Towards Understanding the Changing Web: Mining the Dynamics of Linked-Data Sources and Entities

Publication Type:

Conference Paper

Source:

KDML (Workshop) (2010)

URL:

http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml22.pdf

Abstract:

A huge amount of content found on the Web is dynamic by its nature, particularly with the rise of Web 2.0 and beyond. This is of special interest for the Semantic Web community, not only but particularly regarding resources on the Linked Open Data (LOD) Web. However, the dataset dynamics of the LOD graph are hardly explored so far. Existing approaches from the traditional HTML Web are not sufficient to mine and discover the dynamics with satisfying accu- racy and efficiency, as they do not consider the special characteristics of LOD. We present first initial results on this topic and discuss future steps. First results are obtained by mining the groups of URIs with similar change frequencies and by applying time series techniques as well as clustering techniques.

Notes:

* Non-Clique Members

Social Network Analysis Group

Search

User login

Subscribe to Clique

Sponsors