Data Analytics: Ensuring eLearning Efficiency

Ensuring Learning Efficiency And Targeting Through Data Analytics

With the advent of modern technology, more and more learning is being disseminated through computers and mobile devices. The data generated is at an unprecedented level, yet the effective use of this data remains nascent. Here is how data analytics can be used for effective eLearning.


Designing For Better Learning Through Data Analytics

A learning analytics system can provide the ability to classify learning elements using attribute values and using basic statistical tools to determine mapping between these classifications and desired outcomes. As given in the example below, this would lead to valuable insights for instruction and content design.

Automating Content Delivery Through Data Analytics

Adaptive systems can change its response to inputs based on context (historical data) and circumstance (data gathered from other sources). The efficiency of an adaptive system is measured by its ability to optimize on results by effecting these changes. Adaptive systems are built to be able to gather data, analyze, and formulate recommendations and decisions in order to optimize certain criteria, in this case learning. The system will use neural network algorithms to create personalized learning paths for students according to their goals:

  • Recommendations on courses to study, time to spend, and refreshers based on a student’s progress.
  • Creating dynamic course structures which take into account historical data not only from the student, but also peers.
  • Recommending interventions to teachers/mentors based on learning progress of an individual or group.
  • Certifications and awards: Awards given automatically when a learner jumps to another level among peers (slow learner to fast tracker).

Another way to automate content delivery through analytics is through the Rule Based Expert System. It is a system which would monitor parameters and generate notifications based on pre-defined rules.

For Example:

  • Personalized tracking of skill based progress of a student where a one-to-one session with a Subject Matter Expert is automatically assigned when rate of progress falls below a threshold.
  • Refresher materials start being assigned after completion of a set of courses. Further refreshers being sent to only students who have not scored well in previous assessments.
  • Content being put up for review (ID, Copy) when the average rating falls below a certain benchmark.
  • Adaptive assessments: Easier or more difficult questions as per learner progress and scoring-based on learner ability and progress.

Continuous Skill Development Through Data Analytics

For corporates, learning and training is primarily a tool to increase employee performance. This simple fact is often lost to many learning systems. Corporates view training as an investment and as any investment: Are keen on maximizing the ROI. Employee performance has direct impact on ROI. The most effective way to incorporate a mechanism which can implement monitor and drive ROI is through a skill and competency management system which links to KPI’s and provides a continuous skill development cycle. Measurement of the impact of training to the Key Performance Indicators (KPIs) of an employee is key to the success of any learning initiative in a corporate organization.

Based on the ADDIE Model this system integrates with a performance management or CRM system; to provide the ability to furnish an automatic and continuous improvement cycle, which would be targeted to the users at the exact time, they need the learning.

  • Create a skill/competency matrix for each job role in the organization.
  • Analyze the internal systems to gather data for calculating KPI’s for the users.
  • Create benchmarks on the KPI’s to indicate trigger levels.
  • Link trigger levels to the skill/competency matrix, so that whenever the KPI dips below the trigger level a skill gap is identified.
  • Link targeted content to each skill level which can be suggested to the user’s basis their KPI scores.

Learning Analytics gives a focus on the use of Learner data. Tanya Elias (2011) put it as

“…the focus appears to be on the selection, capture and processing of data that will be helpful for students and instructors at the course or individual level. Moreover, learning analytics is focused on building systems able to adjust content, levels of support and other personalized services by capturing, reporting, processing and acting on data on an ongoing basis in a way that minimizes the time delay between the capture and use of data.”

In conclusion, to make eLearning truly effective, the utilization of data analytics is necessary and wise.