Improvement of recommender systems considering big data of users’ comments on chosen items
Regarding to the increase in the online social networks services during the recent years, the recommender system has turned into an emerging research subject. Currently, regarding to the fast and consistent expansion of using the internet, the necessity of a recommender system for refining the large volume of data has increased greatly. The purpose of recommender systems is to provide a list of the interested items for the user and due to the increase in the current data volume, the previous used tools are nor suitable for processing this data volume; hence, having a system which can save and process the large data has turned into a problem. In this study, to solve the mentioned problems, a system is recommended using a model-based collaborative filtering refinement model which uses the Spark processing model in Hadoop context in order for more exact advising the user from the viewpoint of the users. The obtained results indicate that the current method will be more efficient and effective compared to the common recommendation methods.
Keywords: recommender systems; big data; sentiment analysis; hadoop; spark.