Collaborative Research: III: Small: Towards A Computational Foundation of Post-Pandemic Network Science of Team

Teams appear in almost any organization such as universities, corporations, and governments. The importance of teams is even more evident with the work practice has been evolving to a new hybrid mode – a combination of work in office and from home which inevitably changes how people collaborate as a team. Consequently, it presents new challenges to team collaborations, in that it increases difficulty of communications, stifles innovation, and affects collaboration. Despite an organization as well as an individual’s profound dependency on teams and the rapid changing landscape of team-enabled operations, computational models, algorithms and tools to optimize the team collaboration are lacking and lagging. To name a few, how to model the multi-channel, multi-platform team collaboration data? How to foresee the rising or the falling of a team at an early stage? How to form a high-performing team as well as to enhance the performance of an existing team? This project develops data mining models, algorithms and tools to optimize team collaboration facing novel challenges in a new hybrid working environment. It consists of three mutually complementary and synergistic research tasks. The first task models the raw team collaboration data to provide a worldview representation of how complex tasks are conducted by teams in multiple channels and platforms. The second task builds multi-task, multi-target predictive models to forecast the performance of a given team. The third task develops algorithms and tools to optimize teams. Specially, it develops data-driven approaches to form and enhance teams. Based on that, it develops reinforcement learning based methods to proactively optimize teams and game-theoretic methods to interactively optimize teams by incorporating user feedback. This project helps improve team efficacy, and optimize human resource allocation, thereby mitigating the challenges that the post-pandemic age has posed to the workforce. The project team actively seeks to engage under-represented students. The research outcome of this project is disseminated through publications, tutorials and open-source software. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.