Modified framework for sarcasm detection and classification in sentiment analysis

Abstract

<span>Sentiment analysis is directed at identifying people's opinions, beliefs, views and emotions in the context of the entities and attributes that appear in text. The presence of sarcasm, however, can significantly hamper sentiment analysis. In this paper a sentiment classification framework is presented that incorporates sarcasm detection. The framework was evaluated using a non-linear Support Vector Machine and Malay social media data. The results obtained demonstrated that the proposed sarcasm detection process could successfully detect the presence of sarcasm in that better sentiment classification performance was recorded. A best average F-measure score of 0.905 was recorded using the framework; a significantly better result than when sentiment classification was performed without sarcasm detection.</span>

A Survey of Sentiment Analysis and Sarcasm Detection

“…These models showcase the effectiveness of diverse techniques in social media sentiment analysis. In multilingual analysis, the Non-linear SVM with syntactic pragmatic-and pro-sodic-based features achieves a commendable 90.5% accuracy in Malay-English social media [36]. A prominent trend highlights the consistent success of models leveraging advanced embeddings like Word2Vec, TF-IDF, and BERT.…”

“…Suhaimin et al [36] proposed a sentiment analysis framework that integrates sarcasm detection. The proposed model comprises six modules: pre-processing, feature extraction, feature selection, initial sentiment classification, sarcasm detection, and final sentiment classification.…”

“…The versatility of techniques such as SVM, BiLSTM, and Random Forest, coupled with nuanced linguistic understanding, proves crucial for high accuracy in sentiment analysis across diverse datasets and languages. Tailoring models to specific linguistic nuances emerges as a good factor for optimal performance [9,29,30,36].…”

Sentiment analysis of Twitter posts related to the COVID-19 vaccines

“…In most online comments, people uses irregular language to announce their opinions. Furthermore, these comments and posts contain various language errors, such as in grammars and word spelling [8], [9]. This obstacle opens challenges for analyzing and interpreting human language [10].…”

“…This obstacle opens challenges for analyzing and interpreting human language [10]. Text mining or sentiment analysis [11] appears to be fully grasp the automatic processing of natural language (NLP) [9], [12]. Yang et al in [11] believed that sentiment analysis is aimed to analyse users' comments on the Internet in order to identify the underlying emotional information.…”