Towards quality measures for web network extraction
Within the Web information networks of various kinds are of interest for specific applications. These networks evolve in a decentralised manner. As such, they represent alternatives to centralised information sources such as databases. While crawlers can try to extract these networks from the Web, there is currently no systematic work on how to measure the quality of this extraction. Quality measures are of central importance to justify efforts and investments in Web network mining as an alternative to licence models of centralised information sources. In this paper we present a use case of such an interesting information network, that of the art market. We then present a simple model of a quantifiable quality measure of network extracted from the Web.
Full Text: PDF