Topic Detection and Classification in Social Networks

Provides a language-agnostic method for social media text analysis, which is not based on a specific grammar, semantics or machine learning techniques

Detects topics from large text documents and extracts the main opinion without any human intervention

Compares a variety of techniques and provides a smooth transition from theory to practice with multiple experiments and results

Autorentext
Dr. Dimitrios Milioris is a research associate and lecturer at the Massachusetts Institute of Technology (MIT). He received his Ph.D. from École Polytechnique Paris (2015, honors) while a scholar at Columbia University, New York, USA, as an Alliance Program awardee (2013 2014). He received his double M.Sc. degree (2011, first in class, honors) in computer science & applied mathematics from Paris XI University and the École Polytechnique, and his B.Sc. degree (2009, honors) in computer science from the University of Crete, Greece. Prior to joining MIT, he was a researcher at Bell Labs, Alcatel-Lucent in Paris, France, and a member of the Mathematics of Dynamic & Complex Networks Department. Prior to joining Bell Labs, he served as a research assistant at the Institute of Computer Science (ICS) of the Foundation for Research and Technology Hellas (FO.R.T.H.), and as a research engineer with the Hipercom Team at the National Institute for Research in Computer Science and Automatic Control (I.N.R.I.A.), followed by a compulsory military service in Telecommunications Division.

Inhalt

Introduction.- Background and Related Work.- Joint Sequence Complexity.- Text Classification via Compressive Sensing.- Extension of Joint Complexity and Compressive Sensing.- Conclusion.