MMFFHS: Multi-Modal Feature Fusion for Hate Speech Detection on Social Media

Millions of people use social media platforms such as Facebook, YouTube, and Twitter to stay updated on news, enjoy entertainment, and share personal moments with peers. These platforms have now become medium channels for spreading rumors, posting hate speech, cyberbullying, etc. Hate speech frequently appears on social media platforms nowadays. Sometimes, it impairs readers’ mental and emotional health and societal order. Therefore, timely detection is required to prevent the spread of hate speech posts on social media platforms. The researchers have reported some research works on textual hate speech detection. However, social media posts are not limited to text; images and text with images are also used in the posts, termed multimodal data. The text-based model may not be efficient enough to handle the multimodal data. Therefore, this study introduces a reliable architecture that utilizes deep and transfer learning frameworks to classify multimodal social media posts into hate and non-hate. The proposed model is compatible with text, images, and images with text-based social posts to categorize hate and non-hate. The proposed framework MMFFHS, a feature-fusion-based model, performed better than the existing models by achieving 70.26% accuracy.