Social Learning Network (SLN) is a type of social network among students, instructors, and modules of learning. Recent innovations in online education, including open online courses at various scales, in flipped classroom instruction, and in professional and corporate training have raised interesting research topics concerning SLN. Some of these include: prediction of assessment performance and dropoff rates, recommendation of courses/topics and study partners, personalization of the learning experience, visualization, and incentivization.
We are continually investigating SLN by collecting, analyzing, and leveraging data to design new systems. For example, in summer 2013 we conducted a large-scale statistical analysis of MOOC in which we determined course factors that are significantly correlated with participation dropoff rates. More recently, we have been investigating techniques for student proficiency modeling, using machine learning techniques such as regression/classification and matrix factorization. In particular, we are quantifying the improvement obtained by incorporating SLN data into these models. We also have developed two learning technology systems to support SLN research: 3 Nights and Done, an open online education platform, and the Mobile Integrated and Individualized Course (MIIC), a platform that integrates all modalities of learning into a single mobile app and personalizes the learning experience for each individual student.
For more information, feel free to email Christopher Brinton at "cbrinton [at] princeton [dot] edu".
C. Brinton, M. Chiang. 'Social Learning Networks: A Brief Survey'. 48 Annual Conference on Information Science and Systems (CISS), Mar. 2014. [pdf]
C. Brinton, M. Chiang, S. Jain, H. Lam, Z. Liu, F. Wong. 'Learning about social learning in MOOCs: From statistical analysis to generative model'. Accepted for publication, IEEE Transactions on Learning Technologies, July 2014. [pdf]