Maria Bannert
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maria Bannert has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Christian Hartmann
Chair of Teaching and Learning with Digital Media, Technical University of Munich, Munich, Germany
7 shared publications - Lyn Lim
Center of Advanced Technology for Assisted Learning and Predictive Analytics (CATALPA), FernUniversität in Hagen, Hagen, Germany
7 shared publications - Dragan Gašević
Centre for Learning Analytics, Faculty of Information Technology, Monash University, Melbourne, Australia
6 shared publications - Mladen Raković
Centre for Learning Analytics Monash University Melbourne Victoria Australia
6 shared publications - Inge Molenaar
NOLAI | National Education Lab AI, Behavioural Science Institute, Radboud University, Nijmegen, Netherlands
5 shared publications - Joep van der Graaf
Behavioural Science Institute Radboud University Nijmegen The Netherlands
3 shared publications
Latest Publications
- Open Access
- 5 October 2026
- Published by Springer Nature in Metacognition and Learning
- Vol. 21 (1) , 51
Effects of a self-regulated learning training on adolescents’ metacognitive awareness, learning processes and outcomes: a multi-method perspective
Adolescence represents an important developmental phase for self-regulated learning (SRL), marked by uneven growth in metacognitive knowledge, awareness, and regulatory skills. Research on supporting adolescents’ emerging SRL is particularly relevant in online learning environments (OLEs), where autonomous regulation is essential, but remains limited. This quasi-experimental field study examined immediate effects of a brief digital SRL training on secondary school students’ metacognitive awareness, learning outcomes, and regulatory processes during an online essay-writing task. The experimental group (EG; n = 37) received SRL training before the task, while a control group (CG; n = 32) received comparable training on ergonomics. Results showed significantly higher metacognitive awareness in the EG, but no effects on essay performance, domain-knowledge gains, or learning transfer. Process analyses revealed that the EG spent more time on task orientation, and prior domain knowledge (PK) moderated training effects on cognitive processes; in the EG, rereading and writing frequencies decreased with increasing PK, whereas they showed slight increases in the CG. Within-group associations showed more consistent positive links between PK and learning outcomes in the EG. Sequence analyses further suggested that successful EG students with different PK levels followed partly distinct regulatory pathways: high-PK students displayed metacognitive process sequences, whereas low-PK students relied more on planning-intensive mixed sequences. Overall, findings suggest that a brief SRL training can foster metacognitive awareness and selected regulatory behaviors, while highlighting the need for adaptive and temporally sensitive SRL support for adolescent learners. The study demonstrates the value of multi-method, process-oriented perspectives for informing future SRL intervention designs.
- 5 October 2026
- Published by Springer Nature in Metacognition and Learning
- Vol. 21 (1) , 51
Open AccessEffects of a self-regulated learning training on adolescents’ metacognitive awareness, learning processes and outcomes: a multi-method perspective
Adolescence represents an important developmental phase for self-regulated learning (SRL), marked by uneven growth in metacognitive knowledge, awareness, and regulatory skills. Research on supporting adolescents’ emerging SRL is particularly relevant in online learning environments (OLEs), where autonomous regulation is essential, but remains limited. This quasi-experimental field study examined immediate effects of a brief digital SRL training on secondary school students’ metacognitive awareness, learning outcomes, and regulatory processes during an online essay-writing task. The experimental group (EG; n = 37) received SRL training before the task, while a control group (CG; n = 32) received comparable training on ergonomics. Results showed significantly higher metacognitive awareness in the EG, but no effects on essay performance, domain-knowledge gains, or learning transfer. Process analyses revealed that the EG spent more time on task orientation, and prior domain knowledge (PK) moderated training effects on cognitive processes; in the EG, rereading and writing frequencies decreased with increasing PK, whereas they showed slight increases in the CG. Within-group associations showed more consistent positive links between PK and learning outcomes in the EG. Sequence analyses further suggested that successful EG students with different PK levels followed partly distinct regulatory pathways: high-PK students displayed metacognitive process sequences, whereas low-PK students relied more on planning-intensive mixed sequences. Overall, findings suggest that a brief SRL training can foster metacognitive awareness and selected regulatory behaviors, while highlighting the need for adaptive and temporally sensitive SRL support for adolescent learners. The study demonstrates the value of multi-method, process-oriented perspectives for informing future SRL intervention designs.
