ExpertNet : Searching Collaborative Social Networks

Motivation

In modern life, due to the increasing complexity of tasks and accuracy of labor division, the situation that one problem can be solved by a single person has become history. Instead, problem resolution is the result of dynamic social collaboration of multiple experts toward a unified goal. With the emerge of Web 2.0, such collaborations become inter-disciplinary and global.

Understanding experts' skills, influence and their interactions in a collaborative social network that drives problem-solving processes is the key to find the right experts and thus to accelerate problem resolution and decision making. However, studies of collaborative innovation networks have been so far limited to be qualitative, based on questionnaire and surveys, which are subjective, inaccurate and costly.

 

Approach

In this research, we are developing computational foundations and quantitative frameworks to model, optimize, and search collaborative social networks to expedite problem-solving and to enhance team collaboration. Specifically, we address the following problems:

  1. Modeling Collaborative Social Networks according to Historical Interactions
  2. Quantitatively Profiling Experts and Relations in the Networks
  3. Optimizing Problem Routing for Expert Search in the Networks

 

Publications

 

People

Faculty:

            Yi Chen < yi.chen at njit dot edu >

Students:

            Brian Ackerman < bjackerm at asu dot edu >

            Yunzhong Liu < yunzhong dot liu at asu dot edu >

Alumni:

            Peng Sun, Yichuan Cai

Collaborators:

            Shu Tao (IBM T. J. Watson Research Center)

            Xifeng Yan (UCSB)

 

Acknowledgement

This project is supported by an IBM Faculty award.