A Literature Review : Enhancing Sentiment Analysis of Deep Learning Techniques Using Generative AI Model

Abstract

Sentiment analysis is possibly one of the most desirable areas of study within Natural Language Processing (NLP). Generative AI can be used in sentiment analysis through the generation of text that reflects the sentiment or emotional tone of a given input. The process typically involves training a generative AI model on a large dataset of text examples labeled with sentiments (positive, negative, neutral, etc.). Once trained, the model can generate new text based on the learned patterns, providing an automated way to analyze sentiments in user reviews, comments, or any other form of textual data. The main goal of this research topic is to identify the emotions as well as opinions of users or customers using textual means. Though a lot of research has been done in this area using a variety of models, sentiment analysis is still regarded as a difficult topic with a lot of unresolved issues. Slang terms, novel languages, grammatical and spelling errors, etc. are some of the current issues. This work aims to conduct a review of the literature by utilizing multiple deep learning methods on a range of data sets. Nearly 21 contributions, covering a variety of sentimental analysis applications, are surveyed in the current literature study. Initially, the analysis looks at the kinds of deep learning algorithms that are being utilized and tries to show the contributions of each work. Additionally, the research focuses on identifying the kind of data that was used. Additionally, each work's performance metrics and setting are assessed, and the conclusion includes appropriate research gaps and challenges. This will help in identifying the non-saturated application for which sentimental analysis is most needed in future studies.