@inproceedings{verma-kumar-2025-multimodal,
    title = "Multimodal Deep Learning for Detection of Hate, Humor, and Stance in Social Discourse on Marginalized Communities",
    author = "Verma, Durgesh  and
      Kumar, Abhinav",
    editor = {H{\"u}rriyeto{\u{g}}lu, Ali  and
      Tanev, Hristo  and
      Thapa, Surendrabikram},
    booktitle = "Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/corrections-2026-01/2025.case-1.12/",
    pages = "98--106",
    abstract = "Internet memes serve as powerful vehicles of expression across platforms like Instagram, Twitter, and WhatsApp. However, they often carry implicit messages such as humor, sarcasm, or offense especially in the context of marginalized communities. Understanding such intent is crucial for effective moderation and content filtering. This paper introduces a deep learning-based multimodal framework developed for the CASE 2025 Shared Task on detecting hate, humor, and stance in memes related to marginalized movements. The study explores three architectures combining textual models (BERT, XLM-RoBERTa) with visual encoders (ViT, CLIP), enhanced through cross-modal attention and Transformer-based fusion. Evaluated on four subtasks, the models effectively classify meme content{---}such as satire and offense{---}demonstrating the value of attention-driven multimodal integration in interpreting nuanced social media expressions"
}