Sentiment Analysis of Twitter Data Using Hybrid Classification Methods and Comparative Analysis

Abstract

Recently, there are emergence and advent of data Inter-personal interaction web sites, micro blogs, wikis, in addition to Web applications and data, e.g. tweets and web-postings express views and opinions on different topics, issues and events in many applications, in addition to, different domains that includes business, economy, politics, sociology, and etc., which are resulted from offering immense opportunities for studying and analyzing human views and sentiment. The objective of sentiment analysis is to classify a speaker's or a writer’s attitude towards various events or topics and arranging data into positive, negative or neutral categories. Sentiment analysis means determining the views of a user from the textual content regarding that topic i.e. how one feels about it. It might be used to classify the text content. Various researchers have used a widespread sort of methods to teach the classifiers for the Twitter dataset with various results. The research uses a hybrid method of using Swarm Intelligence optimization (PSO) algorithms with classifiers.

The Support Vector Machine (SVM), k-nearest neighbours algorithm (KNN), k-nearest neighbor (KNN), hybrid classification method, Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO) and planned optimised feature sets model is offered to progression the tweet features and to recognise the out of sight sentiments from these tweets. These essential concepts when used in combinations become a very significant tool for analysing millions of variety conversations with human echelon accurateness. The projected optimised feature sets model Sentiment Analysis exercises the assessment metrics of Precision, Recall, F-score, and Accuracy. Also, average measures weighted F1-scores are constructive for categorization of Positive, Negative and Neutral multi-class problems. Sentiment Analysis with planned optimised feature sets achieves 82 percent accuracy, compared to SVM's 78.6% and ACO 75%. Furthermore, we measured only tweets in English that were acknowledged by the Twitter streaming API while evaluating sentiments of tweets.