期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2014
卷号：9
期号：5
页码：263-272
DOI：10.14257/ijmue.2014.9.5.26
出版社：SERSC
摘要：In our previous work, a user similarity-based contents recommendation service using NFC was proposed for the same goal. This service used a small sample because it used only information of the user who had watched a museum. However, it has been shown that there are some limitations resulting from the difficulty of accurately predicting the user's preference. In order to lift this drawback, this paper introduces a user taste prediction service using big data for improving user-friendliness to a maximum. The proposed service predicts the user's taste using big data such as Twitter and blogs. It is possible to predict the exact user's preference and might recommend more suitable contents to the user's taste because it predicts the user`s taste using big data with a variety of user's social network information. So, it can recommend contents that match the user's taste. Our simulation results show the proposed big data-based approach can give each museum visiting user more accurate recommendation service appropriate to his or her taste compared with the previous one in terms of user preferences to exhibition-related contents.
关键词：Museum Viewing; Contents Recommendation; User-friendliness; Social ; Network; MapReduce
