Personalized recommendation system based on social tags in the era of Internet of Things

Abstract With the rapid development of Internet, recommendation systems have received widespread attention as an effective way to solve information overload. Social tagging technology can both reflect users’ interests and describe characteristics items themselves, making group thus becoming a in urgent demand nowadays. In traditional tag-based systems, general processing method is calculate similarity then rank recommended according similarity. Without considering influence continuous user behavior, this article, we propose personalized algorithm based on social tags by combining ideas Markov chain collaborative filtering. This splits three-dimensional relationship <user-tag-item> into two two-dimensional relationships <user-tag> <tag-item>. The user’s interest degree calculated model, corresponding them are matched tag set. between used model satisfaction correlation contained items, filtering complete sparse values when calculating user–tags user–items improve accuracy recommendations. experiments show that publicly available dataset, proposed article has significantly improved recall rate compared with existing algorithms.