@inproceedings{metin-etal-2026-sarcasturk,
    title = {{S}arcas{T}{\"u}rk: {T}urkish Context-Aware Sarcasm Detection Dataset},
    author = {Metin, Niyazi Ahmet  and
      Y{\i}lmaz, Sevde  and
      Erdo{\u{g}}du, Osman Enes  and
      Meydan, Elif Sude  and
      S{\"u}mer, O{\u{g}}ul  and
      Kek{\"u}ll{\"u}o{\u{g}}lu, Dilara},
    editor = {Oflazer, Kemal  and
      K{\"o}ksal, Abdullatif  and
      Varol, Onur},
    booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.sigturk-1.6/",
    pages = "61--71",
    ISBN = "979-8-89176-370-8",
    abstract = {Sarcasm is a colloquial form of language that is used to convey messages in a non-literal way, which affects the performance of many NLP tasks. Sarcasm detection is not trivial and existing work mainly focus on only English. We present SarcasT{\"u}rk, a context-aware Turkish sarcasm detection dataset built from Ek{\c{s}}i S{\"o}zl{\"u}k entries, a large-scale Turkish online discussion platform where people frequently use sarcasm. SarcasT{\"u}rk contains 1,515 entries from 98 titles with binary sarcasm labels and a title-level context field created to support comparisons between entry-only and context-aware models. We generate these contexts by selecting representative sentences from all entries under a title using summarization techniques. We report baseline results for a fine-tuned BERTurk classifier and zero-shot LLMs under both no-context and context-aware conditions. We find that BERTurk model with title-level context has the best performance with 0.76 accuracy and balanced class-wise F1 scores (0.77 for sarcasm, 0.75 for no sarcasm). SarcasT{\"u}rk can be shared upon contacting the authors since the dataset contains potentially sensitive and offensive language.}
}