Modeling the Evolution of Discussion Topics and Communication to Improve Relational Classification
Textual analysis is one means by which to assess communication type and moderate the influence of network structure in predictive models of individual behavior. However, there are few methods available to incorporate textual content into time-evolving network models. In particular, modeling both the evolution of network topology and textual content change in time-varying communication data poses a difficult challenge. In this work, the authors propose a Temporally Evolving Network Classifier (TENC) to incorporate the influence of time-varying edges and temporally-evolving attributes in relational classification models.