A Cognitive Load View And Empirical Test Of Collaboration Network Structure Versus Learning Rates In New Software Development

This study explores whether characteristics of the collaboration structure in software development teams affect development learning rates, with a secondary goal of testing product complexity as a moderator. We develop suitable hypotheses under the theoretical lens of cognitive load theory. The empirical study uses archival data on an ordinary least squares model to find significant associations between collaboration structure, product complexity and the learning rates exhibited by 230 development teams producing open source software. Results show two distinct subgroups of projects: The first subgroup exhibits an average 78% learning rate, and the other subgroup “unlearned”, i.e., productivity deteriorated over time instead of improved. In the learning subgroup, collaboration network density negatively impacted learning, while product complexity interacted with collaboration network centralisation and boundary spanning activity. In the unlearning subgroup, only network density impacted learning rates and no moderating effects were found. Practical implications and future opportunities for research are discussed.