Learning Analytics

According to Johnson, Adams Becker, Cummins & Estrada (2014), learning analytics is the interpretation of a wide range of data produced and gathered about students to guide their academic progress, predict future actions and identify problematic elements. The aim of the collection, recording, analysis and presentation of these data is to enable teachers to adapt quickly and effectively educational strategies at the level and ability demanded by each student. Even in its early stages of development, learning analytics often respond to the need to carry out monitoring and control activities in the virtual campus for strategic decision making. In addition, also seek to exploit the vast amount of data produced by students in academic activities.

Learning Analytics

Overall, the information provided to customize the training and learning environments designed according to the needs, interests and ways of interaction of teachers and students. The statistical record of the activity of students and teachers also identify hot spots of a teaching-learning process.

Even though experts predict that this technology should be massively adopted in 3 to 5 years, the potential of learning analytics has its obstacles. Indeed, the privacy of student data is an important issue that has received attention recently, but there are others. One of these challenges is to broaden the perspective of educators about the possibilities of a personalized learning guided by analytics. This marks a significant difference from the instructional strategies guided by traditional data. This is because there are many more data available to extract information, make sense and usefulness.

Among the forces impacting this technological trend, we can find the increasingly blurred boundaries between formal and informal learning. This means that the same person may be participating in a course of a virtual campus, following a series of twitters and blogs, communicate in forums with fellow students and synchronously with friends and colleagues, etc. Buckingam and Ferguson (2011) point out that the use of digital fingerprinting can be applied to a wide variety of contexts and allow analyzing the behavior in a wide variety of situations.

Computer-assisted instruction is not new, but the proliferation of technology and sophisticated methods for data analysis are. The quality and quantity of available data opens new opportunities to provide effective personalized learning experience, but it certainly some challenges. However, we have seen firsthand the benefits that these technologies can have on millions of students, so we think it is a journey worth doing.

References

Ballard, C. (2012). Learning Analytics - Improving Student Retention. Retrieved from http://www.slideshare.net/ChrisBallard/learning-analytics-improving-student-retention

Buckingham, S. & Ferguson, R. (2011). Social Learning Analytics. Technical Report KMI-11-01, Knowledge Media Institute, The Open University, UK. Retrieved from http://kmi.open.ac.uk/publications/pdf/kmi-11-01.pdf

Johnson, L., Adams Becker, S., Cummins, M., and Estrada, V. (2014). 2014 NMC Technology Outlook for International Schools in Asia: A Horizon Project Regional Report. Austin, Texas: The New Media Consortium.