Work

Multimodal hate speech detection: a novel deep learning framework for multilingual text and images

Year: 2025

Type: article

Abstract: The rapid proliferation of social media platforms has facilitated the expression of opinions but also enabled the spread of hate speech. Detecting multimodal hate speech in low-resource multilingual contexts poses significant challenges. This study presents a deep learning framework that integrates bidirectional long short-term memory (BiLSTM) and EfficientNetB1 to classify hate speech in Urdu-English tweets, leveraging both text and image modalities. We introduce multimodal multilingual hate speech (MMHS11K), a manually annotated dataset comprising 11,000 multimodal tweets. Using an early fusion strategy, text and image features were combined for classification. Experimental results demonstrate that the BiLSTM+EfficientNetB1 model outperforms unimodal and baseline multimodal approaches, achieving an F1-score of 81.2% for Urdu tweets and 75.5% for English tweets. This research addresses critical gaps in multilingual and multimodal hate speech detection, offering a foundation for future advancements.

Source: PeerJ Computer Science

DOI: 10.7717/peerj-cs.2801

Authors: Furqan Khan Saddozai, Sahar K. Badri, Daniyal Alghazzawi, Asad Khattak, Muhammad Zubair Asghar

Institutions: Gomal University, King Abdulaziz University, Zayed University

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: gold

Estimated APC paid: $1,395