This is a research project supporting a new model of Computer Supported Collaborative Learning (CSCL) that combines the advantages of game based learning with problem based learning. Good game based learning environments combine rich scenarios with engaging activities to serendipitously provide student learning. These learning environments also provide an opportunity for players to collaborate in reaching their game goals. Good problem based learning environments provide support for the solution of complex and ill-structured problems. The combination of these two types of learning environments promises to provide the engagement and richness of game based learning with the support environment to engage students in authentic science. Both of these environments are computer based so the actions and interactions of the students and teachers are captured for analysis. Applying learning analytics to the captured data provides information on student learning for the teacher, provides learning information to the student for self-reflection and improved learning, and provides information for the system designer to improve the effectiveness of the new CSCL environment.
The scientific problem domain is environmental science for middle school students. The CSCL environment is a game based learning environment that incorporates problem based learning. The interaction between the CSCL environment and the student is enhanced by the collection of data on the student based on cognitive, affective, and metacognitive states that are inferred using artificial intelligence technologies. Specific strategies are employed to help students construct explanagions, reason effectively, and become self-directed learners. Key outcomes of the project include a model of collaborative scaffolding for game based learning that is usable in classrooms to help students learn STEM content and learning analytics designed to support the teacher in the roles of guide and collaborator. A goal of the project is wide dissemination of the CSCL system.
This work is supported by the National Science Foundation, NSF grants DRL-1561655 and DUE-1561486