EdPlus’ Dale Johnson on the ‘black box’ of adaptivity

Via Educause Review

Adaptive learning continues to raise hopes and doubts across higher education. On one hand, adaptive learning can easily scale with more learners learning than ever, and at cheaper costs. On the other hand, fears that these systems could replace faculty continue to loom.

Dale Johnson, an adaptive program manager for EdPlus at ASU, said “Neither hype nor hysteria are helpful during this critical phase of development in this nascent industry.” Johnson said that “what professors and providers need is a common framework to organize the discussions about the most effective and efficient ways to create useful adaptive courseware.”

In essence, “the goal of adaptive courseware is to provide the right lesson to the right student at the right time,” Johnson said.

Johnson, having worked on many systems while at EdPlus, has developed a framework that allows him to understand what’s happening inside the “black box of adaptive learning.”

Two questions have guided Johnson: “What is adapting to the student? What is guiding the adaptation?”

What is adapting to the student?

“In the systems we have worked with, the ‘moving parts’ that are adapting are the Lesson Sequence and Content Selection” Johnson said. By adapting the lesson sequence to each student, they each have a personalized path through the course they are taking. As Johnson points out, some students come in at a higher level of mastery, while others may need more assistance.

“Content selection is an adaptive sub-process that occurs within a lesson,” Johnson said. He compared this to how internet search engines work, where content is based on what the search engine knows about you. In this case, if students perform better by watching a video vs reading some text, then adaptive systems can learn from that and make better content selections for that student.

What is guiding the adaptation?

“The second question goes to the heart of the matter of what is happening inside the ‘black box’ in adaptive courseware,” Johnson said. According to Johnson, four major techniques are used to help vendors select what lesson sequence and content selection is most powerful. Those are: algorithms, assessments, association and agency.

Algorithms have gotten the most notable attention from people working with adaptive systems, both positive and negative, while assessment-based adaptivity is a “much more common technique in systems we have explored,” states Johnson. Then you have association which is typically an unrecognized part of adaptive courseware, but very crucial. Lastly, agency explores the students’ opinions on if they think they learned something before they are assessed.

“The Black Box of adaptive courseware does not have to be magical or menacing,” according to Johnson. Rather “it is simply another tool for faculty and students to improve learning.”

Johnson notes some similarities in the self-driving Uber vehicles he sees on his way to work every morning. “Inside is an engineer who evaluates the adaptive driving systems (and possibly takes the wheel), making sure they are performing as expected.”

Read more about the four techniques for lesson sequence and content selection