Back in the 1980s, educational psychologist Benjamin Bloom identified the ‘2 Sigma Problem’. After conducting extensive research, Bloom came to the unarguable conclusion that learners tutored on a one-to-one basis performed far better than through other teaching methods.
Bloom also (wisely) recognized that one-to-one tutoring is “too costly for most societies to bear on a large scale.” Therein lies the 2 Sigma Problem: this learning method is the most successful, but it’s impossible to deliver at scale.
Adaptive Learning: The Solution to the 2 Sigma Problem?
The benefit of one-to-one learning is dedicated attention. A teacher can fully understand strengths and weaknesses and then tailor learning techniques and materials to fit.
L&D teams working in large organizations have even less hope of achieving this level of highly-tailored learning than schools or universities. With an often globally-dispersed workforce who lack dedicated time to learn, delivering individual instruction is unlikely to be a viable business decision.
So could adaptive learning be the answer?
What Is Adaptive Learning? And What About Personalized Learning?
Adaptive learning is essentially a way of mimicking the highly-effective one-to-one teaching environment: using tools and strategies to observe individual learner performance and then adjusting the learning to suit that individual.
You may hear adaptive learning and personalized learning used interchangeably, but there are differences between the two:
- Adaptive learning uses a data-driven approach to adjust the path and pace of learning according to the learner’s needs, enabling the delivery of highly-personalized learning at scale.
- Personalized learning creates a tailored pathway for each student, often based on rules or conditions.
- An example of personalized learning would be to implement a diagnostic check at the start of the course that determines which topics learners see.
How Does Adaptive Learning Work?
Adaptive learning can be implemented in different ways, from the simple to the complex. For example:
Simple:
Could be tracking how a learner answers a question and delivering a simpler subsequent topic if they get it wrong.
Branching scenarios could also be seen as a simple form of adaptive learning. Instead of different content being delivered to the learner, they are simply redirected to a certain point along a predefined line.
Complex:
Could be tracking a learner’s strengths and weaknesses across a course or series of courses, and automatically delivering only the content most relevant to them.
This involves identifying and collecting data on a range of ways a learner interacts with learning content—and potentially how they also learn outside of these formal courses, too.
For example, this could mean aggregating data gained from assessment results across different courses to identify areas of weakness. This approach could also combine data from the learner’s day-to-day performance, providing an even fuller picture of the areas future learning should target.
Is Data the Key?
Adaptive learning relies on tracking prior decisions, behaviors, interactions and external activities to understand learner performance.
This requires the ability to identify and collect a wide range of data sources. To make adaptive learning a reality, businesses need to harness technologies that can make this possible.
xAPI enables the collection of a vast range of data on learner activity, whether online or offline. This can then be collected in one place and analyzed to build a broad picture of learning requirements.
What Is the Role of AI in Adaptive Learning?
While xAPI can be used to collect data, algorithms and machine learning will be needed to instantly decipher that data and make decisions on what learning should be delivered next.
Think about YouTube or Netflix: they collect data on videos we watch, then use algorithms to suggest other content we might like. The same approach will drive adaptive learning to suggest content that is best suited to an individual learner’s needs.
Adaptive Learning Enables Individualized Learning At Scale
Harnessing the latest technologies can help businesses build a truly accurate picture of every learner’s performance and automatically tailor their learning journey to support their development and maintain engagement.
At a broader level, adaptive learning can also enhance performance across the organisation. Tracking more complex data in real-time provides a fuller picture of skills gaps within the business as a whole. This will identify where L&D effort should be concentrated for maximum business impact.
A data-driven approach to adaptive learning has the potential to deliver adaptive learning at scale—and solve the 2 Sigma Problem. But to be successful, businesses will require a considered strategy for data collection and analysis, as well as intelligent use of AI technologies.