Ubiquitous Learning and Instructional Technologies MOOC’s Updates

Essential Peer-Reviewed Update #3: Big Data and Education

Take one aspect of big data in education. How does it work? What are its effects?

Aspect: One aspect of big data is the unstructured nature of some of the data that can be collected in a technology-mediated environment such as Learning Management systems (DiCerbo & Behrens, 2014). Instructors in an online environment focus on the data that emerge from formal tests to assess student outcomes; however, there is a well of other types of data that can be collected, which may not be immediately apparent but which can be equally if not, more useful. There is a solid justification for tapping into this type of data. It can decrease over-reliance on testing data which is often expensive, time-intensive and burdensome (DiCerbo & Behrens, 2014). Cope and Kalantis (2016) give examples of unstructured big data such as timestamps, keystrokes, and clickstreams which can show patterns in engagement, types of activity and social interaction trends.

How it works: These types of data do not rely on a prearranged data model such as an acceptable move in a learning game. The possible use of each data point is thus not evident right away. For these data points to be meaningful, the computer must be trained by comparison to activity patterns based on what a human, such as an expert, has judged as indicative of success.

Effects: The collection and analysis of this type of data bring about many benefits. More responses can be scored at one go, more patterns can be discovered which can show evidence of learning, and quicker feedback can be provided (DiCerbo & Behrens, 2014). Another somewhat controversial benefit is the ability to “profile” a learner. Although this can help instructors in predicting learning outcomes or provide more guidance for success in a course, it ignores some “contextual” factors that may have hampered learning. We are currently in the middle of a pandemic…if a close one gets sick, this invariably affects the learning process. How is the learner profiled in that case? I wonder how to make assessments based on this type of data more contextual.

Click here for a video on how big data is making education smarter here 

References

DiCerbo, K. E., & Behrens, J. T. (2014). Impacts of the digital ocean on education. London, UK: Pearson

Cope, B., & Kalantzis, M. (2016). Big Data Comes to School: Implications for Learning, Assessment, and Research. AERA Open, 2(2), 1-19. https://doi.org/10.1177/2332858416641907