@inproceedings{hacohen-kerner-etal-2022-jct-semeval,
    title = "{JCT} at {S}em{E}val-2022 Task 6-A: Sarcasm Detection in Tweets Written in {E}nglish and {A}rabic using Preprocessing Methods and Word N-grams",
    author = "HaCohen-Kerner, Yaakov  and
      Fchima, Matan  and
      Meyrowitsch, Ilan",
    editor = "Emerson, Guy  and
      Schluter, Natalie  and
      Stanovsky, Gabriel  and
      Kumar, Ritesh  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      Singh, Siddharth  and
      Ratan, Shyam",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.semeval-1.145/",
    doi = "10.18653/v1/2022.semeval-1.145",
    pages = "1031--1038",
    abstract = "In this paper, we describe our submissions to SemEval-2022 contest. We tackled subtask 6-A - {\textquotedblleft}iSarcasmEval: Intended Sarcasm Detection In English and Arabic {--} Binary Classification{\textquotedblright}. We developed different models for two languages: English and Arabic. We applied 4 supervised machine learning methods, 6 preprocessing methods for English and 3 for Arabic, and 3 oversampling methods. Our best submitted model for the English test dataset was a SVC model that balanced the dataset using SMOTE and removed stop words. For the Arabic test dataset our best submitted model was a SVC model that preprocessed removed longation."
}