What are Learning Analytics?


Learning analytics refers to the interpretation of a wide range of data produced by and gathered on behalf of students to assess academic progress, predict future performance, and spot potential issues. Data are collected from explicit student actions, such as completing assignments and taking exams, and from tacit actions, including online social interactions, extracurricular activities, posts on discussion forums, and other activities that are not typically viewed as part of a student’s work. The goal of learning analytics is to enable teachers and schools to tailor educational opportunities to each student’s level of need and ability. Learning analytics promises to harness the power of advances in data mining, interpretation, and modeling to improve understanding of teaching and learning, and to tailor education to individual students more effectively. Still in its very early stages, and not yet at the stage where it is practical to talk about implementation in schools, learning analytics is an emerging scientific practice that hopes to redefine what we know about learning by mining the vast amount of data produced by students in academic activities.

INSTRUCTIONS: Enter your responses to the questions below. This is most easily done by moving your cursor to the end of the last item and pressing RETURN to create a new bullet point. Please include URLs whenever you can (full URLs will automatically be turned into hyperlinks; please type them out rather than using the linking tools in the toolbar.

Please "sign" your contributions by marking with the code of 4 tildes (~) in a row so that we can follow up with you if we need additional information or leads to examples- this produces a signature when the page is updated, like this: - Larry Larry Jan 25, 2011

(1) How might this technology be relevant to the educational sector you know best?

  • The vast majority of courses in higher/tertiary education environments includes at a minimum an online component. We have largely ignored the capabilities that interaction with digital information necessarily creates a digital trail behind it and an opportunity to track characteristics of access and interaction with them. This ability if actively pursued allows for the potential to deeply personalise learning to the student, initially by categorising students and associating learning materials with particular groups, and ultimately using much more sophisticated analyses of student performance and interaction patterns to adapt learning materials to the needs of particular students. - Phillip.Long Phillip.Long Aug 20, 2013
  • Another element of interaction with digital material is the opportunity to track and measure learner interaction with feedback. To date this has largely been a 'black hole' in learning systems. We give feedback, but we have little data on how students use feedback. Indeed a fair hull hypothesis is, once you provide the grade or score to an assessment, nothing else is attended to. The implication were this to be true is faculty shouldn't waste their time providing it. Naturally we hope that's not true, but in reality we don't "know" that. Capturing learning interaction with assessment feedback opens up a line of inquiry into how feedback can/should be structured? What constitutes 'good' feedback? What format is optimal (text, graphics, animation, voice, video ???) - Phillip.Long Phillip.Long Aug 20, 2013
  • I'm with Phil on this. I think the notion of learning analytics around feedback is quite important. It isn't just about making a system better, but understanding how people work within that system. I think learning analytics is probably the most rapidly moving area across all digital education.- klopfer klopfer Aug 21, 2013 - Zeinab.El.Maadawi Zeinab.El.Maadawi Sep 3, 2013

(2) What themes are missing from the above description that you think are important?

  • The goal of learning analytics needs to be broadened and centered on the learner. Informing the instructor is valuable. Providing actionable feedback to the learner so that their decisions about how, what, and when they study is priceless ;) Therefore the goal of learning analytics, and what distinguishes it from 'academic analytics' is the focus on providing the learner with feedback on their learning in as near real-time form as possible so that they may make informed decisions about their learning during the course of instruction within a class. - Phillip.Long Phillip.Long Aug 20, 2013 I agree on that - mohamed.jemni mohamed.jemni Sep 1, 2013
  • A major future opportunity afforded by learning analytics is predictive intervention, offering a student in week two of a course suggestions for study, tutoring, or alternative options based on stochastic models of behaviour derived from near population level data sets, and associated with a meaningful probability of predicated outcome. - Phillip.Long Phillip.Long Aug 20, 2013 - Zeinab.El.Maadawi Zeinab.El.Maadawi Sep 3, 2013
  • One challenge with learning analytics is that they can potentially be used to hyperpersonalize learning -- ignoring the fact that learning is also a social pursuit. The best possible learning pathway for a person needs to take into account those interactions with others. - klopfer klopfer Aug 21, 2013 - Zeinab.El.Maadawi Zeinab.El.Maadawi Sep 3, 2013 agree - roc roc Sep 2, 2013
  • Agree with Klopher. Data is important. We need to keep one-to-one feedback, too, in other words--balance. Students receive scores, numbers corresponding to some type of standard and other stats to improve their learning. Human interaction is key. Seems we have a lot of data/communication, yet, we still remain misunderstood. Just an opinion. - michael.lambert michael.lambert Sep 2, 2013
  • Also in a distributed online learning environment, possibly using several resources and tools, will be important to have analytics incorporated in order to get usage patterns and learning impact correlation from a tool-based heterogenous learning environments. - roc roc Sep 2, 2013
  • To further expand upon what roc said. In research we have been doing on how students navigate digital learning materials we are finding that some groups of students heavily rely on external resources that they discover outside the instructor provided materials. Failing to account for this in the development could lead to significant miscalculations in the value of provided materials. A student could not interact with any provided resources and do well on evaluations, or a student could interact with all the provided materials, but turn to external materials which provided them the most benefit, and neither would be adequately explained in the analytics. Having an understanding the questions that can not be answered will be equally important to knowing what you can answer. - alanwolf alanwolf Sep 2, 2013

(3) What do you see as the potential impact of this technology on STEM+ education?

  • Learning analytics is a revolutionary to formal educational settings as "big data" is to genetics and pharmaceutical research - i.e., it is enormous! It forces a number of the changes and challenges longstanding practices in teaching and learning. Academics would have the potential to see a real-time snapshot the the learning progress of their students allowing them to tailor their activities accordingly. Students could have dashboards that calculate their work during a give day of the week and looking ahead providing a set of options for organising their study, monitoring their progress and managing their allocation of effort.
  • New graduate programs in learning analytics are springing up like mushrooms in a forest. Columbia, Carnegie Mellon, Stanford and others are all recognising the potential and demand for trained research practitioners in learning analytics and creating focused programs for them at the master's level. - Phillip.Long Phillip.Long Aug 20, 2013 - Zeinab.El.Maadawi Zeinab.El.Maadawi Sep 3, 2013

(4) Do you have or know of a project working in this area?

  • UniSA in Adelaide Australia is engaged in the development and integration of learning analytics tools
  • UTS (University of Technology Sydney) has put together the Advance Analytics Institute to support the development and deployment of analytics techniques in education and related disciplines.
  • The University of Queensland has embarked on a Learning Analytics Initiative in parallel with it's engagement with edX through formation of UQx
  • Stanford Univeristy has formed a learning analytics research group called Lytics Lab run by Roy Pea.
  • Carnegie Mellon has incorporated learning analytics into their Open Learning Initiative
  • Columbia University has established the Masters In Cognitive Studies In Education, Focus In Learning Analytics led by Ryan S.J. Baker.
  • The Open University has been a strong contributor to learning analytics with project such as Cohere, Enguiry Blogger and others. They have a Ph.D. program with opportunities for those interested in Learning Analytics for Learning Power, through their Knowledge Media Institute, led by Simon Buckingham-Shum and Rebecca Ferguson.- Phillip.Long Phillip.Long Aug 20, 2013
  • University of Wisconsin System is currently engaged in a multi-year analytics program called S3 - Student Success System. - alanwolf alanwolf Sep 2, 2013

Please share information about related projects via our NMC Horizon Report project submission form.