News Event Understanding by Mining Latent Factors From Multimodal Tensors

We present a novel and efficient constrained tensor factorization algorithm that first represents a video archive, of multimedia news stories concerning a news event, as a sparse tensor of order 4. The dimensions correspond to extracted visual memes, verbal tags, time periods and cultures. The iterative algorithm then approximately but accurately ex- tracts coherent quad-clusters, each of which represents a significant summary of an important independent aspect of the news event. We give examples of quad-clusters extracted from tensors with at least 108 entries derived from the international news coverage of the Ebola epidemic, AirAsia flight Q8501 and Zika virus. We show the method is fast, can be tuned to give preferences to any subset of its four dimensions, and exceeds three existing methods in performance.