Conference Paper

Evaluation of Different Sarcasm Detection Models for Arabic News Headlines

Mohammed P.
Eid Y.
Badawy M.
Hassan A.

Being sarcastic is to say something and to mean something else. Detecting sarcasm is key for social media analysis to differentiate between the two opposite polarities that an utterance may convey. Different techniques for detecting sarcasm are varying from rule-based models to Machine Learning and Deep Learning models. However, researchers tend to leverage Deep Learning in detecting sarcasm recently. On the other hand, the Arabic language has not witnessed much improvement in this research area. Bridging the gap in sarcasm detection of the Arabic language is the target behind this work. In this paper, efficient models in short text classification are tested for detecting sarcasm in the Arabic news headlines for the first time. The dataset used to train and test these different architectures was manually collected by scrapping two different websites, sarcastic and non-sarcastic. Detailed results for each model were also represented, based on different performance metrics, such as accuracy, precision, recall and F1 score. © Springer Nature Switzerland AG 2020.