Representing and summarizing human behaviors with rich contexts facilitates behavioral sciences and user-oriented services. Traditional behavioral modeling represents a behavior as a tuple in which each element is one contextual factor of one type, and the tensor-based summaries look for high-order dense blocks by clustering the values (including timestamps) in each dimension. However, the human behaviors are multicontextual and dynamic: (1) each behavior takes place within multiple contexts in a few dimensions, which requires the representation to enable non-value and set-values for each dimension; (2) many behavior collections, such as tweets or papers, evolve over time. In this paper, we represent the behavioral data as a two-level matrix (temporal-behaviors by dimensional-values) and propose a novel representation for behavioral summary called Tartan that includes a set of dimensions, the values in each dimension, a list of consecutive time slices and the behaviors in each slice. We further develop a propagation method CATCHTAR-TAN to catch the dynamic multicontextual patterns from the temporal multidimensional data in a principled and scalable way: it determines the meaningfulness of updating every element in the Tartan by minimizing the encoding cost in a compression manner. CATCHTARTAN outperforms the baselines on both the accuracy and speed. We apply CATCHTARTAN to four Twitter datasets up to 10 million tweets and the DBLP data, providing comprehensive summaries for the events, human life and scientific development.

Filed under: Mining Rich Data Types | Graph Mining and Social Networks