On the efficiency of online social learning networks

A social learning network (SLN) emerges when users exchange information on educational topics with structured interactions. The recent proliferation of massively scaled online (human) learning, such as massive open online courses (MOOCs), has presented a plethora of research challenges surrounding SLN. In this paper, we ask: how efficient are these networks? We propose a method in which the SLN efficiency is determined by comparing user benefit in the observed network to a benchmark of maximum utility achievable through optimization. Our method defines the optimal SLN through utility maximization subject to a set of constraints that can be inferred from the network, and given multiple solutions searches for the one closest to the observed network so as to require the least amount of change to user behavior in practice. Through evaluation on four MOOC discussion forum data sets and optimizing over millions of variables, we find that the SLN efficiency can be rather low (from 76% to 90% depending on the specific parameters and data set), which indicates that much can be gained through optimization. We find that the gains in global utility (i.e., average across users) can be obtained without making the distribution of local utilities (i.e., utility of individual users) less fair. We also propose an algorithm for realizing the optimal network through curated news feeds in online SLN.