Skip to main content icon/video/no-internet

Adaptive Learning Modules

Adaptive learning modules use artificial intelligence to adjust how instructional content is presented to students based on their understanding of the material, prior knowledge, or personal characteristics. These modules aim to create instructional environments that are individually and contextually tailored, helping students to master concepts at their own pace and to develop personalized pathways through the course material. This entry provides an overview of adaptive learning modules, then explores their use in higher education as well as their benefits and limitations.

Overview

A typical adaptive learning module relies on embedded assessments of learning progress in order to select the next step on the learning path (e.g., further practice with the same concept, remedial instruction on prerequisite skills, or continuation to the next topic in the curriculum). This core functionality can be traced back to research on intelligent tutoring systems, interactive computer programs that include algorithms for measuring student behavior and recommending instructional content from course modules. In contrast to static, one-size-fits-all instruction, these systems diagnose gaps in knowledge or skills at a granular level and dynamically deliver personalized interventions. Adaptive learning modules generally involve three components:

The content or domain model serves as the knowledge base for the course: What are the concepts and/or skills that the student will learn? A basic example of a content model is a list of definitions that must be memorized. Most courses involve more complex domains with a progression or hierarchy of concepts that build on each other, in which case the content model involves a map of the dependencies among different concepts to be learned. More sophisticated domain models attempt to specify at a fine-grained level the individual concepts and procedural steps that are to be mastered by the student.

The learner model is the system’s representation of the student. Although the learner model may be as simple as a list of student attributes (e.g., age, grade level), more sophisticated learner models incorporate estimates of a student’s current knowledge and proficiency (defined in relation to the content model), motivational or emotional states, and other aspects of students’ behavior that might inform adaptive instruction.

The instructional model is the algorithm that modifies the learning experience based on the learner and domain models. Together, the specification of the learner model, domain model, and the instructional environment define the scope of adaptation that is possible. Common forms of adaptation include changes in the pacing, order, or format of presentation depending on the needs and goals of the individual student.

Higher Education Context

Adaptive learning is considered one of the top 10 strategic technological innovations that has potential to impact higher education. Adaptive learning modules provide higher education administrators with data to identify at-risk students who are in danger of falling behind and dropping out. It also provides faculty with data and tools to create personalized instruction, monitor students’ progress, and support at-risk students.

Tailored Learning

Adaptive learning helps tailor the learning experience to at-risk students, assist them master core skills, and develop individual paths to facilitate their progress toward graduation and recommend interventions if needed. It helps identify problem areas where students need the most assistance and helps the faculty to address them immediately.

...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles

Sage Recommends

We found other relevant content for you on other Sage platforms.

Loading