Adaptive learning is a teaching method premised on the idea that the curriculum should adapt to each student. On a basic level, the definition seems simple. But dig a bit deeper, and the nuances of the term begin to reveal themselves. There are many different degrees and types of adaptive learning, but often these distinctions aren’t made clear. As the quest for personalized learning gains traction among educators, and more and more products claim “adaptive learning” capabilities, a certain fuzziness has emerged around the term.
This article is intended to clarify the different types of adaptive learning, share how Waggle approaches adaptive learning, and identify key factors that may contribute to a more personalized experience for students
I. Provide continuous, as opposed to single point adaptivity
When most companies use the buzzword “adaptive learning,” they are typically referring to either a) single point adaptivity, which evaluates a student’s performance at one point in time to determine the level of instruction or material he receives from that point on, or b) adaptive testing, which determines a student’s proficiency level using a fixed number of questions.
In contrast, a program that is continuously adaptive analyzes all of a student’s activity and performance in realtime. By providing the right instruction, at the right time, about the right thing, the system maximizes the likelihood a student will obtain her learning objectives.
In other words, adaptive testing answers the question, “How do I get the most accurate picture of a student’s state of knowledge at a given point in time?” Truly adaptive learning answers the question, ”Given what we understand about a student, what should that student be working on right now?”
To provide continuously adaptive learning, Knewton’s recommendation engine in Waggle analyzes learning materials based on thousands of data points—including concepts, structure, and difficulty level—and uses sophisticated algorithms to piece together the perfect bundle of content for each student, constantly. For example, when a student struggles with a particular set of questions, Knewton will know where that particular student’s weaknesses lie in relation to the concepts assessed by those questions and can deliver content to increase the student’s proficiency in those concepts. In this way, a continuously adaptive system provides each student with a personalized syllabus at every moment.
II. Understand students beyond their scores
No two students are identical—they learn and forget at different rates, come from different educational backgrounds, and have different capabilities, attention spans, and modes of learning. A truly personalized learning program must be sensitive to the characteristics of each student, beyond how many items they got correct.
Imagine that you’re teaching math to fourth graders. You’ve just administered a test with 10 questions. Of those 10 questions, two questions are very simple, two are incredibly hard, and the rest are of medium difficulty. Now suppose that two of your students who take this test answer nine of the 10 questions correctly. The first student answers an easy question incorrectly, while the second answers a hard question incorrectly. Which student has demonstrated greater mastery of the material?
Under a traditional grading approach, you would assign both students a score of 90 out of 100, grant both of them an A, and move on to the next test. But this approach illustrates a key problem with measuring student ability via testing instruments: test questions do not have uniform characteristics. They vary in difficulty as well as on “guessability” and specificity to a topic. So how can we measure student ability while accounting for these differences in questions?
One method to get at a more nuanced view of student activity and proficiency is to use item response theory. Knewton’s recommendation engine in Waggle uses item response theory (closely associated with models by Frederic M. Lord) to understand student ability drawing on question level activity and performance in Waggle instead of aggregate test level performance. Instead of assuming all questions contribute equivalently to our understanding of a student’s abilities, Knewton analyzes a multitude of factors about the practice question and student activity. How many hints did the student access? How many attempts did it take for the student to get it correct? What is the difficulty level of the question? How easy is it for the student to guess and get it right?
Inspired by Hermann Ebbinghaus’s work on memory retention and learning curves, Knewton uses exponential growth and decay curves to model changes in student ability to learn and forget. These curves are governed by the following premise: each time students are exposed to content associated with a given topic, they receive a “bump” in their ability level for a topic; likewise, if they are not exposed to some other topic, they likely forget that topic over time. By integrating these curves, Knewton captures the way each individual student’s knowledge waxes and wanes, depending on how and when they are exposed to content.
III. Promote student engagement
Adaptive learning can improve student engagement by increasing self-confidence, decreasing discomfort and frustration, and encouraging productive learning habits.
Research indicates that boredom is associated with poorer learning outcomes and a propensity for gaming the system, and that confusion is a common state in digital learning environments. When a student’s engagement drops, her productivity also tends to drop, sometimes to the point of ending the session entirely. The data hint that perhaps some content is more likely to cause a student to quit working than others, and indeed, that is frequently the case.
To maximize engagement, adaptive programs need to make learning recommendations as effective as possible. A continuously adaptive learning system is able to deliver personalized feedback to various tech-enhanced item types such as drag-and-drop and multiple-select questions nearly instantaneously. Students are less likely to lose focus if constructive feedback is immediate, and they can quickly self-correct. For example, in Waggle, powered by Knewton recommendation engine, students get customized feedback immediately after checking their answer choice and they can reset the question to try it again. Students can also access hints if they get stuck on a problem and want support. The result is pacing that is conducive to risk-taking, experimentation, iterative development, and rapid learning.
With countless opportunities for students to demonstrate skill and reflect on action and feedback, adaptive learning naturally has features similar to those in games. Adaptive learning keeps students in a game-like state of “flow” by escalating the difficulty of the work incrementally and unveiling levels one at a time to increase suspense. These and other game elements are heightened in Waggle with the Lift Meter that goes up with every activity that a student does, such as accessing a hint or re-attempting a question. Students receive badges for getting several questions in a row correct. Furthermore, the process of “unlocking” new goals in the student dashboard helps heighten the satisfaction students feel in their progress.
IV. Amplify teacher impact
Adaptive learning can be a powerful tool for teachers to extend their reach and impact.
One of the biggest challenges facing teachers and school administrators is the growing diversity of students. Some students may struggle because English is not their first language whereas others may have difficulty with focus or organization. Some students may be particularly weak in one skill but possess unusual strengths in another.
Adaptive learning can allow teachers to address the needs of diverse students while gaining insight into the learning process, in terms of efficacy, engagement, and knowledge retention. A program with intuitive data analysis can make it easier for teachers to inform and differentiate instruction for each student. Teachers can grasp patterns in student activity and performance across the whole class or drill down into individual student profiles to determine exactly why a student is struggling on a specific skill.
For example, an adaptive learning program can identify that a student who is weak with math word problems may be struggling because he has difficulty with reading comprehension, not necessarily math. The program can then direct the teacher to specific material on syntax and vocabulary.
Adaptive learning poses many benefits, but not all adaptive learning programs are equal. Educators should proceed cautiously and evaluate various factors before deciding which program best meets their needs. Is it continuously adaptive or is it an adaptive testing program with single-point adaptivity? How does the program provide the right content for each student at the right time? Does it engage students so that they are motivated to stick with the program? How does it inform teachers to make it easy to differentiate instruction?
Knewton’s learning recommendation engine within Waggle Smart Practice constantly analyzes factors that contribute to a truly adaptive experience that includes continuous adaptivity, customized feedback, gamification, and insights for teachers. Learn how Waggle with Knewton engages students with personalized learning at www.wagglepractice.com