Search

In Social Network Analysis (SNA) centrality measures focus on activity (degree), information access (betweenness), distance to all the nodes (closeness), or popularity (pagerank). We introduce a new measure quantifying the distance of nodes to the network center. It is called weighted distance to nearest center (WDNC) and it is based on edge-weighted closeness (EWC), a weighted version of closeness. It combines elements of weighted centrality as well as clustering. The WDNC will be tested on two e-mail networks of the R community, one of the most important open source programs for statistical computing and graphics. We will find that there is a relationship between the WDNC and the formal organization of the R community., Series: Research Report Series / Department of Statistics and Mathematics

Social network analysis (SNA) provides tools to examine relationships between people. Text mining (TM) allows capturing the text they produce in Web 2.0 applications, for example, however it neglects their social structure. This paper applies an approach to combine the two methods named "content-based SNA" (CB-SNA). Using the R mailing lists, R-help and R-devel, we show how this combination can be used to describe people's interests and to find out if authors who have similar interests actually communicate. We find that the expected positive relationship between sharing interests and communicating gets stronger as the centrality scores of authors in the communication networks increase., Series: Research Report Series / Department of Statistics and Mathematics

Text mining has become an established discipline both in research as in business intelligence. However, many existing text mining toolkits lack easy extensibility and provide only poor support for interacting with statistical computing environments. Therefore we propose a text mining framework for the statistical computing environment R which provides intelligent methods for corpora handling, meta data management, preprocessing, operations on documents, and data export. We present how well established text mining techniques can be applied in our framework and show how common text mining tasks can be performed utilizing our infrastructure. The second part in this thesis is dedicated to a set of realistic applications using our framework. The first application deals with the implementation of a sophisticated mailing list analysis, whereas the second example identifies the potential of text mining methods for business to consumer electronic commerce. The third application shows the benefits of text mining for law documents. Finally we present an application which deals with authorship attribution on the famous Wizard of Oz book series. (author's abstract)