This paper describes a study that examines the effect of cohesion-based feedback on a team members' behaviors in a global software development project. Chat messages and forum posts were collected from a software development project involving students living in the US and Mexico. Half of the teams in the project received feedback in the form of a graphical representation that displayed the group's cohesion level, while the other teams received no feedback. The nature of the group interactions as well as the linguistic content of such interactions was then analyzed and compared. Results from this analysis show statistically significant differences between the feedback and non-feedback conditions. More specifically, cohesion-based feedback had a positive relation to a team's total message count, response rate, and individual cohesion score. In addition, the analysis of linguistic categories showed that the most salient categories observed were related to words about time and work. Although the feedback system did not appear to affect individual performance, the findings suggest that the cohesion measure defined in the study is positively correlated to the task cohesion construct and is also related to individual and team performance.

Abstract-This paper describes the use of an automatic classifier to model group potency levels within software development projects. A set of machine learning experiments that looked at different group characteristics and various collaboration measures extracted from a team's communication activities were used to predict overall group potency levels. These textual communication exchanges were collected from three software development projects involving students living in the US, Turkey and Panama. Based on the group potency literature, group-level measures such as skill diversity, cohesion, and collaboration were developed and then collected for each team. A regression analysis was originally performed on the continuous group potency values to test the relationships between the group-level measures and group potency levels. This method, however, proved to be ineffective. As a result, the group potency values were converted into binary labels and the relationships between the group-level measures and group potency were re-analyzed using machine learning classifiers. Results of this new analysis indicated an improvement in the accuracy of the model. Thus, we were able to successfully characterize teams as having either low or high potency levels. Such information can prove useful to both managers and leaders of teams in any setting.

This paper describes a study that examines the effect of cohesion-based feedback on a team member's behaviors in a global software development project. Chat messages and forum posts were collected from a software development project involving students living in the US and Mexico. Half of the teams in the project received feedback in the form of a graphical representation that displayed the group's cohesion level, while the other teams received no feedback. The nature of the group interactions as well as the linguistic content of such interactions was then analyzed and compared. Results from this analysis show statistically significant d ifferences b etween t he feedback a nd n on-feedback c onditions. M ore s pecifically, cohesion-based feedback had a positive relation to a team's total message count, response rate, and individual cohesion score. In addition, the analysis of linguistic categories showed that the most salient categories observed were related to words about time and work. Furthermore, a comparison between feedback variables and type (i.e., positive and negative feedback) indicates that those individuals exposed to negative feedback had an increase in their communication pacing rates when exposed to positive feedback. Although the feedback system did not appear to affect individual performance, the findings s u g gest t h a t t h e c o h esion m e a sure d e fi ned in th is st ud y is positively correlated to the task cohesion construct and is also related to individual and team performance.

No abstract

No abstract