The relationships among big data, learning analytics, & personalized learning

How large do datasets need to be in order to support meaning learning analytics in a personalized learning system?

I think the size of the data set is not as crucial as understanding the implications for accuracy that more or less or varied data points supply. What is the data providing in its massive or limited volume? From a K-12 assessment point, are we pulling data from a homogenized assessment that skims the surface of the depth of knowledge? Or, are we pulling data from an adaptive assessment system that, with each incorrect response drills deeper into understanding by assessing for misconceptions?

 Interoperability between learning systems widens the capability for data procurement, but if that data is not aligned with the same set of standards, you can make inaccurate determinations. A simple example of this is the confusion that can happen when Texas educators try to translate student data from assessments built around Common Core standards and then respond to the data using TEKS (Texas Essentials Knowledge and Skills)-aligned learning resources.  The reliability of that data, no matter how large the set, is threatened because the response to that data is misaligned. 

Discuss the relationships among big data, learning analytics, and personalized learning.

Personalized learning environments offer adaptability to learner style and learner progression. If working correctly, the relationship between big data, learning analytics, and personalized learning is a cyclical relationship- each informing the other. Through a focus on real learning data, we remove cardiac data from the learning environment- meaning we remove the assumption that is influenced by the learner and teachers’ emotions and replace it with evidence-based initiatives for progress in learning. 

I would be remiss if I did include the following quote in my discussion response today:

“But I wouldn't want to be limited only to what a machine suggests for me. If it's central to my experience, if I'm categorized in a certain way and pushed down a certain path, it could make a much worse experience for me. The machine could have students avoid things they might have been interested in (Levinson, 2013)."

With the fear taking over educational institutions over the use of AI and learning analytics at all, I think this quote brings it into perspective that a holistic approach, which includes human observation, will always be an essential element in a well-rounded education.  I think we are still working through figuring out how that scales down to the most intimate educational settings.

Reference

Levinson, M. (2013). Personalized learning, big data and schools. Edutopia. https://www.edutopia.org/blog/personalized-learning-big-data-schools-matt-levinson