Multi-Class Sentiment Classification using Feature Selection and Machine Learning Algorithms

Sentiment analysis (SA) is a popular method for collecting relevant and arbitrary information from text-based data. To locate, examine, extract reactions, and emotions from the data or states, it applies computational linguistics, biometrics, text analysis, and Natural Language Processing (NLP). A SA model can be developed and improved with the use of the features analysis method. However, it can be difficult to find best classification methods for this type of data. When compared to current feature-based methods, machine learning approaches for analysis of sentiment, are capable of providing precise representation and improved performance. In this paper, the machine learning (ML) method was proposed for improving sentiment classification performance with a sophisticated embedding word method and develop an Emperor Penguin Optimization (EPO) and Multi-class Support Vector Machine (SVM). For the purpose of predicting the sentiment of tweets for classification, a large amount of Amazon data is analysed. This study, concentrate on improving sentiment analysis performance by building a Multi-class SVM network and particularized model of machine learning with novel word embedding techniques. The Multi-class SVM model has achieved 99.89% accuracy sentiment analysis.

I. Introduction

The process of locating, extracting, and categorising subjective information from unstructured text using text analysis and computational linguistic approaches is known as sentiment analysis (sometimes referred to as opinion mining) [1]. Sentiment analysis explores at the opinions, viewpoints, attitudes, sentiments, and perceptions that individuals share on different social media sites [2, 3]. This establishes if a clause, paragraph, or sentence expresses the text’s polarity or positive or negative opinion [4]. By use of textual assessments or reviews on social media (such as forms, social networking sites, blogs, etc.), it looks at people’s feelings on a variety of subjects, including people, issues, events, people, and objects [5]. Amazon is one well-known retailer that permits customers to freely evaluate and discuss products. Evaluating these evaluations and categorising them as good or negative can help customers make decisions about investing, buying a phone, cameras, or other product, or writing movie reviews. The customers’ daily lives will be significantly impacted by each of these behaviours. Sentiment analysis can be using a variety of data mining techniques, many of which are always attempting to get more accurate. Intuition suggests that the previous studies only considered product and user data as separate attributes that might be added separately to the text representation [6]. Everyone may now communicate their thoughts and opinions online thanks to the social media industry’s rapid expansion. In order to understand what customers or reviewers believe, sentiment analysis is crucial [7]. The study aims to create an efficient feature selection approach for sentiment analysis, similarly to this classified using Machine learning, a kind of AI. [8].