Big data and learning analytics would transform education, much more than MOOCs.
To what extent is big data (big-data-not-moocs-will-revolutionize-education) the solution to higher education?
Big data in the online learning space will give institutions the predictive tools they need to improve learning outcomes for individual students. By designing a curriculum that collects data at every step of the student learning process, universities can address student needs with customized modules, assignments, feedback and learning trees in the curriculum that will promote better and richer learning.
In this post on learning analytics:
They found that people take classes or stop for different reasons, and therefore referring globally to “dropouts” makes no sense in the online context. They identified four groups of participants: those who completed most assignments, those who audited, those who gradually disengaged and those who sporadically sampled. (Most students who sign up never actually show up, making their inclusion in the data problematic.) The point of all this is not simply to record who is doing what but to “provide educators, instructional designers and platform developers with insights for designing effective and potentially adaptive learning environments that best meet the needs of MOOC participants,” the researchers wrote.
For example, in all three computer science courses they analyzed, they found a high correlation between “completing learners” and participation on forum pages, suggesting a positive feedback loop: The more students interacted with others on the forum page, the better they learned. This led the researchers to suggest that designers should consider building other community-oriented features, including regularly scheduled videos and discussions, to promote social behavior.
These findings were revealed in our earlier researches in MOOCs and so these latest researches were reinforcing what most of the researches have found, in particular the engagement and interactivity of learners as a critical success factor in MOOCs.
As I have shared in my previous posts, there are assumptions about design of curriculum, where students’ motivation and learning could be accurately traced, assessed and evaluated with the clicks of videos, engagement with discussion boards, and answering those “multiple choice questions” or assessment tasks. To some extent, big data could provide some clues as to students’ skills and interests, and their degree of connections with others, resources and networks, the connectivity as one could define. There are questions that still need to be addressed though, as each individual has his or her own learning style and motivation, which could not be predicted simply by tracing using the big data, especially when they are merely visitors to the sites, and have weak links to others in the networks or social media.
Trying to track down students’ attendance may be one way to gauge their engagement, but then again this requires enormous amount of follow up work and intervention from the professors or institutions in order to develop those customized units, assignments, and feedback.