Beyond Self-Regulated Learning Processes: Unveiling Hidden Tactics in Generative AI-Assisted Writing

2025-08-13

AI Summary

This study challenges the conventional linear, stage-based modeling assumptions of self-regulated learning (SRL) in generative AI (GenAI)-assisted writing, aiming to uncover the dynamic, real-time mechanisms underlying students’ SRL processes. Method: Leveraging digital behavioral traces, we apply a Hidden Markov Model (HMM) to construct a hierarchical SRL model mapping observable behaviors to latent tactical states and higher-order strategic states—thereby representing SRL as a nonlinear, recursive system of implicit tactics. Contribution/Results: Empirical analysis identifies three distinct learner profiles exhibiting significant differences in academic performance, confirming a strong association between strategic typology and writing outcomes. The study not only reveals the inherent complexity of authentic SRL in GenAI-enhanced environments but also delivers a transferable modeling framework and empirical evidence, advancing learning analytics methodology and informing the design of adaptive educational technologies.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Structured Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

The integration of Generative AI (GenAI) into education is reshaping how students learn, making self-regulated learning (SRL) - the ability to plan, monitor, and adapt one's learning - more important than ever. To support learners in these new contexts, it is essential to understand how SRL unfolds during interaction with GenAI tools. Learning analytics offers powerful techniques for analyzing digital trace data to infer SRL behaviors. However, existing approaches often assume SRL processes are linear, segmented, and non-overlapping-assumptions that overlook the dynamic, recursive, and non-linear nature of real-world learning. We address this by conceptualizing SRL as a layered system: observable learning patterns reflect hidden tactics (short, purposeful action states), which combine into broader SRL strategies. Using Hidden Markov Models (HMMs), we analyzed trace data from higher education students engaged in GenAI-assisted academic writing. We identified three distinct groups of learners, each characterized by different SRL strategies. These groups showed significant differences in performance, indicating that students' use of different SRL strategies in GenAI-assisted writing led to varying task outcomes. Our findings advance the methodological toolkit for modeling SRL and inform the design of adaptive learning technologies that more effectively support learners in GenAI-enhanced educational environments.

Problem

• Understanding SRL dynamics in GenAI-assisted learning
• Analyzing non-linear SRL behaviors via learning analytics
• Identifying performance-impacting SRL strategies in AI writing

Innovation

• Using Hidden Markov Models for SRL analysis
• Conceptualizing SRL as layered system
• Identifying distinct learner groups via trace data