@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://aclanthology.org/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.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="metin-etal-2026-sarcasturk">
<titleInfo>
<title>SarcasTürk: Turkish Context-Aware Sarcasm Detection Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niyazi</namePart>
<namePart type="given">Ahmet</namePart>
<namePart type="family">Metin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sevde</namePart>
<namePart type="family">Yılmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="given">Enes</namePart>
<namePart type="family">Erdoğdu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elif</namePart>
<namePart type="given">Sude</namePart>
<namePart type="family">Meydan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oğul</namePart>
<namePart type="family">Sümer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilara</namePart>
<namePart type="family">Keküllüoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Oflazer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Varol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-370-8</identifier>
</relatedItem>
<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 SarcasTürk, a context-aware Turkish sarcasm detection dataset built from Ekşi Sözlük entries, a large-scale Turkish online discussion platform where people frequently use sarcasm. SarcasTürk 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). SarcasTürk can be shared upon contacting the authors since the dataset contains potentially sensitive and offensive language.</abstract>
<identifier type="citekey">metin-etal-2026-sarcasturk</identifier>
<location>
<url>https://aclanthology.org/2026.sigturk-1.6/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>61</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SarcasTürk: Turkish Context-Aware Sarcasm Detection Dataset
%A Metin, Niyazi Ahmet
%A Yılmaz, Sevde
%A Erdoğdu, Osman Enes
%A Meydan, Elif Sude
%A Sümer, Oğul
%A Keküllüoğlu, Dilara
%Y Oflazer, Kemal
%Y Köksal, Abdullatif
%Y Varol, Onur
%S Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-370-8
%F metin-etal-2026-sarcasturk
%X 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 SarcasTürk, a context-aware Turkish sarcasm detection dataset built from Ekşi Sözlük entries, a large-scale Turkish online discussion platform where people frequently use sarcasm. SarcasTürk 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). SarcasTürk can be shared upon contacting the authors since the dataset contains potentially sensitive and offensive language.
%U https://aclanthology.org/2026.sigturk-1.6/
%P 61-71
Markdown (Informal)
[SarcasTürk: Turkish Context-Aware Sarcasm Detection Dataset](https://aclanthology.org/2026.sigturk-1.6/) (Metin et al., SIGTURK 2026)
ACL
- Niyazi Ahmet Metin, Sevde Yılmaz, Osman Enes Erdoğdu, Elif Sude Meydan, Oğul Sümer, and Dilara Keküllüoğlu. 2026. SarcasTürk: Turkish Context-Aware Sarcasm Detection Dataset. In Proceedings of the Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026), pages 61–71, Rabat, Morocco. Association for Computational Linguistics.