@inproceedings{ihtiyar-etal-2023-dataset,
    title = "A Dataset for Investigating the Impact of Context for Offensive Language Detection in Tweets",
    author = {{\.I}htiyar, Musa  and
      {\"O}zdemir, {\"O}mer  and
      Ereng{\"u}l, Mustafa  and
      {\"O}zg{\"u}r, Arzucan},
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-emnlp.103/",
    doi = "10.18653/v1/2023.findings-emnlp.103",
    pages = "1543--1549",
    abstract = "Offensive language detection is crucial in natural language processing (NLP). We investigated the importance of context for detecting such language in reply tweets on Twitter, where the use of offensive language is widespread. We collected a Turkish tweet dataset where the target group was unvaccinated people during the Covid period. Tweets in the dataset were enriched with contextual information by adding the original tweet to which a particular tweet was posted as a reply. The dataset, which includes over 28,000 tweet-reply pairs, was manually labeled by human annotators and made publicly available. In addition, we compared the performance of different machine learning models with and without contextual information. Our results show that this type of contextual information was not very useful in improving the performance of the models in general, although it slightly increased the macro-averaged F1-score of certain models."
}