@inproceedings{thapa-etal-2022-multi,
    title = "A Multi-Modal Dataset for Hate Speech Detection on Social Media: Case-study of Russia-{U}kraine Conflict",
    author = "Thapa, Surendrabikram  and
      Shah, Aditya  and
      Jafri, Farhan  and
      Naseem, Usman  and
      Razzak, Imran",
    editor = {H{\"u}rriyeto{\u{g}}lu, Ali  and
      Tanev, Hristo  and
      Zavarella, Vanni  and
      Y{\"o}r{\"u}k, Erdem},
    booktitle = "Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.case-1.1",
    doi = "10.18653/v1/2022.case-1.1",
    pages = "1--6",
    abstract = "This paper presents a new multi-modal dataset for identifying hateful content on social media, consisting of 5,680 text-image pairs collected from Twitter, labeled across two labels. Experimental analysis of the presented dataset has shown that understanding both modalities is essential for detecting these techniques. It is confirmed in our experiments with several state-of-the-art multi-modal models. In future work, we plan to extend the dataset in size. We further plan to develop new multi-modal models tailored explicitly to hate-speech detection, aiming for a deeper understanding of the text and image relation. It would also be interesting to perform experiments in a direction that explores what social entities the given hate speech tweet targets.",
}