@inproceedings{gurung-shakya-2025-team,
    title = "Team {M}eme{M}asters@{CASE} 2025: Adapting Vision-Language Models for Understanding Hate Speech in Multimodal Content",
    author = "Gurung, Shruti  and
      Shakya, Shubham",
    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-1.18/",
    pages = "146--151",
    abstract = "Social media memes have become a powerful form of digital communication, combining images and text to convey humor, social commentary, and sometimes harmful content. This paper presents a multimodal approach using a fine-tuned CLIP model to analyze textembedded images in the CASE 2025 Shared Task. We address four subtasks: Hate Speech Detection, Target Classification, Stance Detection, and Humor Detection. Our method effectively captures visual and textual signals, achieving strong performance with precision of 80{\%} for the detection of hate speech and 76{\%} for the detection of humor, while stance and target classification achieved a precision of 60{\%} and 54{\%}, respectively. Detailed evaluations with classification reports and confusion matrices highlight the ability of the model to handle complex multimodal signals in social media content, demonstrating the potential of vision-language models for computational social science applications."
}