@inproceedings{sathvik-etal-2024-ukrainian,
    title = "{U}krainian Resilience: A Dataset for Detection of Help-Seeking Signals Amidst the Chaos of War",
    author = "Sathvik, Msvpj  and
      Dowpati, Abhilash  and
      Sethi, Srreyansh",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.16/",
    doi = "10.18653/v1/2024.findings-emnlp.16",
    pages = "294--300",
    abstract = "We propose a novel dataset ``Ukrainian Resilience'' that brings together a collection of social media posts in the Ukrainian language for the detection of help-seeking posts in the Russia-Ukraine war. It is designed to help us analyze and categorize subtle signals in these posts that indicate people are asking for help during times of war. We are using advanced language processing and machine learning techniques to pick up on the nuances of language that show distress or urgency. The dataset is the binary classification of the social media posts that required help and did not require help in the war. The dataset could significantly improve humanitarian efforts, allowing for quicker and more targeted help for those facing the challenges of war. Moreover, the baseline models are implemented and GPT 3.5 achieved an accuracy of 81.15{\%}."
}