A Multimedia Adaptive Tutoring System for Mathematics that Addresses Cognition, Metacognition and Affect

A Hierarchical Bayesian Model of Adaptive Teaching

How do teachers learn about what learners already know? How do learners aid teachers by providing them with information about their background knowledge and what they find confusing? We formalize this collaborative reasoning process using a hierarchical Bayesian model of pedagogy. We then evaluate this model in two online behavioral experiments (N = 312 adults). In Experiment 1, we show that teachers select examples that account for learners' background knowledge, and adjust their examples based on learners' feedback. In Experiment 2, we show that learners strategically provide more feedback when teachers' examples deviate from their background knowledge. These findings provide a foundation for extending computational accounts of pedagogy to richer interactive settings.

Proactive and reactive engagement of artificial intelligence methods for education: a review

The education sector has benefited enormously through integrating digital technology driven tools and platforms. In recent years, artificial intelligence based methods are being considered as the next generation of technology that can enhance the experience of education for students, teachers, and administrative staff alike. The concurrent boom of necessary infrastructure, digitized data and general social awareness has propelled these efforts further. In this review article, we investigate how artificial intelligence, machine learning, and deep learning methods are being utilized to support the education process. We do this through the lens of a novel categorization approach. We consider the involvement of AI-driven methods in the education process in its entirety-from students admissions, course scheduling, and content generation in the proactive planning phase to knowledge delivery, performance assessment, and outcome prediction in the reactive execution phase. We outline and analyze the major research directions under proactive and reactive engagement of AI in education using a representative group of 195 original research articles published in the past two decades, i.e., 2003-2022. We discuss the paradigm shifts in the solution approaches proposed, particularly with respect to the choice of data and algorithms used over this time. We further discuss how the COVID-19 pandemic influenced this field of active development and the existing infrastructural challenges and ethical concerns pertaining to global adoption of artificial intelligence for education.

Cognitive training enhances growth mindset in children through plasticity of cortico-striatal circuits

Growth mindset, the belief that one's abilities can improve through cognitive effort, is an important psychological construct with broad implications for enabling children to reach their highest potential. However, surprisingly little is known about malleability of growth mindset in response to cognitive interventions in children and its neurobiological underpinnings. Here we address critical gaps in our knowledge by investigating behavioral and brain changes in growth mindset associated with a four-week training program designed to enhance foundational, academically relevant, cognitive skills in 7-10-year-old children. Cognitive training significantly enhanced children's growth mindset. Cross-lagged panel analysis of longitudinal pre- and post-training data revealed that growth mindset prior to training predicted cognitive abilities after training, providing support for the positive role of growth mindset in fostering academic achievement. We then examined training-induced changes in brain response and connectivity associated with problem solving in relation to changes in growth mindset. Children's gains in growth mindset were associated with increased neural response and functional connectivity of the dorsal anterior cingulate cortex, striatum, and hippocampus, brain regions crucial for cognitive control, motivation, and memory. Plasticity of cortico-striatal circuitry emerged as the strongest predictor of growth mindset gains. Taken together, our study demonstrates that children's growth mindset can be enhanced by cognitive training, and elucidates the potential neurobiological mechanisms underlying its malleability. Findings provide important insights into effective interventions that simultaneously promote growth mindset and learning during the early stages of cognitive development.

Automatic modeling of student characteristics with interaction and physiological data using machine learning: A review

Student characteristics affect their willingness and ability to acquire new knowledge. Assessing and identifying the effects of student characteristics is important for online educational systems. Machine learning (ML) is becoming significant in utilizing learning data for student modeling, decision support systems, adaptive systems, and evaluation systems. The growing need for dynamic assessment of student characteristics in online educational systems has led to application of machine learning methods in modeling the characteristics. Being able to automatically model student characteristics during learning processes is essential for dynamic and continuous adaptation of teaching and learning to each student's needs. This paper provides a review of 8 years (from 2015 to 2022) of literature on the application of machine learning methods for automatic modeling of various student characteristics. The review found six student characteristics that can be modeled automatically and highlighted the data types, collection methods, and machine learning techniques used to model them. Researchers, educators, and online educational systems designers will benefit from this study as it could be used as a guide for decision-making when creating student models for adaptive educational systems. Such systems can detect students' needs during the learning process and adapt the learning interventions based on the detected needs. Moreover, the study revealed the progress made in the application of machine learning for automatic modeling of student characteristics and suggested new future research directions for the field. Therefore, machine learning researchers could benefit from this study as they can further advance this area by investigating new, unexplored techniques and find new ways to improve the accuracy of the created student models.

