Abstract:
People rely on a personal network of friends and colleagues to get trusted
information; help filter and interpret information; and get referrals to
other people. Moreover, to build such networks, people may leverage multiple
means of interaction, such as email, face-to-face meetings, friending
activities, and etc. These multi-faceted signals about people give ample
opportunities to understand their behavior. In practice, finding the hidden
connections in any organization helps people to work together and share
social resources to achieve common goals. SmallBlue, is an info-social
sensing, analysis and visualization system designed to unlock this valuable
collective intelligence without explicit human involvement. It has been
deployed within IBM in over 70 countries for four years, and inferred the
social networks of 400,000 employees. It has successfully fostered
collaborations in employees' social networks, and it is currently being
extended to apply social network analysis in cyber-security and smarter
commerce.

This talk introduces the recent developments of SmallBlue system. First, I
describe the design of SmallBlue and how it is being used to help
information workers to find experts and manage their social capital. Next, I
discuss SmallBlue’s scientific advances. In particular, we study how
information spread in organizational social networks. We have also studied
how well a person’s attributes can be inferred from social neighbors in
networks, and how people’s interactions are influenced by culture.

Bio:

Dr. Zhen Wen is a research staff member at IBM T. J. Watson Research Center.
He received his PhD from University of Illinois at Urbana-Champaign in
Computer Science in 2004, and B.S from Tsinghua University in 1998. He is a
co-PI of the Social Network Analytics Research in IBM T. J. Watson Research
Center. He is leading both basic and applied research efforts on modeling
human behavior in social networks, which is sponsored by various funding
agencies. His past research at IBM includes context-sensitive visualization
for visual analytics. Specifically, he has worked on generating
visualization that is appropriate for user analytic tasks using contextual
cues. Zhen Wen has broad interests in data mining, signal processing and
human computer interaction with applications on social network analysis and
multimedia analysis. He has been serving as organizing committee member,
technical committee member at various IEEE/ACM conferences. He is an area
chair of social media at ACM conference on Multimedia 2012. His work
received 2011 Association of Information System ICIS Best Theme Paper Award,
the best paper award at ACM Conference on Intelligent User Interfaces (IUI)
2005, an IBM Research division award in 2005, and an IBM invention
achievement award in 2007, 2010 and 2011. Dr. Wen is a senior member of
IEEE.