Qos and Keyword-Aware Service Recommendation Method on Map Reduce for Big Data Applications

Abstract
Similar to most big data applications, the big data tendency also poses heavy impacts on service recommender systems. With the growing number of alternative services, effectively recommending services that users preferred has became an important research issue. Service recommender systems have been exposed as valuable tools to help users deal with services overload and provide appropriate recommendations to them. In KASR, keywords are used to indicate users' preferences, and a user-based Collaborative filtering algorithm is adopted to generate appropriate recommendations. More specifically, a keyword-candidate list and domain thesaurus are provided to help obtain users' preferences. The active user gives his/her preferences by selecting the keywords from the keyword-candidate list, and the preferences of the previous users can be extracted from their reviews for services according to the keyword-candidate list and domain thesaurus. The proposed system proposes methods it aims at presenting a personalized service recommendation list and recommending the most appropriate service(s) to the users. To improve the scalability and efficiency of KASR in “Big Data” environment, the proposed system proposes techniques that have been implemented it on a Map Reduce framework in Hadoop platform. It improves the recommendation accuracy by considering the location of the user while recommend the service.
Keywords:recommender system, preference, keyword, Big Data, MapReduce, Hadoop.
INTRODUCTION
In recent years, the amount of data in our world has been increasing explosively, and analyzing large data sets—so-called “Big Data”— becomes a key basis of competition underpinning new waves of productivity growth, innovation, and consumer surplus. Handling of large scale data, to provide recommendation, consequently, traditional service recommender systems often suffer from scalability and inefficiency problems when processing or analyzing such large-scale data. Moreover, most of existing service recommender systems present the same ratings and rankings of services to different users without considering diverse users' preferences, and therefore fails to meet users' personalized requirements. The proposed system provides technique to personalize recommended services. There have been many recommender systems developed in both academia and industry. The authors propose a Bayesian-inference-based recommendation system for on-line social networks. They show that the proposed Bayesian-inference-based recommendation is better than the existing trust-based recommendations and is comparable to Collaborative Filtering recommendation. In Adomavicius and Tuzhilin give an overview of the field of recommender systems and describe the current generation of recommendation methods. They also describe various limitations of current service recommendation methods, and discussed possible extensions that can improve recommendation capabilities and make recommender systems applicable to an even broader range of applications. Most existing service recommender systems are only based on a single numerical rating to represent a service's utility as a whole. In fact, evaluating a service through multiple criteria and taking into account of user feedback can help to make more effective recommendations for the users.