What are Learning Analytics?

Learning analytics is an educational application of “big data,” a science that was originally used by businesses to analyze commercial activities, identify spending trends, and predict consumer behavior. The rise of the Internet drove research into big data and metrics as well as the proliferation of web tracking tools, enabling companies to build vast reserves of information they could study and apply to their marketing campaigns. Education is embarking on a similar pursuit into data science with the aim of improving student retention and providing a high quality, personalized experience for learners. Learning analytics research uses data analysis to inform decisions made on every tier of the educational system. Whereas analysts in business use consumer data to target potential customers and personalize advertising, learning analytics leverages student data to build better pedagogies, target at-risk student populations, and assess whether programs designed to improve retention have been effective and should be sustained — outcomes for legislators and administrators that have profound impact. For educators and researchers, learning analytics has been crucial to gaining insights about student interaction with online texts and courseware. Students are beginning to experience the benefits of learning analytics as they engage with mobile and online platforms that track data to create responsive, personalized learning experiences.

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 Feb 8, 2012

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

  • add your response here
  • For several years we have had a data warehouse and staff has stuggled with the use of student data. Learning analytics could be our next step, to train teachers to use the tools available to personalize student learning.- jmorrison jmorrison Jan 27, 2014
  • Also, see note under Machine Learning.- jmorrison jmorrison Jan 29, 2014
  • Looking through the various categories, I didn't see anything regarding online assessments. This seems like the closest fit. The CCSS online assessments are shifting toward performance and formative assessments - ryan.tomaps ryan.tomaps Jan 30, 2014
  • Wearable technology and learning analytics are obviously linked. Jawbone and Nike+ Fuel Bands provide immediate feedback to the user. The user can choose to make adjustments. How can we design portions of our learning environment to do the same. Some companies create dashboards that provide learning analytics for students and parents. - michael.lambert michael.lambert Feb 2, 2014
  • The application of Learning Analytics is now also being challenged by 'real time learning' projects. There is a growing use of learner response platforms that enable educators to adjust their delivery/activity during class to provide better understanding for the learners. Clicker technology is one such development. Moving away from the Q and A/ multiple choice style format clicker technology was originally designed to a realtime evaluation of student understanding of a concept- 'Indicate, using Y or N on the clicker, how much you are understanding, as I explain these elements of digital citizenship. You can 'vote' as often as you want.' (Explains the teacher) From this the teacher then monitors the trends in hwo the students are responding. Polleverywhere has readily been used to this end, as well by myself, to indicate collective understanding on a topic, whilst it is being taught. - mtaylor mtaylor Feb 2, 2014
  • As a classroom teacher, I see this as the most relevant idea for my practice. I regularly use clickers with my students to get real-time data and change my delivery. Both my students and I see the benefits of changing instruction to clear misconceptions right away or even "move on" more quickly than anticipated. It also allows me to see where individual students are struggling. My district is also moving towards more frequent online-based assessments (STAR) as screening tests for students. This is very basic, but gives teachers adequate data to see strengths and areas of growth for each student. I also think as we move forward with CCSS learning analytics will be very relevant. - cbsteighner cbsteighner Feb 3, 2014
  • Learning Analytics/ Educational Data Mining is certainly an upcoming technology with a huge potential in K12 education. It has shown its value in the retail area but gonna take some time to adopt it in education - claus.gregersen claus.gregersen Feb 5, 2014
  • Learning Analytics adds new potential to formative assessment and personalization of learning. We are still in early days, and many systems need a coherent approach with both national agencies, researchers and industry to find the models suitable for each individual system - oysteinjohannessen oysteinjohannessen Feb 6, 2014
  • New computer based assessment methodologies enable knowlege to be understood at a larger scale with fewer resources and lower intrusion on instruction. Technology can now make a students thought processes more visible. This in turn is more useful for teachers in formative assessment to allow changes or personalized instruction. The date also can becom more useful at the macro or policy level to guide large scale assessment programs. - jon.k.price jon.k.price Feb 6, 2014
  • Of all of the topics presented here on the wiki, this is the one that is most potentially transformational for learning imho. Eventually, this is what will make lots of the very expensive investments in edtech, which have to date demonstrated minimal impact on student learning, finally worthwhile. We just have a ways to go up the learning curve before we get there, however. - mtrucano mtrucano Feb 6, 2014
  • I love the conversation related to this thread, and like my colleagues believe that it holds enormous potential for solving the teaching riddle for reaching kids and truly changing their learning paths. - kstubbs kstubbs Feb 7, 2014- digitalroberto digitalroberto Feb 9, 2014
  • Whilst this has not yet taken off in many of the developing countries, it will more than likely become more integrated into ICT in Education plans in the near future (over the next five years). Governments that I am working with are considering assessment rubrics and are receptive to learning more about learning analytics and their transformative potential. - shafika.isaacs shafika.isaacs Feb 9, 2014
  • As with nearly everyone else, I see this as the next enormous impactful technology to the classroom. When taken hand-in-hand with BYOD/1:1 the ability to accurately target students with the instruction, assistance, counseling, or challenge they need is breathtaking. As BYOD/1:1 becomes increasingly prevalent so too shall learning analytics; the proliferation of devices or students is really going to drive this, for in a classroom with little technology, learning analytics can only be so useful due to lack of data. There is a huge amount of training needed for all parties, legislators, board, cabinet, administration, teachers, parents and students as we begin to implement analytics. I'm impressed with how useful the simple analytics are in our SIS and LMS services to begin assisting students.- digitalroberto digitalroberto Feb 9, 2014

