RETRACTED ARTICLE: Classifying streaming of Twitter data based on sentiment analysis using hybridization

Abstract

Twitter is a social media that developed rapidly in today’s modern world. As millions of Twitter messages are sent day by day, the value and importance of developing a new technique for detecting spammers become significant. Moreover, legitimate users are affected by means of spams in the form of unwanted URLs, irrelevant messages, etc. Another hot topic of research is sentiment analysis that is based on each tweet sent by the user and opinion mining of the customer reviews. Most commonly natural language processing is used for sentiment analysis. The text is collected from user’s tweets by opinion mining and automatic sentiment analysis that are oriented with ternary classifications, such as “positive,” “neutral,” and “negative.” Due to limited size, unstructured nature, misspells, slangs, and abbreviations, it is more challenging for researchers to find sentiments for Twitter data. In this paper, we collected 600 million public tweets using URL-based security tool and feature generation is applied for sentiment analysis. The ternary classification is processed based on preprocessing technique, and the results of tweets sent by the users are obtained. We use a hybridization technique using two optimization algorithms and one machine learning classifier, namely particle swarm optimization and genetic algorithm and decision tree for classification accuracy by sentiment analysis. The results are compared with previous works, and our proposed method shows a better analysis than that of other classifiers.