence supporting a decision with reliable performance improvements.