Automatic Detection of Team Roles in Computer Supported Collaborative Work

Computer systems designed to support teamwork are environments that enable and enhance collaboration among users. These systems, named groupware, incorporate techniques that facilitate communication and coordination among team members to improve group performance. However, as not all team members ar...

Descripción completa

Detalles Bibliográficos
Autores: Garcia, Patricio, Balmaceda, José María, Schiaffino, Silvia Noemi, Amandi, Analia Adriana
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2013
País:Argentina
Institución:Consejo Nacional de Investigaciones Científicas y Técnicas
Repositorio:CONICET Digital (CONICET)
Idioma:español
OAI Identifier:oai:ri.conicet.gov.ar:11336/182717
Acceso en línea:http://hdl.handle.net/11336/182717
Access Level:acceso abierto
Palabra clave:COMPUTER SUPPORTED COLLABORATIVE WORK (CSCW)
GROUPWARE
TEAM ROLES
TEAMWORK
https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
Descripción
Sumario:Computer systems designed to support teamwork are environments that enable and enhance collaboration among users. These systems, named groupware, incorporate techniques that facilitate communication and coordination among team members to improve group performance. However, as not all team members are identical, it is important to study users' characteristics to build more productive teams. Team Roles Theory allows obtaining the best possible performance taking into account individual skills, combining the weaknesses of each role with the strengths of other team members. Therefore, it is essential in group formation to consider mind the role each member is capable of playing. Currently, each team member has to complete lengthy questionnaires to determine his team role. We propose an approach for automatic detection of team roles from the observation of user interactions in CSCW systems. Particularly, we apply Artificial Intelligence to obtain the team role that best suits a user's characteristics and behaviours. To achieve this, the performance of various classification algorithms was analyzed. The results show that our approach can detect team roles with high degrees of precision.