Paper Contents
Abstract
Sarcasm detection has become one of the important research areas in natural language processing (NLP) 1 in recent years. Many applications in the field of natural language processing like sentiment analysis, opinion mining, and dialogue systems can benefit from understanding sarcasm better. Nevertheless, detecting sarcasm is a complicated and frustrating task. The detection of sarcasm due to the nature of this emotion requires a number of clinical and clinical approaches in this area. This paper provides a critical survey on the emergence of several state-of-the-art techniques and interesting data combination approaches aimed at sarcasm detection 2. We also address the shortcomings of traditional methods and emphasize the necessity of broadening the range of data used for detection, with multimodal data, for instance, being one such data set. In addition, we introduce a new framework for irony detection that considers linguistic, cognitive, and multiple types of resources, including images. The results of our experiments confirmed the validity of our approach: we reached the highest recorded efficiency on a number of thematically relevant datasets 3.
Copyright
Copyright © 2024 Mr. Amit Srivastava, Rishabh Gupta, Sumit Verma. This is an open access article distributed under the Creative Commons Attribution License.