- Open Access
- 21 September 2026
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 42 (5)
Trace Data of Secondary Students and Linguistic Analysis to Predict Learner Performance in a Multi‐Text Writing Task
Background: Writing from multiple sources is a cognitively demanding task that requires students to integrate reading, planning, and composition processes. While prior research has demonstrated the importance of self‐regulated learning (SRL) and linguistic features in predicting writing performance, most studies have focused on university students, with limited research targeting secondary school learners, particularly across multilingual contexts. Objective: This study examined whether SRL processes derived from trace data and linguistic features from essays as learning products can be used to predict writing performance among secondary students from different countries and language backgrounds. Methods: A total of 257 secondary students from Australia, Colombia, Germany, and Finland completed a multi‐source essay task in their school language within a digital learning environment. SRL processes were inferred from interaction trace data, while essay features—topic coverage, cohesion, and word count—were extracted using language‐specific analysis models. These data sources were then used to train several machine learning models to predict students' performance on essay writing. Results: Among the machine learning models tested, the Random Forest classifier achieved the highest accuracy (0.80) and recall (0.71). The most influential predictors were elaboration/organisation (process), topic coverage and cohesion (product), and country. Results revealed distinct engagement patterns across countries, suggesting that language and educational context were associated with differences in both SRL processes and writing quality. Conclusions: This study extends prior work by demonstrating that combining process and product features can support the prediction of writing performance across multilingual secondary education contexts. Findings emphasise the need for further research on younger learners and the role of linguistic background in SRL engagement.
- 21 September 2026
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 42 (5)
Open AccessTrace Data of Secondary Students and Linguistic Analysis to Predict Learner Performance in a Multi‐Text Writing Task
Background: Writing from multiple sources is a cognitively demanding task that requires students to integrate reading, planning, and composition processes. While prior research has demonstrated the importance of self‐regulated learning (SRL) and linguistic features in predicting writing performance, most studies have focused on university students, with limited research targeting secondary school learners, particularly across multilingual contexts. Objective: This study examined whether SRL processes derived from trace data and linguistic features from essays as learning products can be used to predict writing performance among secondary students from different countries and language backgrounds. Methods: A total of 257 secondary students from Australia, Colombia, Germany, and Finland completed a multi‐source essay task in their school language within a digital learning environment. SRL processes were inferred from interaction trace data, while essay features—topic coverage, cohesion, and word count—were extracted using language‐specific analysis models. These data sources were then used to train several machine learning models to predict students' performance on essay writing. Results: Among the machine learning models tested, the Random Forest classifier achieved the highest accuracy (0.80) and recall (0.71). The most influential predictors were elaboration/organisation (process), topic coverage and cohesion (product), and country. Results revealed distinct engagement patterns across countries, suggesting that language and educational context were associated with differences in both SRL processes and writing quality. Conclusions: This study extends prior work by demonstrating that combining process and product features can support the prediction of writing performance across multilingual secondary education contexts. Findings emphasise the need for further research on younger learners and the role of linguistic background in SRL engagement.
- Open Access
- 9 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 303-309
Diagnosing Debugging: The ECDM Framework for Designing Diagnostic Cases in Simulation-Based Teacher Training
Debugging is a central yet challenging activity for novice programmers, and diagnosing students' debugging difficulties places high demands on teachers under time pressure. Research shows that especially novice teachers often struggle to diagnose such situations in a precise and meaningful way. Although simulation-based approaches have proven effective for fostering diagnostic skills in other domains, they remain underexplored in computer science (CS) teacher education, also lacking theory-driven structures for designing diagnostically rich debugging cases. % To this end this paper introduces the ECDM Framework, a conceptual framework for constructing and analyzing realistic diagnostic cases for debugging situations. It integrates four core dimensions, Error, Cause, Debugging process, and Motivational-affective trajectory, to capture essential aspects of authentic debugging situations while allowing controlled complexity. The paper illustrates how the framework can be applied and discusses its potential to support teachers' diagnostic skills in debugging.
