Roger Azevedo

Prof. Dr. Roger Azevedo


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 June 2022 in Frontiers in Psychology
Verified
Journal Article
Open access
RARoger Azevedo
Roger Azevedo
FBFrançois Bouchet
François Bouchet
MDMelissa Duffy
Melissa Duffy
JHJason Harley
Jason Harley
MTMichelle Taub
Michelle Taub
RCRebeca Cerezo
Rebeca Cerezo
Self-regulated learning (SRL) is critical for learning across tasks, domains, and contexts. Despite its importance, research shows that not all learners are equally skilled at accurately and dynamically monitoring and regulating their self-regulatory processes. Therefore, learning technologies, such as intelligent tutoring systems (ITSs), have been designed to measure and foster SRL. This paper presents an overview of over 10 years of research on SRL with MetaTutor, a hypermedia-based ITS designed to scaffold college students’ SRL while they learn about the human circulatory system. MetaTutor’s architecture and instructional features are designed based on models of SRL, empirical evidence on human and computerized tutoring principles of multimedia learning, Artificial Intelligence (AI) in educational systems for metacognition and SRL, and research on SRL from our team and that of other researchers. We present MetaTutor followed by a synthesis of key research findings on the effectiveness of various versions of the system (e.g., adaptive scaffolding vs. no scaffolding of self-regulatory behavior) on learning outcomes. First, we focus on findings from self-reports, learning outcomes, and multimodal data (e.g., log files, eye tracking, facial expressions of emotion, screen recordings) and their contributions to our understanding of SRL with an ITS. Second, we elaborate on the role of embedded pedagogical agents (PAs) as external regulators designed to scaffold learners’ cognitive and metacognitive SRL strategy use. Third, we highlight and elaborate on the contributions of multimodal data in measuring and understanding the role of cognitive, affective, metacognitive, and motivational (CAMM) processes. Additionally, we unpack some of the challenges these data pose for designing real-time instructional interventions that scaffold SRL. Fourth, we present existing theoretical, methodological, and analytical challenges and briefly discuss lessons learned and open challenges.

3 June 2020 in Metacognition and Learning
Verified
Journal Article
Closed access
PDF file
RARoger Azevedo
Roger Azevedo

19 May 2023 in Metacognition and Learning
Verified
Journal Article
Closed access
PDF file
DDDaryn A. Dever
Daryn A. Dever
NSNathan A. Sonnenfeld
Nathan A. Sonnenfeld
MWMegan D. Wiedbusch
Megan D. Wiedbusch
SSS. Grace Schmorrow
S. Grace Schmorrow
Mary Jean AmonMary Jean Amon
Mary Jean Amon
RARoger Azevedo
Roger Azevedo

Verified
Journal Article
Open access
PDF file
DHDanial Hooshyar
Danial Hooshyar
RARoger Azevedo
Roger Azevedo
YYYeongwook Yang
Yeongwook Yang
Artificial neural networks (ANNs) have proven to be among the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, their educational potential is limited in practice due to challenges such as the following: (i) the difficulties in incorporating symbolic educational knowledge (e.g., causal relationships and practitioners’ knowledge) in their development, (ii) a propensity to learn and reflect biases, and (iii) a lack of interpretability. As education is classified as a ‘high-risk’ domain under recent regulatory frameworks like the EU AI Act—highlighting its influence on individual futures and discrimination risks—integrating educational insights into ANNs is essential. This ensures that AI applications adhere to essential educational restrictions and provide interpretable predictions. This research introduces NSAI, a neural-symbolic AI approach that integrates neural networks with knowledge representation and symbolic reasoning. It injects and extracts educational knowledge into and from deep neural networks to model learners’ computational thinking, aiming to enhance personalized learning and develop computational thinking skills. Our findings revealed that the NSAI approach demonstrates better generalizability compared to deep neural networks trained on both original training data and data enriched by SMOTE and autoencoder methods. More importantly, we found that, unlike traditional deep neural networks, which mainly relied on spurious correlations in their predictions, the NSAI approach prioritizes the development of robust representations that accurately capture causal relationships between inputs and outputs. This focus significantly reduces the reinforcement of biases and prevents misleading correlations in the models. Furthermore, our research showed that the NSAI approach enables the extraction of rules from the trained network, facilitating interpretation and reasoning during the path to predictions, as well as refining the initial educational knowledge. These findings imply that neural-symbolic AI not only overcomes the limitations of ANNs in education but also holds broader potential for transforming educational practices and outcomes through trustworthy and interpretable applications.

