作者: Marija Mitrović , Georgios Paltoglou , Bosiljka Tadić
DOI: 10.1140/EPJB/E2010-00279-X
关键词:
摘要: Online communications at web portals represents technology-mediated user interactions, leading to massive data and potentially new techno-social phenomena not seen in real social mixing. Apart from being dynamically driven, the interactions via posts is indirect, suggesting importance of contents posted material. We present a systematic way study Blog by combined approaches physics complex networks computer science methods text analysis. are mapping onto bipartite network where users with comments two natural partitions. With machine learning we classify texts for their emotional as positive or negative, otherwise objective (neutral). Using spectral weighted graphs, identify topological communities featuring clustered around certain popular posts, underly role emergence evolution these communities.