Rijke. Extracting the discussion structure in comments on news-articles

Several on-line daily newspapers offer readers the opportu-nity to directly comment on articles. In the Netherlands this feature is used quite often and the quality (grammatically and content-wise) is surprisingly high. We develop tech-niques to collect, store, enrich and analyze these comments. After giving a high-level overview of the Dutch ‘commento-sphere ’ we zoom in on extracting the discussion structure found in flat comment threads; people not only comment on the news article, they also heavily comment on other com-ments, resembling discussion fora. We show how techniques from information retrieval, natural language processing and machine learning can be used to extract the ‘reacts-on ’ re-lation between comments with high precision and recall