@inproceedings{teng-ohman-2025-using,
    title = "Using Multimodal Models for Informative Classification of Ambiguous Tweets in Crisis Response",
    author = {Teng, Sumiko  and
      {\"O}hman, Emily},
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-06/2025.nlp4dh-1.23/",
    doi = "10.18653/v1/2025.nlp4dh-1.23",
    pages = "265--271",
    ISBN = "979-8-89176-234-3",
    abstract = "Social media platforms like X provide real-time information during crises but often include noisy, ambiguous data, complicating analysis. This study examines the effectiveness of multimodal models, particularly a cross-attention-based approach, in classifying tweets about the California wildfires as ``informative'' or ``uninformative,'' leveraging both text and image modalities. Using a dataset containing both ambiguous and unambiguous tweets, models were evaluated for their ability to handle real-world noisy data. Results show that the multimodal model outperforms unimodal counterparts, especially for ambiguous tweets, demonstrating its resilience and ability to integrate complementary modalities. These findings highlight the potential of multimodal approaches to enhance humanitarian response efforts by reducing information overload."
}