There is a consistent failure in providing desired outcomes at the higher education level. This is indicated by a low employability ratio and the need for firms, which recruit from such institutes, to create a multitude of training programmes for their hires. Such institutes also face challenges in attracting teaching talent. Flipped and blended learning models can augment classroom learning, since these enable more discussion during the class time, by making available lectures and theoretical aspects of the lessons in a multimedia format. Such digital learning environments increase student-teacher and peer-to-peer interaction, thus providing a richer learning experience. But the most important benefit of digital learning environment is that it enables ‘learning analytics’.
Learning analytics is the measurement, collection, analysis and reporting of data about the progress of learners and the contexts in which learning takes place, for the purposes of understanding and optimising learning and the environments in which it occurs. A student’s interaction with institutions in any form—using a computer lab, entering the library, logging in or taking online exams—leaves a digital footprint. Analysis of this data to improve learning and teaching is in general referred to as learning analytics. Institutions have realised the potential of the data produced in their learning environment for solving the challenges they face. Reducing the cost of education, early intervention to help a struggling student, increasing student retention and success ratio, improving admission rates, customising educational content are a few examples learning analytics can help institutions.
Even though higher educational institutions use data such as quiz grades, course evaluations, etc, to improve student learning, today’s analytical systems can empower institutes to gather enormous volumes of data consistently and centrally, analyse it fast, and show the results in simple, easy-to-understand visual representations. Institutions are moving from getting conventional reporting about past performances to predicting almost all parameters of higher education. Learning analytics engine can also provide indicators to students regarding their performance. For example, Purdue University in the US has deployed a Learning Management System (LMS) with student visualisation dashboards that uses symbolic traffic lights to warn students when they are at risk in a course (with a red signal) or to inform them that they are on track (green signal). LMS, based on predictive analysis, can determine which courses are needed for the students to graduate and ranks them according to their significance in the sequence of the course for that degree, and also according to their relevance in the university curriculum. These rankings are then projected with a collaborative filtering model to predict the courses in which a student is most likely to achieve best grades, thus helping both the student and the institute.
Teachers are helped by analytical dashboard to observe identified trends and by enabling early intervention. LMS with learning analytics, with the use of semantic algorithms, can help teachers find relationships among different teaching components to make intelligent recommendations for the content to be delivered to the students to achieve a particular learning objective. It can also help teachers determine how well the content has helped students in the past by analysing historical data. Teachers can monitor and predict student grades from the first week itself with different success levels represented by different visualisation methods.
Administrators at institutional levels have been using predictive models for enrolment for long. However, the modern predictive models enable them to monitor student success, completion and operational aspects too. Predictive models can forecast the number of courses needed to meet student demand by analysing course-taking behaviour. A new approach in the use of LMS with learning analytics should incorporate parents too. They can measure their kids’ performance in a particular course and benchmark the same against historical data as well as against peers. Benefits for employers include analysing students’ skills periodically, throughout their duration of the study, rather than having a one-time test or interview to determine their suitability and skills for the job.
Clearly, all the stakeholders of higher education—students, teachers and administrators—can benefit. It’s in the interest of the stakeholders that higher educational institutions understand the best ways to leverage predictive learning analytics and adopt the same. However, service providers and software vendors of learning analytics solutions must keep in mind that a recent Supreme Court judgment on privacy as a fundamental right of individuals is not violated.
(With inputs from V Sridhar, Professor, International Institute of Information Technology, Bangalore)
The author is co-founder of Epecate, an edtech start-up