- 9 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 303-309
Open AccessDiagnosing Debugging: The ECDM Framework for Designing Diagnostic Cases in Simulation-Based Teacher Training
Debugging is a central yet challenging activity for novice programmers, and diagnosing students' debugging difficulties places high demands on teachers under time pressure. Research shows that especially novice teachers often struggle to diagnose such situations in a precise and meaningful way. Although simulation-based approaches have proven effective for fostering diagnostic skills in other domains, they remain underexplored in computer science (CS) teacher education, also lacking theory-driven structures for designing diagnostically rich debugging cases. % To this end this paper introduces the ECDM Framework, a conceptual framework for constructing and analyzing realistic diagnostic cases for debugging situations. It integrates four core dimensions, Error, Cause, Debugging process, and Motivational-affective trajectory, to capture essential aspects of authentic debugging situations while allowing controlled complexity. The paper illustrates how the framework can be applied and discusses its potential to support teachers' diagnostic skills in debugging.
- 1 June 2026
- Published by Verlag Julius Klinkhardt GmbH & Co. KG
- p. 110-127
Blickbewegungen in VR-Dashboards als Grundlage Pädagogischer Entscheidungen
In VR-Lernumgebungen fehlen Lehrenden Beobachtungsmöglichkeiten zur Diagnostik von Lernprozessen, da Interaktionen und Aufmerksamkeitsprozesse der Lernenden in der VR-Umgebung nicht unmittelbar sichtbar sind. Blickbewegungsdaten bieten neue diagnostische Potenziale. Bisher ist jedoch unklar, wie solche Daten dafür genutzt werden können. In einer explorativen Studie wurde untersucht, wie ein VR-Dashboard mit Blickbewegungsdaten zur Unterrichtsplanung genutzt werden kann. Daraus werden Designempfehlungen für Dashboards abgeleitet, die Lehrpersonen beim Einsatz von Blickdaten in VR unterstützen.
- 1 June 2026
- Published by Verlag Julius Klinkhardt GmbH & Co. KG
- p. 110-127
Blickbewegungen in VR-Dashboards als Grundlage Pädagogischer Entscheidungen
In VR-Lernumgebungen fehlen Lehrenden Beobachtungsmöglichkeiten zur Diagnostik von Lernprozessen, da Interaktionen und Aufmerksamkeitsprozesse der Lernenden in der VR-Umgebung nicht unmittelbar sichtbar sind. Blickbewegungsdaten bieten neue diagnostische Potenziale. Bisher ist jedoch unklar, wie solche Daten dafür genutzt werden können. In einer explorativen Studie wurde untersucht, wie ein VR-Dashboard mit Blickbewegungsdaten zur Unterrichtsplanung genutzt werden kann. Daraus werden Designempfehlungen für Dashboards abgeleitet, die Lehrpersonen beim Einsatz von Blickdaten in VR unterstützen.
- Open Access
- 23 February 2026
- Published by Adelaide University in Learning Letters
- Vol. 8, 61
How do students regulate their learning with a genAI chatbot?
Self-regulated learning (SRL) is essential for effective learning, yet students often struggle to regulate in digital environments, including suboptimal learning tool use. The rapid integration of generative AI (e.g., ChatGPT) into learning settings raises questions about their role in supporting or hindering SRL. This exploratory study investigated how students’ SRL in a technology-enhanced learning environment with a genAI tool was associated with learning processes and performance. Thirty university students were tasked to read texts and write an essay within 45 minutes. Learning performance was measured using knowledge and transfer tests, and the essay. SRL processes were measured using trace-based SRL event analysis and learner-genAI interaction with chatbot log events and coded queries. Most students (73%) used the chatbot voluntarily, primarily for seeking information. Chatbot users achieved higher essay scores than non-users. Chatbot interaction frequencies correlated positively with high cognitive activities; durations of chatbot use and high cognition negatively correlated with reading time. Qualitative data indicated reliance on the chatbot to summarise and extract key points, suggesting offloading of learning. Findings highlight potential performance benefits but also risks of outsourcing critical SRL processes to genAI. Implications point to instructional and tool design that align technological advances with educational fit.
