Finding association rules in linked data, a centralization approach

Abstract

Linked Data is used in the Web to create typed links between data from different sources. Connecting diffused data by using these links provides new data which could be employed in different applications. Association Rules Mining (ARM) is a data mining technique which aims to find interesting patterns and rules from a large set of data. In this paper, the problem of applying association rules mining using Linked Data in centralization approach has been addressed i.e. arranging collected data from different data sources into a single dataset and then apply ARM on the generated dataset. Firstly, a number of challenges in collecting data from Linked Data have been presented, followed by applying the ARM using the dataset of connected data sources. Preliminary experiments have been performed on this semantic data showing promising results and proving the efficiency, robust, and useful of the used approach. © 2013 IEEE.