Abstract

In recent years, the field of the Internet of Things (IoT), including smart and wearable devices, has witnessed a tremendous advancement leading to the collection of a wide variety of information not only about users but also their activities via various systems such as social networks, apps and so on. Thus, the collection of this large amount of data allows social systems to reach a wide variety of targets and gives more visibility about users and their profiles. It can also help to improve the services and functionalities of the users. Besides, the analysis and prediction of user’s activities in location-based social networks (LBSNs) have received much attention both from industries and research communities, especially in smart city developments, which give much importance to the automation of the LBSNs. In this paper, we present a new method based on association rules for user activity analysis in LBSNs. In particular, the Apriori algorithm has been applied to extract the consequential and advantageous rules to categorize users’ profiles. Empirical evaluations on a publicly available large-scale real-world dataset, named Gowalla, demonstrate the effectiveness of the presented association rules-based system in analyzing users’ activities via LBSNs.