Exploring big data in small forms: A multi-layered knowledge extraction of social networks

Big data poses great challenges for social network analysts in both the data volume and the latent dimensions hidden in the unstructured data. In this paper, we propose a comprehensive knowledge extraction approach for social networks to guide latent dimensions analysis. An improved hypergraph model of social behaviors was then proposed for conveniently conducting multi-faceted analytics in relationships inherent to social media. A real life case study based on Twitter´s data was also presented to illustrate the multi-dimensional relations between users based on the categories they co-join and the tweets they co-spread with three orthogonal dimensions of affect analyzed simultaneously, i.e. valence, activation, and intention.