30 September 2023 in British Journal of Educational Technology
Verified
Journal Article
Open access
MSMarta Sobocinski
Marta Sobocinski
DDDaryn Dever
Daryn Dever
MWMegan Wiedbusch
Megan Wiedbusch
FMFoysal Mubarak
Foysal Mubarak
RARoger Azevedo
Roger Azevedo
SJSanna Järvelä
Sanna Järvelä
This study examines the embodied ways in which learners monitor their cognition while learning about exponential functions in an immersive virtual reality (VR) based game, Pandemic by Prisms of Reality. Traditionally, metacognitive monitoring has been assessed through behavioural traces and verbalised instances. When learning in VR, learners are fully immersed in the learning environment, actively manipulating it based on affordances designed to support learning, offering insights into the relationship between physical interaction and metacognition. The study collected multimodal data from 15 participants, including think‐aloud audio, bird's‐eye view video recordings and physiological data. Metacognitive monitoring was analysed through qualitative coding of the think‐aloud protocol, while movement was measured via optical flow analysis and cognitive load was assessed through heart rate variability analysis. The results revealed embodied metacognition by aligning the data to identify learners' physical states alongside their verbalised metacognition. The findings demonstrated a temporal interplay among cognitive load, metacognitive monitoring, and motion during VR‐based learning. Specifically, cognitive load, indicated by the low‐ and high‐frequency heart rate variability index, predicted instances of metacognitive monitoring, and monitoring predicted learners' motion while interacting with the VR environment. This study further provides future directions in understanding self‐regulated learning processes during VR learning by utilizing multimodal data to inform real‐time adaptive personalised support within these environments. Practitioner notes: What is already known about this topic Immersive virtual reality (VR) environments have the potential to offer personalised support based on users' individual needs and characteristics. Self‐regulated learning (SRL) involves learners monitoring their progress and strategically regulating their learning when needed. Multimodal data captured during VR learning, such as birds‐eye‐view video, screen recordings, physiological changes and verbalisations, can provide insights into learners' SRL processes and support needs. What this paper adds Provides insights into the embodied aspects of learners' metacognitive monitoring during learning in an immersive VR environment. Demonstrates how SRL processes can be captured via the collection and analysis of multimodal data, including think‐aloud audio, bird's‐eye view video recordings and physiological data, to capture metacognitive monitoring and movement during VR‐based learning. Contributes to the understanding of the interplay between cognitive load, metacognitive monitoring, and motion in immersive VR learning. Implications for practice and/or policy Researchers and practitioners can use the causal relationships identified in this study to identify instances of SRL in an immersive VR setting. Educational technology developers can consider the integration of online measures, such as cognitive load and physiological arousal, into adaptive VR environments to enable real‐time personalised support for learners based on their self‐regulatory needs.

28 October 2021 in Journal of Computing in Higher Education
Verified
Journal Article
Open access
PDF file
WCWilson Chango
Wilson Chango
RCRebeca Cerezo
Rebeca Cerezo
MSMiguel Sanchez-Santillan
Miguel Sanchez-Santillan
RARoger Azevedo
Roger Azevedo
CMCristóbal Romero Morales
Cristóbal Romero Morales
The aim of this study was to predict university students’ learning performance using different sources of performance and multimodal data from an Intelligent Tutoring System. We collected and preprocessed data from 40 students from different multimodal sources: learning strategies from system logs, emotions from videos of facial expressions, allocation and fixations of attention from eye tracking, and performance on posttests of domain knowledge. Our objective was to test whether the prediction could be improved by using attribute selection and classification ensembles. We carried out three experiments by applying six classification algorithms to numerical and discretized preprocessed multimodal data. The results show that the best predictions were produced using ensembles and selecting the best attributes approach with numerical data.