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

  • - bobmoore bobmoore Feb 4, 2014There are separate topic here focused on the visualization of data and information. Learning Analytics on their own are great, but is the consumers (students, teachers, principals, district leaders, parents, policymakers) don't really understand what they are being told, analytics have limited value. We need to embrace new ways of looking at data.
  • One concern, perhaps not as much "missing" as is the way "big data" is illustrated - as a consumer sales & marketing approach. This illustration depicts a suspicious corporate approach that would surely affect public confidence. The second concern would be data confidentiality, privacy, security and access. - jon.k.price jon.k.price Feb 6, 2014
  • Lots of folks touched on missing elements in their answers to Q1. Wearables, etc. I'd also connect this to the work that is being done by SETDA to offer unification around tagging of learning objects and resources so that it is easier to point kids toward common learning objects based on their assessments. - kstubbs kstubbs Feb 7, 2014
  • As alluded/mentioned above, there may be a difference between data mining and learning analytics, as terminology evolves. It may be helpful to distinguish the two: http://www.edudemic.com/a-look-at-big-datas-plan-to-personalize-your-education/ - anton.inglese anton.inglese Feb 8, 2014
  • Implications of the data that is gathered through 1 to 1 device deployments are huge. If you know what students read, what they highlight, how long they take to solve problems, what sequence they are doing their work...etc has big implications about usefulness toward personalized learning. Future technologies that will become ubiquitous including active stylus (allows for detail/paper-like writing) and eye tracking (with word per word resolution) will enrich analytics opportunities with rich sources. - russell.beauregard russell.beauregard Feb 10, 2014

(3) What do you see as the potential impact of this technology on teaching, learning, or creative inquiry?

  • Improving learning at the time of learning is incredible powerful and efficient. Using real time learning analytics such as clickers/polleverywhere will allow teachers to adjust content and activities as the students are learning, rather than waiting for a reflective piece or evaluation at the end. It also allows for anonymity. Students, particularly here in SE Asia, will not indicate they don't understand because of culture of saving face and agreeing with the teacher.
  • The ability for each student to receive immediate feedback and for teachers to personalize instruction for each learner. I'm interested in seeing how learning analytics works with CCSS. - cbsteighner cbsteighner Feb 3, 2014
  • - bobmoore bobmoore Feb 4, 2014I have seen first-hand how analytics can be used in a school district. Predicative analytics are most powerful. Of course, all the analytics in the world have limited usefulness of educators don't know how to change instruction.
  • On the positive side, I presented formative and summative assessment opportunities. On the negative side, current public confidence and concern over digital common core assessments relate to both who gets/has access to the data, but also how curriculum, assessments or unit plans that are created by individual teachers may be absorbed by the owner of the data platform only to be used for profit later. - jon.k.price jon.k.price Feb 6, 2014
  • For me, it all comes back to personalized learning and getting away from the continued factory model of teaching and learning. - kstubbs kstubbs Feb 7, 2014

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

  • ISS International School Singapore teacher professional development session on ESL teaching strategies (Using Polleverywhere).
  • Hong Kong Academy project into understanding student learning (using Mimio Clicker) - mtaylor mtaylor Feb 2, 2014
  • The Learning Genome Project. - cbsteighner cbsteighner Feb 3, 2014
  • Again, the Intel education division is exporing technology opportunities for assessing 21st century skills through the ATC21S project:http://atc21s.org/ and the Collaborative Assessment Alliance:

Please share information about related projects in our Horizon Project Sharing Form.