- 23 February 2026
- Published by Adelaide University in Learning Letters
- Vol. 8, 61
Open AccessHow do students regulate their learning with a genAI chatbot?
Self-regulated learning (SRL) is essential for effective learning, yet students often struggle to regulate in digital environments, including suboptimal learning tool use. The rapid integration of generative AI (e.g., ChatGPT) into learning settings raises questions about their role in supporting or hindering SRL. This exploratory study investigated how students’ SRL in a technology-enhanced learning environment with a genAI tool was associated with learning processes and performance. Thirty university students were tasked to read texts and write an essay within 45 minutes. Learning performance was measured using knowledge and transfer tests, and the essay. SRL processes were measured using trace-based SRL event analysis and learner-genAI interaction with chatbot log events and coded queries. Most students (73%) used the chatbot voluntarily, primarily for seeking information. Chatbot users achieved higher essay scores than non-users. Chatbot interaction frequencies correlated positively with high cognitive activities; durations of chatbot use and high cognition negatively correlated with reading time. Qualitative data indicated reliance on the chatbot to summarise and extract key points, suggesting offloading of learning. Findings highlight potential performance benefits but also risks of outsourcing critical SRL processes to genAI. Implications point to instructional and tool design that align technological advances with educational fit.
- Open Access
- 9 January 2026
- Published by Elsevier in Computers & Education: X Reality
- Vol. 8
Seeing the whole picture? An experiment on environmental detail and coherence formation in immersive virtual reality
- 9 January 2026
- Published by Elsevier in Computers & Education: X Reality
- Vol. 8
Open AccessSeeing the whole picture? An experiment on environmental detail and coherence formation in immersive virtual reality
- Top Cited PapersOpen Access
- 23 January 2025
- Published by Society for Learning Analytics Research in Journal of Learning Analytics
- Vol. 12 (1) , 391-413
FLoRA Engine
The focus of education is increasingly on learners’ ability to regulate their own learning within technology-enhanced learning environments. Prior research has shown that self-regulated learning (SRL) leads to better learning performance. However, many learners struggle to productively self-regulate their learning, as they typically need to navigate the myriad of cognitive, metacognitive, and motivational processes that SRL demands. To address these challenges, the FLoRA engine is developed to help students, workers, and professionals improve their SRL skills and become productive lifelong learners. FLoRA incorporates several learning tools that are grounded in SRL theory and enhanced with learning analytics (LA), aimed at improving learners’ mastery of different SRL skills. The engine tracks learners’ SRL behaviours during a learning task and provides automated scaffolding to help learners effectively regulate their learning. The main contributions of FLoRA include (1) creating instrumentation tools that unobtrusively collect intensively sampled, fine-grained, and temporally ordered trace data about learners’ learning actions; (2) building a trace parser that uses LA and related analytical techniques (e.g., process mining) to model and understand learners’ SRL processes; and (3) providing a scaffolding module that presents analytics-based adaptive, personalized scaffolds based on students’ learning progress. The architecture and implementation of the FLoRA engine are also discussed in this paper.
