Learning analytics (LA) investigates and processes digital footprints that students leave behind while accessing digital platforms including learning management systems (LMSs), intelligent tutoring systems (ITSs), massive open online courses (MOOCs), and educational video games.
The outcome of such study helps to trace the learning experience and then suggest personalized alternatives for improvements and ultimately optimize the learning process.
LA also helps to increase awareness of both students and instructors and allow them to make constructive decisions and conduct their tasks effectivelyy, and to personalize educational opportunities to fit individual learner's needs.
LA provides many opportunities for academic institutions to implement efficiently adaptive learning and active learning. It also helps to analyze data from at least four different views: 1) Descriptive; 2) Diagnostic; 3) Predictive; and 4) Prescriptive.
The outcome of an effective big data analysis would enable researchers to identify valuable information to support educational institutions, learners, instructors to improve personalized learning and student engagement.
Hence, the benefits of LA are manifold including identifying target courses, curriculum development, student learning performance and behavior, and improved instructor performance.
Many academic institutions are using LA to analyze students' learning data.
There are a few challenges that need to be addressed before applying LA and harvesting its gains.
For more details, please contact me here.