@inproceedings{003fd555daac4848a2008917d2a37cc1,
title = "DAICT: A dialectal arabic irony corpus extracted from twitter",
abstract = "Identifying irony in user-generated social media content has a wide range of applications; however to date Arabic content has received limited attention. To bridge this gap, this study builds a new open domain Arabic corpus annotated for irony detection. We query Twitter using irony-related hashtags to collect ironic messages, which are then manually annotated by two linguists according to our working definition of irony. Challenges which we have encountered during the annotation process reflect the inherent limitations of Twitter messages interpretation, as well as the complexity of Arabic and its dialects. Once published, our corpus will be a valuable free resource for developing open domain systems for automatic irony recognition in Arabic language and its dialects in social media text.",
keywords = "Arabic Dialects, Corpus Generation, Irony, Twitter",
author = "Ines Abbes and Wajdi Zaghouani and Omaima El-Hardlo and Faten Ashour",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC; 12th International Conference on Language Resources and Evaluation, LREC 2020 ; Conference date: 11-05-2020 Through 16-05-2020",
year = "2020",
language = "English",
series = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "6265--6271",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis",
booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
}