- 23 January 2025
- Published by Society for Learning Analytics Research in Journal of Learning Analytics
- Vol. 12 (1) , 391-413
Top Cited PapersOpen AccessFLoRA Engine
The focus of education is increasingly on learners’ ability to regulate their own learning within technology-enhanced learning environments. Prior research has shown that self-regulated learning (SRL) leads to better learning performance. However, many learners struggle to productively self-regulate their learning, as they typically need to navigate the myriad of cognitive, metacognitive, and motivational processes that SRL demands. To address these challenges, the FLoRA engine is developed to help students, workers, and professionals improve their SRL skills and become productive lifelong learners. FLoRA incorporates several learning tools that are grounded in SRL theory and enhanced with learning analytics (LA), aimed at improving learners’ mastery of different SRL skills. The engine tracks learners’ SRL behaviours during a learning task and provides automated scaffolding to help learners effectively regulate their learning. The main contributions of FLoRA include (1) creating instrumentation tools that unobtrusively collect intensively sampled, fine-grained, and temporally ordered trace data about learners’ learning actions; (2) building a trace parser that uses LA and related analytical techniques (e.g., process mining) to model and understand learners’ SRL processes; and (3) providing a scaffolding module that presents analytics-based adaptive, personalized scaffolds based on students’ learning progress. The architecture and implementation of the FLoRA engine are also discussed in this paper.
- Open Access
- 2 June 2024
- Published by Springer Nature in Discover Education
- Vol. 3 (1) , 1-23
Enhancing knowledge construction in emerging technologies: the role of imagination training in immersive virtual reality environments
In the rapidly evolving landscape of educational technologies, Immersive Virtual Reality (iVR) stands out as a transformative tool for teaching and learning. The learner must actively engage, particularly when visual and auditory knowledge information is presented simultaneously. Generative learning strategies support learners in processing and integrating the information provided effectively and help them select, organize, and integrate information into a coherent mental model. Yet, learners often do not use such strategies spontaneously, so pre-training of the learning strategy is recommendable. IVR provides a spatial context for learning, where an essential strategy for promoting learning is to integrate auditory knowledge information into visually perceived space. We hypothesize that this can be done effectively through imagination, i.e., learners mentally visualize auditory information. This study investigated an imaginative pre-training strategy that targets integrating visual-spatial and auditory knowledge information. In a pre-post between-subjects design, we tested the effects of imaginative strategy pre-training. Students received either a pre-training (EG = 30) or no training (CG = 30) before exploring an iVR learning environment. Against our expectations, the EG did not outperform the CG on semantic and spatial knowledge. These findings may be explained by the demands on learners to process sensory input, and focus directed attention in a spatial iVR environment, suggesting that imagination strategies need to be anchored and complemented by other selection and organization strategies. This study contributes to a critical understanding of the possibilities and limitations of iVR in education, shedding light on the learners' processes and needs.
- 2 June 2024
- Published by Springer Nature in Discover Education
- Vol. 3 (1) , 1-23
Open AccessEnhancing knowledge construction in emerging technologies: the role of imagination training in immersive virtual reality environments
In the rapidly evolving landscape of educational technologies, Immersive Virtual Reality (iVR) stands out as a transformative tool for teaching and learning. The learner must actively engage, particularly when visual and auditory knowledge information is presented simultaneously. Generative learning strategies support learners in processing and integrating the information provided effectively and help them select, organize, and integrate information into a coherent mental model. Yet, learners often do not use such strategies spontaneously, so pre-training of the learning strategy is recommendable. IVR provides a spatial context for learning, where an essential strategy for promoting learning is to integrate auditory knowledge information into visually perceived space. We hypothesize that this can be done effectively through imagination, i.e., learners mentally visualize auditory information. This study investigated an imaginative pre-training strategy that targets integrating visual-spatial and auditory knowledge information. In a pre-post between-subjects design, we tested the effects of imaginative strategy pre-training. Students received either a pre-training (EG = 30) or no training (CG = 30) before exploring an iVR learning environment. Against our expectations, the EG did not outperform the CG on semantic and spatial knowledge. These findings may be explained by the demands on learners to process sensory input, and focus directed attention in a spatial iVR environment, suggesting that imagination strategies need to be anchored and complemented by other selection and organization strategies. This study contributes to a critical understanding of the possibilities and limitations of iVR in education, shedding light on the learners' processes and needs.
