Semantic Data Acquisition by Traversing Class–Class Relationships Over Linked Open Data

Linked Open Data (LOD), a powerful mechanism for linking different datasets published on the World Wide Web, is expected to increase the value of data through mashups of various datasets on the Web. One of the important requirements for LOD is to be able to find a path of resources connecting two given classes. Because each class contains many instances, inspecting all of the paths or combinations of the instances results in an explosive increase of computational complexity. To solve this problem, we have proposed an efficient method that obtains and prioritizes a comprehensive set of connections over resources by traversing class–class relationships of interest. To put our method into practice, we have been developing a tool for LOD exploration. In this paper, we introduce the technologies used in the tool, focusing especially on the development of a measure for predicting whether a path of class–class relationships has connected triples or not. Because paths without connected triples can be predicted and removed, using the prediction measure enables us to display more paths from which users can obtain data that interests them.