A baseline for content-based blog classification

Abstract: A content-based network representation of web logs (blogs) using a basic word-overlap similarity measure is presented. Due to a strong signal in blog data the approach is sufficient for accurately classifying blogs. Using Swedish blog data we demonstrate that blogs that treat similar subjects are organized in clusters that, in turn, are hierarchically organized in higher-order clusters. The simplicity of the representation renders it both computationally tractable and transparent. We therefore argue that the approach is suitable as a baseline when developing and analyzing more advanced content-based representations of the blogosphere.