Improved recommendation system with review analysis
Vinaya B. Savadekar, Manoj E. Patil · 2016
Recommender systems are proven to be valuable in course of time. From the development of web and ecommerce, the amount of online information has grown rapidly, which produces the big data analysis problem. Conventional recommender systems undergoes through scalability and inefficiency problems in processing of big data. Besides, most of existing recommendation systems present the same static ratings and rankings of items to different users without considering their different needs, and therefore fails to meet users personalized requirements. This paper uses English language Keyword list and domain thesaurus based personalized recommendation method. The system presents a personalized recommendation list and recommending the most appropriate items to the users effectively according to their needs. To improve its scalability and efficiency in big data environment, it is implemented on Hadoop, a distributed computing platform for parallel processing. The system improves the accuracy and scalability recommendation systems over existing approaches.