In Higher Education Institutions as well as in other organizations, various electronic systems are constantly leaving users with electronic traces, or data. When a student takes an electronic exam, he/she registers how long he/she took the time to answer and how many words he/she wrote. Learning environments record information such as student assignment returns and logins. The course register again accumulates course scores and grades.
Human data can be broken down into an active or a passive footprint. An active footprint is created when, for example, people write messages or leave feedback. The passive trace, on the other hand, is left to everything the user is unaware of, such as time and clicks.1
By definition, learning analytics is the process of gathering, measuring, analyzing and reporting learner-centered information with for the purpose of understanding and optimizing learning and learning environments.2 Thus, learning analytics seeks to add value to information that has been too laborious to deal with prior to analytics, to serve different user groups: students, teachers, tutors, and administration and management.
The potential for using analytics depends on what kind of applications are built around it. The digital learning platform collects data naturally and many learning environments have analytical capabilities. However, analytics can also be extended to include library card loans or even lecture attendance by adding electronic registration to lessons, for example through a mobile application. In theory, data can be collected endlessly, so it is essential to identify what information is really useful for developing learning processes.
Learning analytics can be utilized in many different ways to serve the needs of users. The analytics can be directly descriptive, whereby, for example, the student can see real-time information about the overall status of their studies or the performance of students in their teacher course. Descriptive information can be used for comparison. This allows the student to see how they have progressed relative to other students, or the teacher to see how the course implementation relates to previous rounds of the same course. Analytics also enables foresight. Data collected over a longer period of time may predict that a student who meets certain criteria is at risk of dropping out of the course, providing them with situational support. In addition, Artificial Intelligence can automatically provide students with feedback or exercises appropriate to their skill level. The list of examples is endless.
Finally, how data is presented to users in the form of various results and reports is key to the successful exploitation of learning analytics.3 The goal of visualisation is to present the information and recommendations discussed in learning analytics reporting as clearly as possible to the users.4, 5 Two examples of learning analytics’ results are presented below.
University of Turku
1 Madden, M. – Fox, S. – Smith, A. – Vitak, J. (2007). Digital Footprints – Online identity management and search in the age of transparency. https://www.pewinternet.org/2007/12/16/digital-footprints/
2 Siemens, G. (2013). Learning analytics: The emergence of a discipline. American Behavioral Scientist, 57(10), 1380-1400.
3 Auvinen, A. (2017). Oppimisanalytiikka tulee – Oletko valmis? Suomen eOppimiskeskus Ry. https://poluttamo.fi/2017/08/02/oppimisanalytiikka-tulee-oletko-valmis/
4 Brown, M. (2012). Learning analytics: Moving from concept to practice. EDUCAUSE Learning Initiative, 1-5.
5 Reyes, J. A. (2015). The skinny on big data in education: Learning analytics simplified. TechTrends, 59(2), 75-80.