Automatic Detection of Team Roles in Computer Supported Collaborative Work

Abstract

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.

Mining Associations Between Collaborative Skills and Group Roles in Collaborative E-Learning Environments

“…Knowing collaborative skills associated with every group role would make easier for CSCL teachersthedecision-makingandplanningwithregardtothecompositionofthegroups.Forexample, supposethatalearningactivityrequiresgroupswheretheShaper,PlantandImplementerrolesare manifested.Basedonknowledgeofstudentsfeatures(forinstance,collaborationskills)ateacherwould distributestudentsingroupwithsomecertaintythatthestudentswillassumetherequiredroles.The knowledgeoffeaturesofstudentscouldcomefrompreviousexperienceswheretheteachertaught thesamestudentsortheapplicationofautomatictechniquestoanalyzethelogofonlinecollaborative interactionsinsubjectswheretheteacherwasnotnecessarilyincharge.Inscientificliteraturethere areresearchworksthatprovethatskillsofapersoncanbeidentifiedautomaticallythroughsentence openers (Costaguta, García, & Amandi, 2011) or even applying text mining (Santana-Mansilla, Costaguta,&Missio,2014). While the approach of García et al (2013) only works with semi-structured interfaces (sentenceopener),associationrulesofFigure5canbeusedforanalyzinginteractionthrough semi-structured interfaces and non-structured interfaces. In last case one should apply some technique(suchastextmining)inordertoidentifyrolesandcollaborativeskillsinfreetext interactions.…”

“…In last case one should apply some technique(suchastextmining)inordertoidentifyrolesandcollaborativeskillsinfreetext interactions. Another difference with García et al (2013) is the number of roles that can be detected.TheapproachofGarcíaetal. ( 2013)allowstherecognitionofjustoneroleplayedby eachgroupmemberduringainteractionsession,yetassociationrulesdiscoveredinthisresearch workcanbeusedtorecognizeseveralrolesplayedbythesamestudent.Individualsarenotpurely describedbyjustastaticandstrictrole.Despitethefactthatonemayhaveamostpredominant roleduetotheindividual'spersonality,individualsshowarichvarietyofbehavioralpatterns dependingoncircumstances (Ounnasetal.,2009).…”

Arquitectura Basada en Roles Aplicada en Equipos de Fútbol de Robots con Control Centralizado

“…También permiten a los agentes especializarse en comportamientos en los que son responsables y reducen el número de agentes que compiten por una tarea en particular (Campbell and Wu, 2011). Al nivel de diseño de arquitecturas, se ha mostrado que equipos basados en roles permiten obtener un óptimo rendimiento, dadas las habilidades individuales de los agentes, compensando las debilidades de los roles con las fortalezas de otros miembros del equipo (Garcia et al, 2013). Arquitecturas basadas en roles han sido utilizadas en diferentes aplicaciones mostrando adaptabilidad y una adecuada respuesta en diferentes ramas de la ingeniería, por ejemplo en ingeniería de software, para el diseño y análisis de programas orientados a objetos (Baldoni et al, 2008), o definiendo la interacción entre objetos proveyendo una abstracción entre clases y roles (Kendall, 2000).…”

Assembly oriented control algorithm of collaborative disassembly and assembly operation in collaborative virtual maintenance process

“…Collaborative virtual maintenance (CVM) that developed mainly based on virtual maintenance (VM) [1,2] and computer supported cooperative work (CSCW) [3][4][5][6] provides an appropriate and efficient approach to collaborative maintenance training of the large-scale and complex equipment. The studies on key techniques of CVM and the developments of training systems are gradually concerned by many researchers [7][8][9][10][11][12][13].…”