The Intertwined Histories of Artificial Intelligence and Education

In this paper, I argue that the fields of artificial intelligence (AI) and education have been deeply intertwined since the early days of AI. Specifically, I show that many of the early pioneers of AI were cognitive scientists who also made pioneering and impactful contributions to the field of education. These researchers saw AI as a tool for thinking about human learning and used their understanding of how people learn to further AI. Furthermore, I trace two distinct approaches to thinking about cognition and learning that pervade the early histories of AI and education. Despite their differences, researchers from both strands were united in their quest to simultaneously understand and improve human and machine cognition. Today, this perspective is neither prevalent in AI nor the learning sciences. I conclude with some thoughts on how the artificial intelligence in education and learning sciences communities might reinvigorate this lost perspective.

The potential of learning with (and not from) artificial intelligence in education

AI-powered technologies are increasingly being developed for educational purposes to contribute to students' academic performance and overall better learning outcomes. This exploratory review uses the PRISMA approach to describe how the effectiveness of AI-driven technologies is being measured, as well as the roles attributed to teachers, and the theoretical and practical contributions derived from the interventions. Findings from 48 articles highlighted that learning outcomes were more aligned with the optimization of AI systems, mostly nested in a computer science perspective, and did not consider teachers in an active role in the research. Most studies proved to be atheoretical and practical contributions were limited to enhancing the design of the AI system. We discuss the importance of developing complementary research designs for AI-powered tools to be integrated optimally into education.

Mathematical modeling analysis on the dynamics of university students animosity towards mathematics with optimal control theory

Animosity towards mathematics is a very common worldwide problem and it is usually caused by wrong information, low participation, low challenge tolerance, falling further behind, being unemployed, and avoiding the advanced math classes needed for success in many careers. In this study, we have considered and formulated the new SEATS compartmental mathematical model with optimal control theory to analyze the dynamics of university students' animosity towards mathematics. We applied the next-generation matrix, Ruth-Hurwitz criteria, Lyapunov function, and Volterra-Lyapunov stable matrices to show local and global stability of equilibrium points of the model respectively. The study demonstrated that the animosity-free equilibrium point is both locally and globally asymptotically stable whenever the model basic reproduction number is less than unity, whereas the animosity-dominance equilibrium point is both locally and globally asymptotically stable when the model basic reproduction number is greater than unity. Finally, we applied numerical ode45 solvers using the Runge-Kutta method and we have carried out numerical simulations and shown that applying both prevention and treatment controls is the best strategy to minimize and possibly eradicate the animosity-infection in the community under consideration.

Jim Greer’s and Mary Mark’s Reviews of Evaluation Methods for Adaptive Systems: a Brief Comment about New Goals

Mark and Greer’s (International Journal of Artificial Intelligence in Education, 4(2/3), 129–153, 1993) review was very influential in setting out effective goals and methods for evaluating adaptive educational systems of all kinds. A later review brought the story up to date (Greer, International Journal of Artificial Intelligence in Education, 26(1), 387–392, 2016). The current paper explores a new range of evaluative goals which go beyond the quality of learning outcomes, learning efficiency, transfer, retention, and short-term motivation. While learner satisfaction has been downgraded over the years as a reliable indicator of learning quality, it cannot be wholly ignored in terms of wider issues such as the learner’s developing metacognitive and meta-affective insight, regulatory competence and longer-term motivation. These factors lead on to such evaluable issues as the learner’s appetite for further learning of the kind just experienced as well as for learning in general. The rise in the use of data analytics and the increasing use of AIED and computer-based learning systems in schools and universities has led to the development of orchestration systems to assist the teacher to manage their students using such systems. Orchestration systems raise new kinds of evaluation goal, such as the balance of activity, cooperation and agency between the human teacher and the adaptive systems, as well as between the learner, the systems, the teacher and, indeed, other learners. Further evaluable goals include the degree to which the teacher is alerted to the learning difficulties of the learners, the degree to which the teacher’s scarce and valuable time is being used efficiently, and the degree to which the orchestration system can be used as a reflective device for teachers to examine their own practice.

