Towards Interpretable Multilingual Detection of Hate Speech against Immigrants and Women in Twitter at SemEval-2019 Task 5
This work provides an incremental improvement in hate speech detection for social media platforms, specifically targeting immigrants and women in English and Spanish, which is relevant for content moderation and online safety.
This paper addresses the detection of hate speech against women and immigrants on Twitter in English and Spanish. Their proposed models achieved F1 scores of 57 (English) and 75 (Spanish) for Task A, and 67 (English) and 75.33 (Spanish) for Task B, showing improvements of 2, 10, and 5 points in specific tasks.
his paper describes our techniques to detect hate speech against women and immigrants on Twitter in multilingual contexts, particularly in English and Spanish. The challenge was designed by SemEval-2019 Task 5, where the participants need to design algorithms to detect hate speech in English and Spanish language with a given target (e.g., women or immigrants). Here, we have developed two deep neural networks (Bidirectional Gated Recurrent Unit (GRU), Character-level Convolutional Neural Network (CNN)), and one machine learning model by exploiting the linguistic features. Our proposed model obtained 57 and 75 F1 scores for Task A in English and Spanish language respectively. For Task B, the F1 scores are 67 for English and 75.33 for Spanish. In the case of task A (Spanish) and task B (both English and Spanish), the F1 scores are improved by 2, 10, and 5 points respectively. Besides, we present visually interpretable models that can address the generalizability issues of the custom-designed machine learning architecture by investigating the annotated dataset.