Hybrid Spider Monkey Optimization Technique for Twitter Sentiment Inspection

Abstract

Sentiment analysis (SA) is an interesting subject of data analysis that aims to recognise and translate the diverse feelings expressed on social media sites. Twitter is a social service where users may update their friends and followers with short messages called “tweets.” This paper's goal is to provide a technique for mining Twitter for sentiments. Based on the sentiment expressed, a tweet might be seen as good, neutral, or negative. The personal character of tweets makes traditional clustering methods impractical, making metaheuristic-based methods the best option. To measure the efficiency of the planned technique, we use two datasets: sender2 and tweeter. Several prominent nature-inspired methods, including Spider-Monkey optimization, Particle-Swarm algorithm, Genetic-Algorithm, and degree of difference Evolution, are compared with the conventional method to determine its validity. This is done so that the legitimacy of the suggested technique can be assessed.