As Jonathan Kantrowitz summarizes, "Researchers tracked 250,000 students from nearly every country in 250 massive open online courses (MOOCs) over 2 1/2 years in the study." What they found was that interventions that appeared to work in the short term were much less effective in the long term. The researchers also "found minimal evidence that state-of-the-art machine learning methods can forecast the occurrence of a global gap or learn effective individualized intervention policies." None of this especially surprises me (and I would venture that a similarly-sized study in traditional classrooms would yield a similar result). As the authors say, "The kind of large-scale research that is needed to advance this work is not well-represented in the dominant paradigm of experimental educational research." As the authors suggest, "Context matters... In a new paradigm, the question of 'what works?' would be replaced with 'what works, for whom, right here?'"
Today: 4 Total: 94 [Direct link] [Share]
