Analysis of e-discussions using classifier induced semantic spaces

We categorize contributions to an e-discussion platform using Classifier Induced Semantic Spaces and Self-Organizing Maps. Analysing the contributions delivers insight in to the nature of the communication process, makes it more comprehensible and renders the resulting decisions more transparent. Additionally, it can serve as a basis to monitor how the structure of the communication evolves over time. We evaluate our approach on a public e-discussion about an urban planning project, the Berlin Alexanderplatz, Germany. The proposed technique does not only produce high-level features relevant to structure and monitor computer mediated communication, but also provides insight into how typical a particular document is for a specific category.