What is Learning Analytics?

Learning analytics is education’s approach to “big data,” a science that was originally leveraged 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 leverage in 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 Oct 30, 2011

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

  • Learning Analytics will be the key when we think of more personalized learning processes and experiences. - jochen.robes jochen.robes Oct 13, 2013 - paul.signorelli paul.signorelli Oct 21, 2013
  • Learning Analytics(LA) is related with Machine Learning (ML). In my experience, LA is (and will) provide insights to every actor in higher ed (students, professors, parents, advisors, etc..) helping them to take better decisions. Predictive Learning Analytics is particularly useful because, bases on several ML and statistica techniques, allows actors to get insight on the enormous amount of data that we are capturing now. Students can get some probability distribution about their future success taking a particular course, based on their characteristics (demographis, previous courses, professors, etc..). Professor can get insight on the probability distribution of success (or failure) of their current students (in a particular course) such that they can adjust their material for that course. Advisors can help students to decide what courses to take. Universities can decide which aspirants to accept as new students and the same techniques can be applyied for selecting new professors. And of course, new Learning Managment Systems with LA capabilities can help teachers to adapt their material course such that they fit to their particular students. (- jreinoso jreinoso Oct 14, 2013)
  • Learning analytics has huge growth potential in online learning in public 4-year institutions. Online learning environments capture mountains of data, which can be managed, filtered, sorted for research, evaluation, and improvement. This has potential to impact teaching practices online and personalized learning for students. - Jolie Jolie Oct 16, 2013 Agree, and believe the same can be said for adult learning in a variety of other formal and informal settings through workplace learning and performance (staff training) efforts. If learners benefit from this through their higher education experiences, they may expect to see it continue in other lifelong learning efforts.- paul.signorelli paul.signorelli Oct 21, 2013
  • Learning analytics will become a primary tool for decision making for institutions in an increasingly competitive market. The use of analytic tools to be able to find trends in student information systems, learning management systems, and course evaluation systems will drive how institutions create and reformulate programs, courses and discipline offerings. - joseph.cevetello joseph.cevetello Oct 24, 2013

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

  • As there are data in learning since the first days of the computer and local networks, the huge gap between learning analytics concepts and the small number of software solutions and institutions practicing analytics is still quite astonishing.
  • I think that it must be clarify that Learning Analytics involves Machine Learning Algorithms and/or Statistical Analysis (- jreinoso jreinoso Oct 15, 2013)
  • Essential to the growth of learning analytics and for it to reach its fullest potential, it will need to incorporate some kind of algorithm for analyzing online text in discussions, blog posts, social media, etc. for evidence of critical and creative thinking for example.- Jolie Jolie Oct 16, 2013
  • I think there are two kinds of Learning Analytics. First, there are analytics of a mass group of students. This can give feedback to the instructor in near realtime, allowing adjustments to the rest of the class. Ultimately though I don't think this will be of great impact as long as every student gets the same curriculum. The second kind of analytics is at the user level. By collecting data about each student, it will be possible to create adaptive learning systems. These will then personalize the learning experience to each student, thus allowing the most effective learning. - andrew.barras andrew.barras Oct 17, 2013 Very creative to think that a possible use of LA could be formative assessment data. Reflective practitioners would care about this kind of data. - Jolie Jolie Oct 20, 2013
  • Could this be the place to mention the new generation of technical interfaces like Tin Cap API to track learning? - jochen.robes jochen.robes Oct 21, 2013
  • An emerging trend to use learning/data analytics to analyse the performance of academics in relation to the educational value they add to student learning. This could also be taken higher to analyse the value added by programs, and institutions. - j.zagami j.zagami Oct 23, 2013
  • The connection between the ability to analyze big data sets through high performance computing and the ability to visualize this data in 3D and immersive environments. The ability to "see" and manipulate data in 3D will reveal an ability of insight not possible in 2D with such huge amounts of data.- joseph.cevetello joseph.cevetello Oct 24, 2013

