Adaptive learning, especially as it is used in eLearning, adapts learning intelligently to meet the needs of the learner. Based on information that the learner provides, the adaptive learning can deliver content and exercises that take into consideration such things as the learner’s expressed preferences, knowledge level (prior knowledge), needs and motivation level. While it is related to differentiated learning and personalized learning, it is not the same.  Differentiated and personalized learning give students options in learning that are more tailored to their needs, but they still rely on set learning paths and are often determined by the instructional designer or subject matter expert. Adaptive learning, by contrast, adapts the learning as the learner progresses through the material. The following video presents a good discussion and Venn diagram showing the differences between the three learning types:

The arguable benefit of adaptive learning is that it can be developed to deliver the optimal cognitive load, depending on the learner’s experience with a particular subject matter.  For example, a learner with little prior knowledge in one area may be presented with additional explanations and examples, extras that would not be used with learners who already had a high knowledge level. It can also include such things as spaced repetition at a rate that is most beneficial for the individual learner.  

Today’s adaptive learning technologies more and more seem to be leveraging developments in artificial intelligence. The AI technology behind the language learning software Duolingo (http://www.duolingo.com), for example, makes it possible for “chatbots” to adapt the language material presented to the learner, correct mistakes and make suggestions, all based on the learner input. Decisions about which content to present to the learner are not just made by one or two subject matter experts. With the right algorithms the technologies can mine huge amounts of data to provide very targeted and highly adaptive responses to learner input.  Nevertheless, these kinds of adaptive technologies still view learning largely as a very individuated, isolated activity. As Dr. Cole pointed out in this week’s video, and given the importance of social and collaborative learning that we’ve discussed previously, this kind of “lonely learner at the computer” scenario can be problematic.

While much adaptive learning is eLearning, adaptive technologies are also available to provide a kind of hybrid adaptivity for a face-to-face or blended class.  For example, the technology provided by CogBooks (http://www.CogBooks.com) allows instructors to create interactive content for students (like an interactive textbook) that also tracks data about how the learners engage with the content.  It can track such things as the concepts the students spend the most time going over, how often the student engages with the content, and what the students’ main questions are.  The instructor can then use this information to tailor or adapt her lectures or discussions so that they best address the knowledge or skill gaps that learners have.  If the data show that learners have mostly grasped a concept, the teacher may be able to simply review that concept in lecture and spend more time going over something more complex.  By integrating adaptive eLearning technologies into existing classes, there are more opportunities to leverage a range of learning modalities.

The following TED-style talk describes how AI is influencing the current generation of adaptive learning technologies:

Other Resources on Adaptive Learning:

“Adaptive Learning.” Wikipedia. November 16, 2016. https://en.wikipedia.org/wiki/Adaptive_learning

“Adaptive Hypermedia.” Wikipedia.  February 21, 2017. https://en.wikipedia.org/wiki/Adaptive_hypermedia

Flores, R., Ari, F., Inan, F. A., & Arslan-Ari, I. (2012). The impact of adapting content for students with individual differences. Journal of Educational Technology & Society, 15(3), 251-n/a. Retrieved from https://search.proquest.com/docview/1287024917?accountid=167280

Huang, S.-L. and J.-H. Shiu. (2012). A user-centric adaptive learning system for E-learning 2.0. Journal of Educational Technology & Society, 15(3), 214-n/a. Retrieved from https://search.proquest.com/docview/1287025364?accountid=167280