Sarcasm Detection on Social Media: Addressing the Issues of Short and Long Texts Using Machine Learning and Deep Learning Approaches

Abstract

Sarcasm is a linguistic term that conveys a meaning that is different from what is meant to be said, frequently used to mock, taunt, or convey disdain. Sarcasm is a complicated social phenomenon that can be recognized by its tone of voice, exaggeration, or context. Because sarcastic discourse is nuanced, detecting sarcasm in Natural Language Processing (NLP) has become a major difficulty. This paper thoroughly examines the tradition machine learning approaches like SVM, Naive Bayes and Random Forest well as advanced deep learning methods such as RNN, LSTM, and transformer based models, like BERT, that has demonstrated superior performance used for sarcasm detection, and also the paper offers more sophisticated data preprocessing techniques that comprise several stages, each focusing on a different facet of the fragmented and informal character of the social media material. It focuses mainly on short and long texts that may be found in news headlines and social media sites like Facebook, Instagram, X (formerly known as Twitter), and others. The paper also explores various challenges like cultural and linguistic barriers, and increased use of audio and visual sarcastic content on social media. At last paper concludes with possible guidelines for future works including the development of real-time, multilingual systems to examining holistic strategies that can encompass the complexity of sarcasm in multimodal communications. Key Words: sarcasm, NLP, social media, machine learning, deep learning