Adaptive or personalized learning is a promising concept, providing the learner with a tailored learning experience at any time. Despite the increasing interest of learning designers in adaptive learning, the lack of clear definitions and structured theoretical models has led to inconsistent implementations. Jan L. Plass & Shashank Pawar (2020) offer precise definitions of key terms related to adaptivity and personalization. They also describe different types of adaptivity in the form of a taxonomy to guide designers and researchers of adaptivity systems.

The authors first define several key terms to specify the concept of adaptivity:

• Adaptivity: System-driven adjustments in learning environments to optimize outcomes by diagnosing learner characteristics and automatically adjusting content, difficulty, and support
• Adaptability: Learner-controlled modifications to personalize the learning experience, fostering autonomy and self-regulation
• Learning Activity: Structured tasks designed to facilitate learning, adjustable based on learner needs
• Differentiated Learning: Instruction modified based on students’ interests, prior knowledge, and learning preferences
• Individualized Learning: Tailored instruction to individual skills and abilities, including special needs
• Personalized Learning: Encompasses both adaptivity and adaptability to customize learning experiences
• Responsive Systems: Educational systems that dynamically adjust to learner characteristics
• Adaptive Educational Technologies: Technologies that monitor learner performance in real-time and adjust instruction to maximize efficiency

Adaptive systems should consider cognitive, motivational, affective, and socio-cultural factors to optimize learning outcomes. Designers should evaluate these variables’ relevance, variability, and knowledge to justify adaptivity.

Effective measurement of learner variables is crucial for guiding adaptation. Methods include pre/post-tests, real-time tracking, and advanced analytics like educational data mining and learning analytics.

Adapting the Learning Environment

Adaptation can be approached through:

1. Attribute-by-Treatment Interaction (ATI) Research: Examines how learner traits influence instructional effectiveness
2. Cognitive Models & Knowledge Space Theory: Uses structured knowledge graphs to guide instruction
3. Data Science & AI-Based Adaptation: Predictive modeling and learning analytics to identify effective adaptation.

Plass and Pawar categorize adaptivity into macro-level (broad adjustments over time) and micro-level (real-time adjustments during learning) adaptations. Emerging forms of adaptivity leverage AI and technology for expanded personalization.

Challenges and Future Research

Adaptive learning faces challenges such as a lack of empirical research on non-cognitive adaptivity, ethical and privacy concerns, and resource-intensive implementation. Further research is needed to refine adaptive models for scalability, effectiveness, and ethical soundness.

References

• Plass, J. L., & Pawar, S. (2020). Toward a taxonomy of adaptivity for learning. Journal of Research on Technology in Education, 52(3), 275–300. https://doi.org/10.1080/15391523.2020.1719943