Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Rakib Ullah, Mominul islam, Md Sanjid Hossain, Md Ismail Hossain

TL;DR

This work introduces Bn-HIB (Bangla Hate Inflammatory Benign), a novel dataset containing 3,247 manually annotated Bengali memes categorized as Benign, Hate, or Inflammatory, and proposes 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.

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.

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

TL;DR

This work introduces Bn-HIB (Bangla Hate Inflammatory Benign), a novel dataset containing 3,247 manually annotated Bengali memes categorized as Benign, Hate, or Inflammatory, and proposes 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.

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.
Paper Structure (10 sections, 2 equations, 7 figures, 5 tables)

This paper contains 10 sections, 2 equations, 7 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset
  4. Methods
  5. Models And Fusion Strategies
  6. Experimental Details
  7. Evaluation Metrics
  8. Results
  9. Error Analysis
  10. Conclusion

Figures (7)

  • Figure 1: Meme (a) portrays Hindus as hypocrites for allegedly destroying their own temples and blaming Muslims, while Meme (b) specifically targets an organization and individual, making it more directed but less representative of the broader Hindu population.
  • Figure 2: Data Collection and Pre-Processing Overview
  • Figure 3: Proposed Multi-Modal Co-Attention Fusion Model (MCFM)
  • Figure 4: Annotation Decision Tree
  • Figure 5: Class-Wise Performance Of Top Models
  • ...and 2 more figures