Sarcasm detection is the demanding natural language processing (NLP) task for sentiment analysis. Sarcasm detection is the process of identifying whether the text is sarcastic or non-sarcastic. Text pattern analysis is important to recognize the sarcastic text from the user. Analyzing the behavioral changes of the user is also considered an important factor in sarcasm detection. Behavioral changes of the users vary based on their mindset.
Consequently, it is inadequate with binary class modeling to investigate the various behavior of the users. Multi-class behavior modeling possesses the ability to analyze the various attitude of the user. Multi-class behavior modeling is performed by utilizing deep learning networks, which can better ability to classify multiple classes. Sarcasm detection with multi-class behavior modeling using deep learning capture the multi-level expression of the user to understand the nature of sarcasm effectively.
• Sarcasm plays a significant role as an interceding consideration that capsizes the sentimental polarity of the text, as such sarcasm detection raised as an interesting research area in sentiment analysis.
• Behavior modeling is manipulated to detect sarcasm based on analyzing the historical evidence of the text and verifying the probability of sarcastic text.
• With multi-level aspects of the sarcastic information and generated user to determine the variations of sarcasm, improve the productivity and outcomes of sarcasm identification.
• Multi-class classification fabricated with a deep learning approach for implementation of sarcasm detection help to analyze the sarcastic information and user opinion with multiple factors.
• Sarcasm detection using multi-class behavior modeling with deep learning is an effective approach to detecting sarcasm.