Predicting social networks in weblogs

Abstract

Weblogs and other platforms used to organize a social life online have achieved an enormous success over the last few years. Opposed to applications directly designed for building up and visualizing social networks, weblogs are comprised of mostly unstructured text data, that comes with some meta data, such as the author of the text, its publication date or the URL it is available under. In this paper, we propose a way, how these networks may be inferred not by the available meta data, but by pure natural language analysis of the text content, allowing inference of these networks without any meta data at hand. We discuss results of first experiments and outline possible enhancements as well as other ways to improve prediction of social networks based solely on content analysis.