Zoek in de site...

Iprogress project

Facilitating self-regulated learning in adaptive learning technologies

Many students in primary education regularly learn using adaptive learning technologies (ALTs) on tablets. Driven by developments in the emerging field of learning analytics, ALTs successfully adjust instructional events (instructional texts, assignments, tools) to learners’ performance, and hence facilitate learning efficiency. Yet, ALTs largely eliminate the need for learners to engage in self-regulated learning activities (SRL). Research showed that learners’ self-regulated activities drive learner effort, which is essential for retention and transfer of knowledge (learning effectiveness). Hence, this research project investigates how ALTs can facilitate learner effort and learning effectiveness.

To this end personalized visualizations are developed to support learners’ self-regulated learning and tested within in four consecutive experiments. The personalized visualizations are designed to support learners to adequately adjust their effort and effectively regulate their learning.

Students who monitor and control their own learning process, are able to learn more and develop important self-regulations skills. These skills are of importance throughout a life-time of learning. Through the learning path app, students gain insight into their own learning process. They learn in an adaptive learning environment such as Snappet or Gynzy. Our AI@EDU infrastructure allows us to use the data generated in these adaptive learning environments in the learning path app. The learning path app contributes to improving exercise behaviour, learning outcomes and the development of self-regulation skills.

Learning Path App

In designing the learning path app, we follow the four phases of the COPES model to support learners with external cues following internal regulation processes. Regulation in the COPES model unfolds in four loosely coupled phases: i) in the task definition phase, learners develop an understanding of the task, ii) during the goal setting phase, learners set their goals and plan their learning, iii) in the enactment phase, learners execute their plans and control and monitor progress iv) in the adaptation phase, adjustments are made when progress towards the goals is not proceeding as planned.

Learner-faced dashboards function as a visual layer between the internal regulation of the learner and the external regulation support of the ALT. Their primary function is to support learners to explicitly engage in the four phases that are critical for successful self-regulation. As such, the different visualizations in the learning path app function as a reference for learners to better understand their own regulation process. In essence, the app is a mirror for learners to better monitor their progress and recognize the need for control actions and thus drive their internal regulation process, see below figure.

Afbeelding1

The learning path app contains 3 personalized visualizations (overview, goal setting and learning path) that are designed to support learners’ internal regulation. The visualizations are explicitly developed as external feedback to help learners to create a valid reference for their regulation process. Based on this reference learners can optimize their internal regulation process. In the learning path app, trace data from the ALT are used to provide learners with continuous feedback about their performance, progress and how progress towards their learning goal is related to their actions. In this way we extend the role of learner-faced dashboards from discussing what learners learned to also incorporate how learners have learned. Hence the learning path app is expected to be a first step towards developing a novel way to overcome learners’ utilization deficiencies in SRL.

Afbeelding1 Afbeelding11

Afbeelding1

Research outcomes

We have found that learners using the learning path app (PV condition) improved the regulation of their practice behavior, as indicated by higher accuracy and less complex moment-by-moment learning curves compared to learners in the control group. Learners in the PV condition showed better transfer on learning. Finally, students in the PV condition were more likely to under-estimate instead of over-estimate their performance. Overall, these findings indicates that the personalized visualizations improved regulation of practice behavior, transfer of learning and changed the bias in relative monitoring accuracy.

However, long-term effects of PV on the development of SRL skills could not be assessed in this study. To address this research question a longer-term intervention with the learning path app is needed.

Find the rest of the article here.