Time-aware IoE service recommendation on sparse data

With the advent of "Internet of Everything" (IoE) age, an excessive number of IoE services are emerging on the web, which places a heavy burden on the service selection decision of target users. In this situation, various recommendation techniques are introduced to alleviate the burden, for example, Collaborative Filtering- (CF-) based recommendation. Generally, CF-based recommendation approaches utilize similar friends or similar services to achieve the recommendation goal. However, due to the sparsity of user feedback, it is possible that a target user has no similar friends and similar services; in this situation, traditional CF-based approaches fail to produce a satisfying recommendation result. Besides, recommendation accuracywould be decreased if time factor is overlooked, as IoE service quality often varies with time. In view of these challenges, a time-aware service recommendation approach named Ser_Rec_time is proposed in this paper. Concretely, we first calculate the time-aware user similarity; afterwards, indirect friends of the target user are inferred by Social Balance Theory (e.g., "enemy's enemy is a friend" rule); finally, the services preferred by indirect friends of the target user are recommended to the target user. At last, through a set of experiments deployed on dataset WS-DREAM, we validate the feasibility of our proposal.