Hybrid Particle Swarm Optimization with Deep Learning Driven Sarcasm Detection on Social Media

Sarcasm is a language phrase that transports the polar opposite of what is being said, usually something extremely disagreeable to mock or offend someone. Sarcasm was commonly employed on social networking sites daily. Since sarcasm might alter the significance of statement, the opinion analysis process is error-prone. Concerns regarding the integrity of analytics have developed as the utilization of automatic social media analytics apparatuses has extended. Based on the earlier study, sarcastic statements alone have considerably decreased the performance of automated sentiment analysis. This article develops a Hybrid Particle Swarm Optimization with Deep Learning Driven Sarcasm Detection (HPSO-DLSD) technique. The presented HPSO-DLSD technique mainly concentrates on the recognition of sarcasm on social media. In the presented HPSO-DLSD technique, the initial stage of data preprocessing is carried out. To detect and classify sarcasm, sparse stacked autoencoder (SAE) model is exploited and the detection performance can be boosted via the HPSO algorithm. The experimental result analysis of the HPSO-DLSD technique can be tested on benchmark dataset and the outcomes emphasized the enhancements of the HPSO-DLSD method over other current approaches.