The Team Formation Approach: Problems, Algorithms & Applications

Tuesday, March 5, 2013 ( 2:00 pm to 3:00 pm )

Location: Babbio 430

Howe School Talk

Theodoros Lappas, Ph.D., Boston University

 

ABSTRACT

The popularity of Social Media and E-commerce Platforms has led to the accumulation of large volumes of diverse data. Access to such datasets is typically provided via search engines and recommendation systems that evaluate candidate objects (e.g. documents, pictures, products, individuals) based on their estimated relevance to the user's interests. The potential of such mechanisms is limited by the fact that they evaluate candidates individually, ignoring their latent connections and the different ways in which they complement each other. For example, consider two very similar articles that deliver the same information on the same topic. Even though both articles may be highly relevant to the topic, it is redundant to present both of them to the interested user. Instead, it is preferable to select a team of relevant articles that covers different aspects of the topic of interest. In this talk, Dr. Lappas will motivate the team formation approach and discuss how he has applied it to design algorithms and build scalable systems to support popular applications from different domains. A special focus will be placed on expert team formation in social networks. Given a project that requires a certain set of skills in order to be completed, the talk will describe efficient methods for selecting a team of experts who can collectively cover all the required skills, and are also able to communicate and collaborate effectively. It will then be shown how the value of an individual expert can be assessed in the context of a collaborative setting, such as those found in crowdsourcing platforms and freelance marketplaces.

 

BIOGRAPHY

Dr. Theodoros Lappas is a Postdoctoral Researcher in the Data Management Lab at Boston University. He also holds the position of Visiting Fellow at the Rafik B. Hariri Institute for Computing and Computational Science & Engineering, Boston University's hub for interdisciplinary research. His research interests include Data Mining, Social Computing, Machine Learning, Web Search, and Ecommerce. Dr. Lappas received his Ph.D. from the Department of Computer Science & Engineering at the University of California Riverside, where he completed his dissertation on Algorithmic Challenges in Social Media Search. He also holds an undergraduate degree in Informatics from the Athens University of Economics and Business, with a specialization in Information Systems.