Service Recommendation Based on Ranking Using Keywords in Hadoop

Abstract

Recommendation system acts as a tool in providing the most appropriate service to the user. Currently, information through online services is increased. This leads to the overhead of data in online and there is a possibility of getting less accurate prediction. In previous approaches, recommendation of services does not consider the suggestion of the user at a time, was in need of searching for the particular service. The proposed system deals with the implementation of personalized recommendation to provide services for hotel reservation system. Candidate service is created as the combination of keyword list and Domain Thesaurus which consist of semantically annotated words. Preferences are collected from the active user about particular service for each application. Similar user’s opinions are taken from the reviews using keyword extraction method. Similarity is calculated between user preferences with reviews of the previous user using jaccard and cosine similarity measures. From this most similar keywords are provided to the user as a recommended service using MapReduce framework. It outperforms about 8% when compared with previous approaches, in providing the accurate prediction of relevant service to the active user.