Amrita_CEN at SemEval-2022 Task 6: A Machine Learning Approach for Detecting Intended Sarcasm using Oversampling

Abstract

This paper describes the submission of the team Amrita_CEN to the shared task on iSarcasm Eval: Intended Sarcasm Detection in English and Arabic at SemEval 2022. The sarcasm detection task was formulated as a classification problem and modelled using machine learning classifiers. We used K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, Decision Tree, and the Random Forest ensemble method. In addition, the class imbalance problem in the dataset was addressed using a feature engineering technique. We submitted the predictions by SVM, Logistic Regression and Random Forest ensemble based on the performance during training.