Knowledge co-construction and initiative in peer learning interactions

Peer learning has been shown to be an effective mode of learning for all participants. However the study of peer learning from a computational perspective is still in the early stages. In this research, I developed a computational model of peer learning and embedded this model in a peer learning agent. To endow the agent with appropriate behaviors, I undertook an extensive corpus analysis to identify correlates of knowledge co-construction and found that linguistically based initiative shifts seem to capture this notion of collaborative construction. The results of this analysis were incorporated into KSC-PaL, an artificial agent that can collaborate with a human student via natural-language dialog and actions within a graphical workspace. Evaluations of KSC-PaL showed that the agent was able to encourage shifts in initiative in order to promote learning and that students learned using the agent.