Many students in primary education learn mathematics using adaptive learning technologies (ALTs) on tablets every day. Driven by developments in the emerging field of learning analytics, these technologies adjust problems based on learners' performance. Yet, until now it is largely unclear how students regulate their learning with ALTs. Hence, we explored how learners regulate their effort, accuracy and learning with an ALT using moment-by-moment learning curves. The results indicated that moment-by-moment learning curves did reflect students' accuracy and learning, but no associations with effort were found. Immediate drops were associated with high prior knowledge and suboptimal learning. Immediate peaks were associated with robust learning and pointed to effective student regulation. Close multiple spikes showed moderate learning and lower initial levels of accuracy but, with system support, these students seemed able to regulate their learning. Separated multiple spikes indicated reduced learning and accuracy and potentially signal the inability of students to regulate their learning. In this light, moment-by-moment learning curves seem to be valuable indicators of accuracy regulation during learning with ALTs and could potentially be used in interventions to support SRL with personalized visualizations.

There is a strong increase in the use of devices that measure physiological arousal through electrodermal activity (EDA). Although there is a long tradition of studying emotions during learning, researchers have only recently started to use EDA to measure emotions in the context of education and learning. This systematic review aimed to provide insight into how EDA is currently used in these settings. The review aimed to investigate the methodological aspects of EDA measures in educational research and synthesize existing empirical evidence on the relation of physiological arousal, as measured by EDA, with learning outcomes and learning processes. The methodological results pointed to considerable variation in the usage of EDA in educational research and indicated that few implicit standards exist. Results regarding learning revealed inconsistent associations between physiological arousal and learning outcomes, which seem mainly due to underlying methodological differences. Furthermore, EDA frequently fluctuated during different stages of the learning process. Compared to this unimodal approach, multimodal designs provide the potential to better understand these fluctuations at critical moments. Overall, this review signals a clear need for explicit guidelines and standards for EDA processing in educational research in order to build a more profound understanding of the role of physiological arousal during learning.

No abstract

This paper proposes a new approach to translate learner data into self-regulated learning support. Learning phases in blended classrooms place unique requirements on students' self-regulated learning (SRL). Learning path graphs merge moment-by-moment learning curves and learning phase data to understand student' SRL support needs. Results indicate 4 groups with different SRL support needs. Students in the self-regulated learning group are capable of learning without external regulation. In the teacher regulation group students need initial teacher regulation but rely on SRL thereafter. Students in the system regulation group require teacher and system regulation to learn. Finally, the advanced system support group is in need of support beyond the current level of system regulation. Based on these insights, the application of personalized dashboards and hybrid human-system regulation is further specified.

Although research indicates positive effects of Adaptive Learning Technologies (ALTs) on learning, we know little about young learners' regulation intentions in this context. Learners' intentions and self-evaluation determine the signals they deduce to drive self-regulated learning. This study had a twofold approach as it investigated the effect of feed-up and feed-forward reports on practice behavior and learning and explored learners' self-evaluation of goal-attainment, performance and accuracy. In the experimental condition, learners described their goals and self-evaluated their progress in feed-up and forward reports. We found no conclusive effects of the feedup and forward reports on learners' regulation of practice behavior and learning. Furthermore, results indicated that young learners' self-evaluations of goal attainment and performance were biased. Contrary to other research, we found learners both over-and underestimated performance which was strongly associated with over-or underestimation of goal attainment. Hence the signals learners used to drive regulation were often incorrect, tending to induce over-or under-practicing. Similarly, we found a bias in self-evaluation of accuracy and accuracy attainment. Learners over-or underestimated their accuracy, which was associated with over-or underestimation of accuracy attainment, which may in turn have affected effort regulation. We concluded that goal setting and self-evaluation in feed-up and forward reports was not enough to deduce valid regulatory signals. Our results indicate that young learners needed performance feedback to support correct self-evaluation and to correctly drive regulatory actions in ATLs.