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

  • Learning analytics hold a wealth of information about students - possibly more than they can know or voice themselves, but possibly also more than they would want to be known. While providing a highly effective tool for individual learner support, the application of learning analytics is a very sensitive issue that ideally requires a deep sense of trust between student and teacher (data protection issues left aside...). - helga helga Oct 12, 2013 important issue! - amichaelberman amichaelberman Oct 23, 2013
  • I see great impact even if it is not clear how we can put the learner in the drivers seat of learning analytics. Currently it seems mainly a promising market for software providers. - jochen.robes jochen.robes Oct 13, 2013
  • It will (is?) impact several actors in the higher education system helping them to take better decisions. Aspirants (new students) could be chosen based on their background (high school information, public available information as facebook or twitter, etc.). The same situation could apply for selecting new professors. Advisors could use this technology in order to provide better suggestions to their students about what courses to take. Students could choose courses based on successful probability distributions built using their background data. Head Departments could use this technology for helping them to decide which professor assign to which course based on the type of students that is taking it. Graduate students can be advice about extension courses that might help them in their careers. (- jreinoso jreinoso Oct 14, 2013)
  • This has potential to open up new ways to assess student learning and new ways for students to demonstrate understanding (i.e, knowledge gained, skills mastered, etc.). - Jolie Jolie Oct 16, 2013
  • There will be a lot of money thrown at this and a lot of companies starting up to provide this service. - andrew.barras andrew.barras Oct 17, 2013
  • It could enhance the learning experience and for all involved since it allows for in-the-moment fine-tuning for learners and learning facilitatators.- paul.signorelli paul.signorelli Oct 21, 2013
  • A possible negative impact is that we will choose instructional methods based on what generates the most data for analysis, rather than what appears to be most effective for student learning. - amichaelberman amichaelberman Oct 23, 2013
  • If administrators have the ability to measure and quantify outcomes, patterns, and processes they will not doubt attempt to base key decisions about the educational experience based upon metrics and numbers. This could be a great boon, but also a great disservice to education. Institutions will need to carefully balance their desire to measure, benchmark, and certify the learning experience while at the same time allowing for serendipity, happenstance, and unanticipated or unmeasurable activities that create a campus environment and culture.- joseph.cevetello joseph.cevetello Oct 24, 2013
  • Big Data Analytics will challenge the hegemony of traditional statistical analysis and the attempt to determine causality (Schoenberger and Cukier, 2013). Correlations will become more important, and research design will be less about hypothesis testing, and more about "seeing" what such large data pools reveal through manipulation (Scheoberger and Cukier, 2013). This will impact not just the decisions of those running our institutions, but the very core of the academic enterprise, how we conduct research and create and craft knowledge.- joseph.cevetello joseph.cevetello Oct 24, 2013

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

  • The most known project is Signals Project from Purdue (http://www.itap.purdue.edu/studio/signals/) (- jreinoso jreinoso Oct 14, 2013)
  • the Rio Salado Commmunity College Analytics Project is also known (http://blog.riosalado.edu/2012/09/predictive-analytics-reporting-par.html)(- jreinoso jreinoso Oct 14, 2013)
  • At State Level, Colombia has been working on a model that help Higher Education Institution (HEI) to prevent desertion (the opposite to retention). The model try to characterize students with high desertion probability such that HEIs can develop politics and procedures in order to minimize that situation. It is called SPADIES and it can be found at http://www.mineducacion.gov.co/1621/w3-article-156292.html (- jreinoso jreinoso Oct 14, 2013)
  • While I have used data from my own online courses for reflective practices to improve my own online teaching, I am not aware of any major implementations at public 4-year institutions. - Jolie Jolie Oct 16, 2013
  • USC has launched a University initiative in Informatics and Digital Knowledge that will affect all parts of the university including research, curriculum, and infrastructure. Funding will be at least $1 billon over in the next 10 years.- joseph.cevetello joseph.cevetello Oct 24, 2013
  • George Siemens SOLAR and Open Learning Analytics - http://www.solaresearch.org - alanwolf alanwolf Oct 27, 2013

Please share information about related projects in our Horizon Project sharing form.