Applied Linguistics Driven Large Language Model For Sarcasm Recognition On Social Media Corpora

Sarcasm is a language phrase that expresses the opposite of what is stated, often used for mocking or offending. It is commonly seen on social media platforms day by day. The opinion analysis process is susceptible to errors due to the potential for sarcasm to alter the statement’s meaning. As automated social media research tools become more prevalent, the reliability problems of analytics have also increased. According to the prior study, sarcastic reports alone have greatly diminished the automatic Sentiment Analysis (SA) performance in complex systems platforms. Sarcasm detection utilizing Deep Learning (DL) contains training models to identify the nuanced linguistic cues that indicate sarcasm in text. Typically, this process applies large datasets annotated with sarcastic and non-sarcastic samples to teach models to discriminate between them. DL methodologies, namely Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformer methods like BERT or GPT, are widely applied due to their ability to capture intricate patterns in language. This model learns to detect sarcasm by discriminating exaggerated expressions, contextual incongruities, and semantic reversals frequently related to sarcastic remarks. Therefore, this study presents a Fractal Red-Tailed Hawk Algorithm with Hybrid Deep Learning-Driven Sarcasm Detection (RTHHDL-SD) technique on complex systems and social media platforms. The purpose of the RTHHDL-SD technique is to identify and classify the occurrence of sarcasm in social media text. In the RTHHDL-SD approach, data preprocessing is performed in four ways to transform input data into valuable design. Besides, the RTHHDL-SD technique applies the FastText word embedding approach to generate word embeddings. The RTHHDL-SD technique applies a Deep Neural Network (DNN) with bi-directional long short-term memory for sarcasm detection, called the deep BiLSTM model. The RTH method was utilized as the hyperparameter optimizer to enhance the detection performance of the deep BiLSTM model. Moreover, the large language model is used to estimate the outcomes of the social media corpora. The simulation outcomes of the RTHHDL-SD methodology are examined under Twitter and Headlines datasets. The investigational outcomes of the RTHHDL-SD methodology exhibited superior accuracy values of 89.10% and 92.77% with other approaches.