Student Agency Analytics Enhance Adaptive Learning Systems

Why It Matters

Understanding and quantifying student agency allows for the creation of more responsive and personalized educational experiences. This data-driven approach can inform the design of learning platforms that actively support and encourage learners to take ownership of their educational journey, leading to deeper engagement and potentially better outcomes.

Key Finding

The study highlights that analyzing student agency through learning analytics can lead to more effective adaptive learning systems by understanding how students engage with and control their learning.

Key Findings

• Student agency is a critical factor in fostering autonomy, meaningful learning experiences, and improved educational outcomes.
• Learning analytics, particularly student agency analytics, can provide actionable insights for adaptive teaching and learning.
• The convergence of computational psychometrics, learning analytics, and educational sciences offers a powerful approach to understanding and supporting learners.
• Adaptive AI, informed by student agency data, has significant potential to personalize and optimize educational interventions.

Research Evidence

Aim: How can student agency analytics be integrated into adaptive learning systems to enhance teaching and learning processes?

Method: Literature Review and Conceptual Framework Development

Procedure: The research synthesizes existing literature on student agency, learning analytics, computational psychometrics, and adaptive artificial intelligence to propose a framework for utilizing student agency analytics in educational settings. It explores the technological underpinnings and pedagogical implications of this approach.

Context: Higher Education Learning Environments

Design Principle

Design for learner empowerment by providing transparent data and responsive feedback that supports self-directed learning.

How to Apply

When designing or evaluating adaptive learning platforms, consider how user interactions can be analyzed to infer levels of student agency and use these insights to tailor the learning path and support provided.

Limitations

The research is primarily conceptual and relies on existing literature; empirical validation of the proposed framework is needed. The definition and measurement of 'student agency' can be complex and context-dependent.

Student Guide (IB Design Technology)

Simple Explanation: This research shows that by looking at how students take control of their learning (their 'agency'), we can make computer-based learning systems smarter and more helpful.

Why This Matters: Understanding student agency helps create educational tools that empower learners, making them more active participants in their own education, which can lead to better learning.

Critical Thinking: To what extent can 'student agency' be objectively measured through digital interactions, and what are the ethical considerations of using such analytics to adapt learning experiences?

IA-Ready Paragraph: This research highlights the importance of student agency in adaptive learning. By analyzing how learners take control of their educational journey, systems can be designed to be more responsive and supportive, fostering autonomy and potentially improving outcomes. This principle can inform the design of educational technologies that empower users through personalized feedback and opportunities for self-directed learning.

Project Tips

• When designing an educational tool, think about how users can make choices and influence their learning path.
• Consider how you might collect data that reflects user autonomy and engagement, not just correct answers.

How to Use in IA

• Use the concept of student agency to justify the need for user control and personalization features in your design.
• Discuss how your design could potentially be enhanced by learning analytics that track user engagement and autonomy.

Examiner Tips

• Demonstrate an understanding of how user autonomy can be a key factor in the success of an educational design.
• Consider how your design might provide feedback that encourages self-directed learning.

Independent Variable: Student Agency Analytics (as input for adaptation)

Dependent Variable: Learning Outcomes, Learner Engagement, Learner Autonomy

Controlled Variables: Learning Content, Core Curriculum, Instructor Support

Strengths

• Addresses a crucial aspect of learner motivation and engagement.
• Connects theoretical educational concepts with practical technological applications.

Critical Questions

• What are the potential biases in algorithms designed to measure student agency?
• How can we ensure that adaptive systems designed to promote agency do not inadvertently reduce it?

Extended Essay Application

• Investigate the impact of different interface designs on users' perceived sense of agency within a simulated learning environment.
• Develop a prototype adaptive system that explicitly offers users choices and tracks their decision-making patterns to infer agency.

Source

Adapting Teaching and Learning in Higher Education Using Explainable Student Agency Analytics · Advances in computational intelligence and robotics book series · 2023 · 10.4018/979-8-3693-0230-9.ch002