Simulating the dynamics of self-regulation, emotion, grit, and student performance in cyber-learning environments

This research presents the results of development and validation of the Cyclical Self-Regulated Learning (SRL) Simulation Model, a model of student cognitive and metacognitive experiences learning mathematics within an intelligent tutoring system (ITS). Patterned after Zimmerman and Moylan's (2009) Cyclical SRL Model, the Simulation Model depicts a feedback cycle connecting forethought, performance and self-reflection, with emotion hypothesized as a key determinant of student learning. A mathematical model was developed in steps, using data collected from students during their sessions within the ITS, developing solutions using structural equation modeling, and using these coefficients to calibrate a System Dynamics (SD) Simulation model. Results provide validation of the Cyclical SRL Model, confirming the interplay of grit, emotion, and performance in the ITS. The Simulation Model enables mathematical simulations depicting a variety of student background types and intervention styles and supporting deeper future explorations of dimensions of student learning.

Artificial Intelligence and Machine Learning: An Instructor’s Exoskeleton in the Future of Education

The role of artificial intelligence in US education is expanding. As education moves toward providing customized learning paths, the use of artificial intelligence (AI) and machine learning (ML) algorithms in learning systems increases. This can be viewed as growing metaphorical exoskeletons for instructors, enabling them to provide a higher level of guidance, feedback, and autonomy to learners. In turn, the instructor gains time to sense student needs and support authentic learning experiences that go beyond what AI and ML can provide. Applications of AI-based education technology support learning through automated tutoring, personalizing learning, assessing student knowledge, and automating tasks normally performed by the instructor. This technology raises questions about how it is best used, what data provides evidence of the impact of AI and ML on learning, and future directions in interactive learning systems. Exploration of the use of AI and ML for both co-curricular and independent learnings in content presentation and instruction; interactions, communications, and discussions; learner activities; assessment and evaluation; and co-curricular opportunities provide guidance for future research.

Using Robotics to Enhance Active Learning in Mathematics: A Multi-Scenario Study

The use of technology, which is linked to active learning strategies, can contribute to better outcomes in Mathematics education. We analyse the conditions that are necessary for achieving an effective learning of Mathematics, aided by a robotic platform. Within this framework, the question raised was “What are the conditions that promote effective active math learning with robotic support?” Interventions at different educational scenarios were carried in order to explore three educational levels: elementary, secondary, and high school. Qualitative and quantitative analyses were performed, comparing the control and treatment groups for all scenarios through examinations, direct observations, and testimonials. The findings point to three key conditions: level, motivation, and teacher training. The obtained results show a very favourable impact on the attention and motivation of the students, and they allow for establishing the conditions that need to be met for an effective relationship between the teacher and the technological tool, so that better learning outcomes in Mathematics are more likely to be obtained.

Integration of an intelligent tutoring system in a magnetic resonance simulator for education: Technical feasibility and user experience

BACKGROUND AND OBJECTIVE

In this paper we propose to include an intelligent tutoring system (ITS) within a magnetic resonance (MR) simulator that has been developed in house. With this, we intend to measure the impact, in terms of user experience, of including an ITS in our simulator.

METHODS

We thoroughly describe the integration procedure and we have tested the benefits of this integration by means of two actual educational experiences, with one of them using the simulator as a standalone tool, and the other with the joint use of simulator+ITS. The experiences have consisted of two online courses with a number of students around 180 in both of them, where measurements of usability, perceived utility and likelihood to recommend were collected.

RESULTS

We have observed that the three measurements improved noticeably in the second course with respect to the first one; specifically, overall usability improved by 22.3%, perceived utility by an average of 55.1% and likelihood to recommend by 13.7%. In addition, quantitative measurements are complemented with comments in free text format directly provided by the students. Results show evidence on the benefits of integrating an ITS in terms of quantitative user experience, as well as qualitative comparative comments directly by students of both courses.

CONCLUSIONS

This is the first time that an ITS is used within the scope of MR simulation for training purposes. Benefits of integrating an ITS within an MR simulator have been evaluated in terms of user experience, with satisfactory comparative results.

