Making Project Team Recommendations from Online Information Sources

We are developing an Internet platform called MediaTeam that provides a marketplace connecting media content consumers to communities of media content creators. The platform is enabled by our method for automated assembly of virtual project teams. Media creators use the automated team assembler to quickly identify and team with collaborators. The team assembly platform factors in how the skills, work, and communication styles of team members complement each other into its team recommendation process. We are now testing the teaming and collaboration platforms with video creators and seek to launch by the summer. Virtual Teaming for Media Production Virkaz Technologies is developing tools to support collaboration between digital media creators. In conducting interviews of film and video professionals, we discovered widespread interest in the ability to form virtual, limitedduration project teams to perform the work associated with specific production projects. This ephemeral teaming is echoed by the nature of video production work, which is becoming increasingly decentralized, enabled by the spectrum of communication technologies available. Independent filmmakers, postproduction companies, and broadcast news organizations are increasingly turning to virtual collaboration and outsourcing to achieve production tasks, but team formation happens through word of mouth and is largely ad hoc. Virtual teaming for film and video is inadequately addressed by current virtual freelance marketplace platforms. We have constructed a platform called MediaTeam to provide this service. Copyright © 2011, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. This material is based upon work supported by the National Science Foundation under Grant No. 0944407. Background While the need to rapidly assemble, activate and manage virtual teams is acute in video production, these capabilities are increasingly important across the complete spectrum of modern work. Literature surveys of virtual teaming (Ebrahim, Ahmed, and Taha 2009) identify the use of virtual teaming across nearly every professional endeavor. The principle challenge is that of management: how does one manage roles, project deadlines and conflicts in teams that have minimal (if any) physical interaction? This argues for team selection platforms that factor in team cohesion. Yet, our analysis of existing platforms reveals little in the way of support team-specific construction, let alone the ability to factor in cohesiveness. Collaborator recommendation (McDonald, Ackerman 2000) and matchmaking (Diaz, Metzler and Amer-Yahia 2010) systems focus mostly on interest and skills selection and do not consider selection of complementary skills and work styles. Commercial outsourcing platforms (e.g. odesk.com) provide per-skill-set search and recommendation but do Figure 1:MediaTeam interface. User supplies requirements for virtual team and is presented with recommendations within budget and schedule constraints. not consider cohesion-supporting factors important in the selection of a team. The process of virtual team construction is therefore one in which an individual wishing to form a team describes the complementary skills necessary in team members, defines the budget and time constraints and then submits this description to a system which then returns dossier of individuals recommended for the team, giving consideration to the skills, communication styles, and experiences of the team members. MediaTeam automates this process by running team construction algorithms upon semantic networks derived from profession-oriented websites and social networks.