Tue, Oct 08, 2013 @ 09:00 AM - 11:00 PM
Ming Hsieh Department of Electrical Engineering
Conferences, Lectures, & Seminars
Speaker: Charalampos Chelmis, Ph.D. Candidate / USC Viterbi School of Engineering
Talk Title: HETEROGENEOUS GRAPHS VS MULTI-MODAL CONTENT: MODELING, MINING AND ANALYSIS OF SOCIAL NETWORK DATA
Abstract: Complex networks arise everywhere. Online social networks are famous complex networks due to (a) revolutionizing the way people interact on the Web, and (b) permitting in practice the study of interdisciplinary theories that arise from human activities, at both micro (i.e. individual) and macro (i.e. community) level. Understanding the rich properties and dimensional interdependencies of topology and content in complex networks is necessary to uncover hidden structures and emergent knowledge.
We propose a formal model that abstracts the semantics of complex networks into an integrated, context aware, time sensitive, multi-dimensional space, enabling holistic examination of their static and dynamic properties, facilitating joint analysis of graphs and content and their explicit and implicit interactions. Traditionally, network analysis methods, either ignore content and focus on the network structure, or make implicit assumptions about the complex correlation of these two components. We show that accurately modeling multiple symmetric or asymmetric, explicit and hidden interaction channels between people, integrating auxiliary networks into a unified framework, leads to significant performance improvements in a variety of prediction and recommendation tasks. We empirically verify this insight using real-world datasets from online social networks and corporate microblogging data.
In this research, we investigate implicit relationships in composite networks. We propose a novel, robust model which facilitates multimodal analysis of time varying, complex social networking data. We 1) study informal communication behavior, information sharing, and influence at the workplace, 2) perform accurate communication intention prediction using auxiliary information, and 3) significantly improve social tie recommendation in online social bookmarking systems by exploiting the dynamics of collaborative annotation.
Biography: Charalampos Chelmis is a PhD candidate in the Department of Computer Science at the University of Southern California, Los Angeles. His research interests include modeling, mining and analysis of composite networks, large-scale (big) data analytics and information integration. He received his Master of Science in Computer Science from the University of Southern California in 2010 and his Bachelor in Computer Engineering & Informatics from the University of Patras, Greece in 2007.
Host: Defense Chair: Prof Viktor K. Prasanna
Audiences: Everyone Is Invited
Posted By: Janice Thompson