As technology use increases in the classroom, more data is captured about student activities throughout the learning process. This information can be used to create individualized learning pathways for students. Systems that attempt to automate this process are called "adaptive learning systems" and have the potential to drastically change how we educate students.
The US Department of Education Office of Educational Technology defines adaptive learning systems as follows:
“Digital learning systems are considered adaptive when they can dynamically change to better suit the learning in response to information collected during the course of learning rather than on the basis of preexisting information such as a learner’s gender, age, or achievement test score. Adaptive learning systems use information gained as the learner works with them to vary such features as the way a concept is represented, its difficulty, the sequencing of problems or tasks, and the nature of hints and feedback provided.”
Adaptive learning systems are not meant to replace the teacher. Rather, they can be used to support the classroom teacher. Below are a few examples:
- Students can use software and online services outside of class to interact with content traditionally covered in lectures.
- Dashboards and reports generated by adaptive learning products can give teachers aview into class-wide trends and individual progress made by students.
- Adaptive learning products can function as tutors, providing interactive feedback to learners and recommending learning paths for them to follow.
Adaptive learning systems are still in their infancy. A number of adaptive learning systems are starting to be used in K-12 institutions around the globe, but important challenges still remain:
Teaching more than math: At this point, most adaptive learning systems only target math instruction or other concrete topics. It is much more challenging to create systems for language-dependent learning like writing and reading, where there is no right or wrong answer.
Moving from supplemental to core: Adaptive learning systems are still largely meant to be supplemental learning resources. Teachers may use them occasionally for independent study, but so far at least, they are not viewed as core instructional tools. As a result, it’s easy to view them as non-essential.
Being actually adaptive: Many of these companies say their products are adaptive, but beyond providing some basic interactivity and monitoring student progress through their content, most do not approach the level of actually being an intelligent tutoring system capable of replacing in-person tutoring.
Gathering and interpreting new data sources: In the coming years, adaptive learning systems will also likely be able to gather and interpret new data sources, increasing systems’ validity across subject areas. For example, AutoTutor, developed at the University of Memphis, uses a conversational system to interact with students and is able to understand student-written responses and question. Utilizing new hardware and software, adaptive learning systems will also start to gather “affective” data from students, seeking to interpret students’ emotional response to the learning activities. One possible example of this includes using device cameras to gauge understanding and emotions through facial expressions. Wearables may also record data from learners as they work through lessons and assessments.
Drawing more meaningful conclusions from data: Many adaptive learning systems are improving their ability to draw meaningful conclusions from the data that they gather. As these systems aggregate more and more students, they will be able to make more insights about students, such as levels of engagement and frustration.
What experiences do you have with students using adaptive learning tools in the classroom? Please share your observations and opinions below.