Out of the laboratory and into the classroom: the future of artificial intelligence in education

Like previous educational technologies, artificial intelligence in education (AIEd) threatens to disrupt the status quo, with proponents highlighting the potential for efficiency and democratization, and skeptics warning of industrialization and alienation. However, unlike frequently discussed applications of AI in autonomous vehicles, military and cybersecurity concerns, and healthcare, AI’s impacts on education policy and practice have not yet captured the public’s attention. This paper, therefore, evaluates the status of AIEd, with special attention to intelligent tutoring systems and anthropomorphized artificial educational agents. I discuss AIEd’s purported capacities, including the abilities to simulate teachers, provide robust student differentiation, and even foster socio-emotional engagement. Next, to situate developmental pathways for AIEd going forward, I contrast sociotechnical possibilities and risks through two idealized futures. Finally, I consider a recent proposal to use peer review as a gatekeeping strategy to prevent harmful research. This proposal serves as a jumping off point for recommendations to AIEd stakeholders towards improving their engagement with socially responsible research and implementation of AI in educational systems.

Accessible mathematics videos for non-disabled students in primary education

Our work applies Universal Design criteria for producing and using Mathematics videos for primary education students, at a time when many countries are shifting towards inclusive education policies. We have focused on how the accessibility criteria used for students with visual impairments might affect non-disabled students. For this, we reviewed applicable Universal Design principles as well as best practices in multimedia learning. We took into account the roles, procedures, tools and standards involved in the multimedia lifecycle. We then undertook an experiment consisting of producing two videos about prime numbers with the same pedagogical contents; one video was accessible for students with visual impairments and the other one was not accessible to them. We conducted a trial in real world school settings with 228 non-disabled children, who were randomly assigned a version, either accessible or not accessible, and were then asked to take a test to measure objective aspects of their learning concerning retention and transfer as well as several subjective aspects, including the attractiveness of the videos. Results indicate that there were no significant differences in the scores obtained by students using either video, although the group who watched the accessible video obtained higher score medians in the retention questions. Moreover, students found the accessible video significantly more attractive (p = 0.042). Our study provides recommendations for different stakeholders and stages within the process of producing multimedia mathematics materials that are accessible to primary students with visual impairments, as well as evidence demonstrating that everybody can benefit from the recommendations for developing good quality, accessible multimedia material.

Affect-Aware Adaptive Tutoring Based on Human-Automation Etiquette Strategies

OBJECTIVE

We investigated adapting the interaction style of intelligent tutoring system (ITS) feedback based on human-automation etiquette strategies.

BACKGROUND

Most ITSs adapt the content difficulty level, adapt the feedback timing, or provide extra content when they detect cognitive or affective decrements. Our previous work demonstrated that changing the interaction style via different feedback etiquette strategies has differential effects on students' motivation, confidence, satisfaction, and performance. The best etiquette strategy was also determined by user frustration.

METHOD

Based on these findings, a rule set was developed that systemically selected the proper etiquette strategy to address one of four learning factors (motivation, confidence, satisfaction, and performance) under two different levels of user frustration. We explored whether etiquette strategy selection based on this rule set (systematic) or random changes in etiquette strategy for a given level of frustration affected the four learning factors. Participants solved mathematics problems under different frustration conditions with feedback that adapted dynamic changes in etiquette strategies either systematically or randomly.

RESULTS

The results demonstrated that feedback with etiquette strategies chosen systematically via the rule set could selectively target and improve motivation, confidence, satisfaction, and performance more than changing etiquette strategies randomly. The systematic adaptation was effective no matter the level of frustration for the participant.

CONCLUSION

If computer tutors can vary the interaction style to effectively mitigate negative emotions, then ITS designers would have one more mechanism in which to design affect-aware adaptations that provide the proper responses in situations where human emotions affect the ability to learn.

Advances from the Office of Naval Research STEM Grand Challenge: expanding the boundaries of intelligent tutoring systems

This special issue presents evaluations of four intelligent tutoring systems. These systems were funded under the Office of Naval Research's STEM Grand Challenge for intelligent tutoring systems. The systems each represent aspects of how ITS can address STEM education or how aspects of multiple systems can be integrated to support STEM education. The selected papers also provide empirical evidence for the effectiveness of each system. The current paper provides an overview of the Office of Naval Research STEM Grand Challenge program, the systems funded under the program, and summaries of the articles within this special issue.