Nov 11, 2021 By Team YoungWonks *
What is adaptive learning? In the aftermath of the Covid19 pandemic, the edtech industry - especially elearning / online learning - has grown exponentially and concepts that were nascent have come to assume more importance and shown more progress in terms of their development. The world of adaptive learning would be one such example. But what is adaptive learning? One of our older blogs about top edtech trends of 2021 (https://www.youngwonks.com/blog/Top-Edtech-Trends-in-2021) also talks about adaptive learning as a key trend. In this blog, we look at what it means, how it works and more…
What is Adaptive Learning?
Adaptive learning, also called adaptive teaching, AI powered learning or intelligent tutoring, is an educational method that makes use of technology (computer algorithms and Artificial Intelligence (AI)) to bring about a focused interaction with the learner such that he/ she is offered customized resources and learning activities as per their unique needs. In other words, adaptive learning refers to the delivery of custom learning experiences that factor in each individual student’s unique personality and needs. It is carried out through just-in-time feedback, pathways, and resources as opposed to offering a standardized, one-size-fits all learning experience.
So in such a learning environment, the instructor will modify his / her teaching technique, right down to hints and advice so as to accommodate one-on-one questions from the individual learner. In doing so, the instructor references current events or known student passions and preferences, changing learning activities and learning styles on the go, if needed. Basically the instructor adapts to the student needs, thus offering an adaptive learning experience. That said, practising adaptive learning with more than one or two learners at a time can be very challenging. This is where adaptive learning technology comes in.
Adaptive learning systems aim to change the role of the learner from being a passive recipient of information to becoming an active collaborator in the educational process. Here, computers tweak how the educational material is presented as per the students’ learning needs, as gleaned from their responses to several questions, tasks and experiences. The technology used culls from different fields of study, including computer science, AI, psychometrics, education, psychology and even brain science.
And while the primary application of adaptive learning systems lies in education, they also hold promise for the field of business training. Today, adaptive learning systems are being designed as desktop computer applications, web applications, and even being introduced into the curriculum at many educational institutions.
Indeed, there are many examples of adaptive learning platforms today. There’s Prodigy Math, which teaches early math skills to children and ALEKS teaches math, science and business to university students. Meanwhile, IKnow teaches East Asian languages.
A Brief History of Adaptive Learning
Adaptive learning can be traced back to the 1970s, when the AI movement first caught on. Back then, the main challenges were the exorbitant cost and big size of the computers, that made the widespread application of adaptive learning rather unfeasible. Another obstacle lay in the fact that the user interfaces were not conducive to the learning process. Actual work on adaptive and intelligent learning systems began thanks to the SCHOLAR system that offered adaptive learning for the subject of geography of South America; many other innovative systems came about in another five years.
And interestingly, the first teaching machine actually dates back to 1924, when Ohio State University professor Sidney Pressey built the Automatic Teacher. The first device in electronic learning, it allowed students to drill and test themselves. That said, deploying AI to cater personalized learning experiences to students is very much a recent phenomenon, fueled by increasing processing power being available in the cloud and on local devices.
Adaptive Learning Models
Adaptive learning systems can be classified as different models. Broadly speaking, they are one of the below:
The expert model
The model with the information that has to be taught.
The student model
The model that tracks and gathers relevant info about the student.
The instructional model
The model that shares the information.
The instructional environment model
The user interface for interacting with the system.
Goals of Adaptive Learning
The main aim of adaptive educational technology is to make the learning process a smooth, successful one. This is achieved through the following:
Focus on the student: Knowing the student’s nature, their personality, preferences, cognitive processes, and strengths and weaknesses.
Fulfilling the established educational goals: Figuring out the set goals with corresponding deadlines and the study material, teaching methods, implementation methodology, and evaluation criteria that needs to be in place for achieving it.
Improving student learning on quality and quantity fronts: Using modern educational technology to improve the learning experiences of students in terms of their quality and also increasing the number of students whose learning experiences are being influenced.
Organizing forms, means and methods of work: Student performance can be enhanced not only through effective teaching, but also by encouraging their participation in activities using optimized teaching forms, methods and tools.
Evaluating student work: Adaptive learning systems can be used also for basic tasks such as assessing how far the students have come in terms of achieving their goals and identifying measures that can be undertaken to speed up the process.
Benefits and Challenges of Adaptive Learning
Benefits of Adaptive Learning
Increased engagement: A personalized learning experience is more likely to increase engagement with the student than a mass class where students do not get individual attention.
Self-paced learning: Since adaptive learning involves factoring in each student’s abilities, it effectively translates into self-paced learning where the student is not rushed into learning anything and can move at their own pace to the next concept only after mastering the previous one. Conversely, the student also does not lose any time learning content already mastered.
Efficient training: A curated learning experience crafted using individualized study material, activities, quizzes and questions has an edge over a large class with no adaptive learning.
Instant feedback: In the adaptive learning model, teachers can easily identify gaps in the student’s knowledge and keep track of their personal growth and development.
For training managers
Scalability: Adaptive learning, when armed with the corresponding technology, can be scaled up to include more students without compromising on its offerings.
Data: Using adaptive learning systems, training managers can check out metrics sharing information about employees’ engagement and progress in terms of their students' skill levels; thus offering an insight into the success of the training program.
Challenges of Adaptive Learning
Understanding and deploying adaptive learning takes effort and is often time and money consuming. Given that most programs cost a large sum of money to purchase for large educational institutions, choosing the right provider can be stressful and time consuming.
Not having much evidence to go on is not exactly a plus. Adaptive learning being relatively new, there is not a big pool of research that speaks strongly for its effectiveness.
Finding resources for development of adaptive learning is not easy, since it takes a lot to research and develop adaptive learning programs.
Convincing students and instructors to try out a new way of instruction can be tricky especially since it depends on the algorithm to decide whether the student can progress to the next level/ concept.
With adaptive learning, the instructor is no longer the deliverer/grader of material; instead, he / she is now the manager of the learning experience and has to even analyze extensive data that is generated as part of the experience.
*Contributors: Written by Vidya Prabhu; Lead image by: Abhishek Aggarwal