This research focuses on misogyny detection in Dravidian languages using multimodal techniques. It leverages advanced machine learning models, including Vision Transformers (ViT) for image analysis and BERT-based transformers for text processing. The study highlights the challenges of working with regional datasets and addresses these with innovative preprocessing and model training strategies. The evaluation reveals significant improvements in detection accuracy, showcasing the potential of multimodal approaches in combating online abuse in underrepresented languages.

Social media has transformed communication, but it has opened new ways for women to be abused. Because of complex morphology, large vocabulary, and frequent code-mixing of Tamil and Malayalam, it might be especially challenging to identify discriminatory text in linguistically diverse settings. Because traditional moderation systems frequently miss these linguistic subtleties, gendered abuse in many forms—from outright threats to character insults and body shaming—continues. In addition to examining the sociocultural characteristics of this type of harassment on social media, this study compares the effectiveness of several Natural Language Processing (NLP) models, such as FastText, transformer-based architectures, and BiLSTM. Our results show that FastText achieved an macro f1 score of 0.74 on the Tamil dataset and 0.64 on the Malayalam dataset, outperforming the Transformer model which achieved a macro f1 score of 0.62 and BiLSTM achieved 0.57. By addressing the limitations of existing moderation techniques, this research underscores the urgent need for language-specific AI solutions to foster safer digital spaces for women.

Mental health analysis from social media text demands both high accuracy and interpretability for responsible healthcare applications. This paper explores Kolmogorov Arnold Networks (KANs) for mental health detection and classification, demonstrating their superior performance compared to Multi-Layer Perceptrons (MLPs) in accuracy while requiring fewer parameters. To further enhance interpretability, we leverage the Local Interpretable Model Agnostic Explanations (LIME) method to identify key features, resulting in a simplified KAN model. This allows us to derive governing equations for each class, providing a deeper understanding of the relationships between texts and mental health conditions.