There are so many social networking sites available. Tweets have evolved into a crucial tool for gathering people's thoughts, ideas, behaviours and sentiments surrounding particular entities. One of the most intriguing subjects in this context is analyzing the sentiment of tweets using natural language processing (NLP). Although several methods have been created, the accuracy and effectiveness of those methods for sentiment analysis are yet to be improved. This paper proposes an innovative strategy that takes advantage of machine learning and lexical dictionaries. Tweets are classified using a stacked ensemble model that has Naive Bayes as a base classifier and the Logistic Regression as a meta classifier model. The performance of the proposed method is compared with common machine learning models such as Naïve Bayes and Logistic Regression using the sentiment140 dataset, experiments were carried out and their accuracy was determined. The results of the experiment endorse the proposed methodology. exhibits better outcomes of attaining accuracy score of 86%.

sentiment analysis ensemble model logistic regression natural language processing naive bayes machine learning