Chaos Sine Cosine Algorithm with Graph Convolution Network for Sarcasm Detection in Social Media

Abstract

Sarcasm is a procedure of verbal irony that is planned to convey ridicule, contempt or mockery with the aid of words that expresses the opposite of what is meant or through facial expression, tone of voice, or inflection. In another word, it is a way of saying something but meaning the opposite, often intending to be critical or humorous. Sarcasm is widely applied in social media, humour, and casual conversation. Sarcasm detection using deep learning (DL) includes training a machine learning (ML) algorithm for identifying instances of sarcasm and recognizing the pattern in language. The study presents a new Chaos Sine Cosine Algorithm with Graph Convolution Network for Sarcasm Detection (CSCA-GCNSD) technique in Social Media. The presented CSCA-GCNSD technique aims to recognize and categorize various kinds of sarcasm. Primarily, the CSCA-GCNSD technique involves different stages of data pre-processing. Next, the CSCA-GCNSD technique applies the GCN model for the detection and classification of various kinds of sarcasm. Finally, the CSCA technique is used to optimally choose the hyperparameter values of the GCN model and thereby resulting in improved detection outcomes. The simulation outcomes of the CSCA-GCNSD methodology was tested on different sarcasm datasets and the outcomes reported the betterment of the CSCA-GCNSD algorithms over other models.