H. K. S. K. Hettikankanama, S. Vasanthapriyan, K. T. Rathnayake
Abstract
Opinions of others may be essential in making decisions or selecting from variety of alternatives. Review of customer feedback helps to improve sales and eventually benefits the company. Most online businesses use recommendation systems which use data mining and machine learning algorithms to find right product for right customer at right time to increase customer satisfaction. This study illustrate how to increase quality of product selection process for customers by reducing information overloading and complexity. Goal of this study is to propose a novel product ranking model considering user reviews which enable multiuser recommendation. Dataset was taken through some different supervised learning methods and best accurate algorithm was proposed. Values are predicted considering positivity and negativity of reviews for particular product using proposed algorithm. Products are ranked according to the given value. New recommendation model and its workflow is illustrated here.
Keywords: Machine learning, Opinion mining, Recommendation system, Sentiment analysis.
**View Full Paper in the Springer Source.