@article{coltekin-gunes-2026-corpus,
    title = "A Corpus of Misunderstood Irony on {T}urkish Social Media",
    author = {{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}  and
      G{\"u}ne{\c{s}}, G{\"u}liz},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.879/",
    pages = "11252--11259",
    abstract = "We present a new Turkish social media corpus annotated for verbal irony. The ironic post candidates are identified by a distant supervision method relying on reports of misunderstood irony in social media platforms. The data collected through this method, as well as irony-tagged posts and a random sample of posts are annotated by three annotators, resulting in a corpus of 3000 tweets with high quality annotations that may be useful for linguistic analysis as well as for training automatic irony detection systems or testing irony understanding of large language models. Since irony interpretation typically involves context, our dataset also includes the preceding conversational context of the potentially ironic expression. Besides the description of the corpus and the annotation process, this paper presents an analysis of the corpus. Our findings indicate that relying on distant supervision alone may result in suboptimal labels for irony/sarcasm corpora. We also investigate the usefulness of context for the annotators in identifying irony."
}