- Open Access
- 10 January 2024
- Published by Wiley in British Journal of Educational Technology
- Vol. 55 (4) , 1747-1771
Towards prescriptive analytics of self‐regulated learning strategies: A reinforcement learning approach
Self‐regulated learning (SRL) is an essential skill to achieve one's learning goals. This is particularly true for online learning environments (OLEs) where the support system is often limited compared to a traditional classroom setting. Likewise, existing research has found that learners often struggle to adapt their behaviour to the self‐regulatory demands of OLEs. Even so, existing SRL analysis tools have limited utility for real‐time or individualised support of a learner's SRL strategy during a study session. Accordingly, we explore a reinforcement learning based approach to learning optimal SRL strategies for a specific learning task. Specifically, we utilise the sequences of SRL processes acted by 44 participants, and their assessment scores for a prescribed learning task, in a purpose‐built OLE to develop a long short‐term memory (LSTM) network based reward function. This is used to train a reinforcement learning agent to find the optimal sequence of SRL processes for the learning task. Our findings indicate that the developed agents were able to effectively select SRL processes so as to maximise a prescribed learning goal as measured by predicted assessment score and predicted knowledge gains. The contributions of this work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualised SRL focused scaffolding. Practitioner notes: What is already known about this topic Learners often fail to adequately adapt their behavior to the self‐regulatory demands of e‐Learning environments. In order to promote effective Self‐regulated learning (SRL) capabilities, researchers and educators need tools that are able to analyze and diagnose a learner's SRL strategy use. Current methods for SRL analysis are more often descriptive as opposed to prescriptive and have limited utility for real‐time analysis or support of a learner's SRL behavior. What this paper adds This paper proposes the use of Reinforcement Learning for prescriptive analytics of SRL. We train a Reinforcement Learning agent on sequences of SRL processes acted by learners in order to learn the optimal SRL strategy for a given learning task. Implications for practice and/or policy Our work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualized SRL focused scaffolding. The implications of our work can aid in course design by predicting the self‐regulatory load imposed by a given task. The ability to model SRL strategies using Reinforcement Learning can be extended to simulate or test SRL theories.
- 10 January 2024
- Published by Wiley in British Journal of Educational Technology
- Vol. 55 (4) , 1747-1771
Open AccessTowards prescriptive analytics of self‐regulated learning strategies: A reinforcement learning approach
Self‐regulated learning (SRL) is an essential skill to achieve one's learning goals. This is particularly true for online learning environments (OLEs) where the support system is often limited compared to a traditional classroom setting. Likewise, existing research has found that learners often struggle to adapt their behaviour to the self‐regulatory demands of OLEs. Even so, existing SRL analysis tools have limited utility for real‐time or individualised support of a learner's SRL strategy during a study session. Accordingly, we explore a reinforcement learning based approach to learning optimal SRL strategies for a specific learning task. Specifically, we utilise the sequences of SRL processes acted by 44 participants, and their assessment scores for a prescribed learning task, in a purpose‐built OLE to develop a long short‐term memory (LSTM) network based reward function. This is used to train a reinforcement learning agent to find the optimal sequence of SRL processes for the learning task. Our findings indicate that the developed agents were able to effectively select SRL processes so as to maximise a prescribed learning goal as measured by predicted assessment score and predicted knowledge gains. The contributions of this work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualised SRL focused scaffolding. Practitioner notes: What is already known about this topic Learners often fail to adequately adapt their behavior to the self‐regulatory demands of e‐Learning environments. In order to promote effective Self‐regulated learning (SRL) capabilities, researchers and educators need tools that are able to analyze and diagnose a learner's SRL strategy use. Current methods for SRL analysis are more often descriptive as opposed to prescriptive and have limited utility for real‐time analysis or support of a learner's SRL behavior. What this paper adds This paper proposes the use of Reinforcement Learning for prescriptive analytics of SRL. We train a Reinforcement Learning agent on sequences of SRL processes acted by learners in order to learn the optimal SRL strategy for a given learning task. Implications for practice and/or policy Our work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualized SRL focused scaffolding. The implications of our work can aid in course design by predicting the self‐regulatory load imposed by a given task. The ability to model SRL strategies using Reinforcement Learning can be extended to simulate or test SRL theories.