Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework

TL;DR

This paper introduces a new Bengali meme dataset with annotations for hate and inflammatory content, and proposes a co-attention based multimodal model that effectively detects such content, outperforming existing methods.

Contribution

It presents the first Bengali meme dataset distinguishing inflammatory content from hate speech and introduces a novel co-attention fusion model for improved detection.

Findings

MCFM outperforms state-of-the-art models on Bn-HIB dataset.

First dataset to differentiate inflammatory content from hate speech in Bengali memes.

Effective multimodal approach for nuanced hate and inflammatory content detection.

Abstract

Internet memes have become a dominant form of expression on social media, including within the Bengali-speaking community. While often humorous, memes can also be exploited to spread offensive, harmful, and inflammatory content targeting individuals and groups. Detecting this type of content is excep- tionally challenging due to its satirical, subtle, and culturally specific nature. This problem is magnified for low-resource lan- guages like Bengali, as existing research predominantly focuses on high-resource languages. To address this critical research gap, we introduce Bn-HIB (Bangla Hate Inflammatory Benign), a novel dataset containing 3,247 manually annotated Bengali memes categorized as Benign, Hate, or Inflammatory. Significantly, Bn- HIB is the first dataset to distinguish inflammatory content from direct hate speech in Bengali memes. Furthermore, we propose the MCFM (Multi-Modal Co-Attention Fusion Model), a simple yet effective architecture that mutually analyzes both the visual and textual elements of a meme. MCFM employs a co-attention mechanism to identify and fuse the most critical features from each modality, leading to a more accurate classification. Our experiments show that MCFM significantly outperforms several state-of-the-art models on the Bn-HIB dataset, demonstrating its effectiveness in this nuanced task.Warning: This work contains material that may be disturbing to some audience members. Viewer discretion is advised.