Speaker: Ehsan Ebrahimzadeh
Affiliation: Ph.D. Candidate - UCLA
Abstract: We present computational and statistical tools that can efficiently and accurately extract multi-scale narrative structures from large-scale social media datasets. We summarize discussions as “Story Narratives Networks” comprised of nodes that represent primary actant groups, and links that capture sequences of interactions amongst the actant groups. As one of the contributions of our work, we demonstrate how to determine distinct actant groups in an unsupervised manner from contextual unstructured data. In particular, we provide a mathematical framework for formalizing the notion that each such group consists of actors that have the same contextual role in the narrative. We construct low-dimensional sparse vector embeddings using dimensionality reduction techniques such as Non-Negative Matrix Factorization (NMF) for actors, and then cluster these embeddings to obtain actant groups. We propose an exterior point method to solve the NMF problem, which constructs a solution based on a suitably rotated optimal solution of the unconstrained matrix factorization problem. We evaluate the performance of our proposed algorithm and embedding-based clustering scheme on two datasets, namely data from a discussion forum on parenting issues and a corpus of tweets on user experience with contact-less payment methods. Finally, towards understanding the dynamics in the evolution of stories, we study the problem of detecting changes in the temporal evolution of the user activities. We formulate this problem in a transient change point detection setting and design a statistical test to detect the change based on the number of user activities observed so far, with minimum expected delay under a controlled measure of false alarm. We evaluate the change detection method on a corpus of tweets related to Super Bowl 2015.
Biography: Ehsan Ebrahimzadeh is a Ph.D. candidate in the UCLA Electrical and Computer Engineering Department under the supervision of Professor Vwani Roychowdhury. He is interested in information retrieval, online learning and high dimensional statistics. Ehsan received his master’s degree in Electrical Engineering from University of Waterloo in Canada, focusing on Information Theory and Random Graphs, and his bachelor’s degrees in Mathematics and Electrical Engineering from Isfahan University of Technology, Isfahan, Iran.
Date(s) - Jun 07, 2018
2:00 pm - 4:00 pm
E-IV Tesla Room #53-125
420 Westwood Plaza - 5th Flr., Los Angeles CA 90095