Sentiment Classification on Mobile Review Using Extraction of Sentiment Conveying Sentences
Mohammad Irsad · Journal of Informatics Electrical and Electronics Engineering (JIEEE) · 2024
In the present time, sentiment analysis has become the most successful technique to identifying people's views, opinions or emotions about any product, service or event. Sentiment analysis became more popular as a result of the widespread use of e-commerce sites and social media platforms such as Twitter, Facebook etc. by individuals who want to express their feelings, views emotions or opinions about any product, service or event. Individuals make efforts in order to express themselves. Sentiment analysis is extremely helpful for companies that are selling a product to determine how their product was perceived by consumers. Therefore, it has become essential to generate fast, reliable and efficient techniques for mining user reviews. In this paper, we have proposed an approach to extract sentiment conveying sentences from the review and used three machine learning classifiers: Random Forest, Multinomial Naïve Bayes and Random Forest. The experimental results show that the machine learning classifiers achieve higher accuracy and Random Forest achieve highest accuracy.