期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：10
DOI：10.15680/IJIRCCE.2015.0310114
出版社：S&S Publications
摘要：Recommender systems are the systems that can give personalized recommendations or can suggest bestservice among all when a number of options are available. Traditional Recommender systems suffer from scalabilityand inefficiency. Moreover most of the existing recommender services presents same results as the ratings given. So, akeyword aware service recommendation method is suggested in this paper. KASR gives personalized recommendation.Both active users preferences and passive users reviews and sentiments in the text are considered for score calculation.Sentiment Analysis is applied on these reviews to provide more accuracy. This method will be implemented on Hadoopusing MapReduce paradigm. Hadoop will significantly improve the accuracy and efficiency by providing data setclustering across multiple nodes and fault tolerance in case of system failure.
