Promises and challenges of learning analytics
I joined a MOOC (Learning Analytics and Knowledge – LAK11 with George Siemens, et al.) looking at learning analytics as a means to gather data about student and institutional performance and needs. This emerging research method has promises of reaching for far and wide for clusters of data and analyzing them in a systematic way, simultaneously, spontaneously, and immediately – thus, supporting data-driven decisions in the moment.
In my exploration for robust research methods to see if and how students are learning with technologies, I latched onto this course and upcoming conference.
In the initial week, preliminary readings were given (basic description and educational data mining). From what I have learned, this method has promises of gathering data from various systems – such as student database, social networks, online courses, institutional records, etc. The point is such data is already available and can further be merged and analyzed using numerous analysis methods, such as predictive and relational applications.
I had two reactions. First, what are the possibilities? Can we gather data about student attitudes and interests through social networking sites, their interaction in online learning platforms, their use of online library systems, etc. and blend the data to discover who they are, what they want, and how they learn along with their progress? In my opinion, this would require a paradigm shift in quantitative research thinking that insists on controlled variables and focused outcomes.
This leads to my second reaction: how will we be able to logistically mix the variables and constructs of the various data types? Will we be able to find a way to compare student preferences (from likes and dislikes on Facebook), with chosen modes and frequency of communication (email, LMS, smartphones), with grades and course evaluations?
This sort of blows my mind, but I am game to find out more. It really has potential to bring together hoards of data, presently available due to technology, and make sense of it.
However, I think we have a long tough job ahead of us to make this type of research analysis valid and reliable. But, I’m in!