A Survey of Sentiment Analysis and Sarcasm Detection: Challenges, Techniques, and Trends

Authors

  • Ahmed Derbala Yacoub Helwan University Faculty of Computers and Artificial Intelligence Cairo EGYPT https://orcid.org/0009-0006-1200-1301
  • Salwa O. Slim Helwan University Faculty of Computers and Artificial Intelligence Cairo EGYPT
  • Amal Elsayed Aboutabl Helwan University Faculty of Computers and Artificial Intelligence Cairo EGYPT

DOI:

https://doi.org/10.32985/ijeces.15.1.7

Keywords:

Sarcasm detection, Sentiment analysis, Natural language processing, Deep learning, machine learning

Abstract

In recent years, more people have been using the internet and social media to express their opinions on various subjects, such as institutions, services, or specific ideas. This increase highlights the importance of developing automated tools for accurate sentiment analysis. Moreover, addressing sarcasm in text is crucial, as it can significantly impact the efficacy of sentiment analysis models. This paper aims to provide a comprehensive overview of the conducted research on sentiment analysis and sarcasm detection, focusing on the time from 2018 to 2023. It explores the challenges faced and the methods used to address them. It conducts a comparison of these methods. It also aims to identify emerging trends that will likely influence the future of sentiment analysis and sarcasm detection, ensuring their continued effectiveness. This paper enhances the existing knowledge by offering a comprehensive analysis of 40 research works, evaluating performance, addressing multilingual challenges, and highlighting future trends in sarcasm detection and sentiment analysis. It is a valuable resource for researchers and experts interested in the field, facilitating further advancements in sentiment analysis techniques and applications. It categorizes sentiment analysis methods into ML, lexical, and hybrid approaches, highlighting deep learning, especially Recurrent Neural Networks (RNNs), for effective textual classification with labeled or unlabeled data.

Downloads

Published

2024-01-09

Issue

Section

Review Papers