Adaptive Learning Technology

Get Started:

Welcome to our OER about adaptive learning technologies. Before we jump-in, let's find out how much you already know. Read the survey below and select the answer that you think is MOST correct. Be sure to read the feedback closely.

Introduction:

Something we recognized early in our research is that there is significant ambiguity surrounding the term "adaptive technology". It is frequently used interchangeably with other terms (like "personalized learning"), and also holds different definitions in different spaces. So our first challenge was identifying: What definition of 'adaptive technology' do we want to explore for this OER?

“The term “adaptive technology” can be used in reference to technology used by people with disabilities as well as technology that adapts to meet the needs of users.” (McMahon, n.d.)

This OER will focus on learning technologies that adapt to meet the needs of students.

One of the hallmarks of technologies that adapt to meet the needs of students, is the ability to create a personalized learning experience based on learner input, responses, or activity within a system. In the most advanced examples, user generated data is analyzed by an intelligent system via ‘machine learning’, resulting in a variety of system actions aimed to improve learning.

The image below shows how 'Adaptive Learning Technologies' can be categorized as a sub-group of Artificial Intelligence (AI) that employ machine learning. All adaptive learning technologies are a form of AI, however not all AI are adaptive technologies.


Personalized Learning

Another way to think about it is that 'Personalized learning' forms the foundation upon which 'adaptive technologies' are built. This begins to answer the big question of "WHY" adaptive technologies are relevant in education: because they have potential to personalize learning.

Watch the video provided here to refamiliarize yourself with the concept of "personalized learning".

Deeper Dive:

Adaptive learning technologies can come in all shapes and sizes, as well as perform at different levels of complexity. One helpful breakdown divides adaptive learning technologies into three categories or levels:

Adapted from: BottomlinePerformance

Using the categories above, we tried to further classify different examples.

Pseudo Adaptive Solutions:

  • Designing assignments that allow student choice

  • Designing assignments with peer feedback (hence, generating the feedback loop)

  • Providing optional assignments or resources

  • Providing personalized and specific feedback based on student inputs

  • Designing eLearning with open navigation OR where choices matter, and create branching pathways

Stand Alone Adaptive Solutions:

Many educational Apps. seem to fall into this category. Apps like Knowjii, IXL Math/English, CrashCourse, and Mathia, just to name a few. These adaptive learning apps. promote features such as immediate feedback (loops), self-reported confidence level, contextual hints, spaced repetition and gamification. Stand-alone adaptive apps. are quite prevalent for certain subjects like math, language and music learning.

Adaptive Learning Eco-System:

Currently you can find learning management systems (LMS') designed and promoted specifically with AI-adaptability in mind. Some examples of this include: Cerego, iReady and ExactPath, to name a few. A recurring theme in these products is the intelligent use of analytics to create better insights (dashboards) for the instructor AND to automate certain feedback, pathway or hints/suggestion activity. Data Analytics has been a growing field in EdTech for some time, and most LMS' collect significant student data already, often offering more robust analytics dashboards / insights at additional cost. Few major LMS' harness the power of analytics to automate (much) adaptation...yet.

how do alts work?

The process

Here’s a simplified example of the adaptive sequence process: Several students are assigned different math content to work on.

  1. As each student interacts with the content, either by answering questions, clicking on hints, or using virtual manipulatives, the tool saves information about each student’s actions.

  2. When a student completes the assignment, the tool analyzes their academic performance and learning behaviors and then matches the student to a new set of skills based on performance.

  3. The platform automatically assigns the student new content.

This expert-model approach to adaptivity uses an "If THIS, then THAT" approach. It can be used to provide needed remediation, share advanced content with excelling learners, words of encouragement, and more.

Something to Ponder:

Before proceeding to the next section, take a moment to consider where adaptive learning technologies might evolve in the future? Do you think the major LMS' will continue to enhance the use of student data/analytics or will NEW LMS' disrupt the market with their enhanced features? Perhaps new LMS' will force the dominant ones to innovate and offer more robust adaptive functionalities?

What about stand-alone adaptive solutions? These technologies tend to compliment the current EdTech eco-system and might offer less resistance to adoption in the short-term.

[You don't have to submit anything here, just take pause and consider the questions.]