Teaching and learning are passing through an era of exciting change, evolving from basic online learning serving small segments of students, to large scale MOOCs and adaptive and AI-supported learning permutations. As a subject, mathematics has witnessed a plethora of challenges and concerns at every level of education and is exposed to further investigation and revamp in light of the dynamic eduscape and new tools and technologies. To ensure that mathematics learning is systematic, adaptive, and personalized, educators have begun to deploy various analytics and analysis tools. Machine and deep learning are in the vanguard of artificial intelligence methods that have transformed every life domain, including the education sector. This Research Topic seeks to bring out the different trends in the usage of analytical and applied methods in various domains across the spectrum of education, with an emphasis on mathematics. From a tourism perspective where mathematics content and learning need is one-off, to primary schools where the need is for a solid knowledge of mathematics basics and fundamentals, to a higher education environment where the mathematics content keeps changing dynamically, we need assistive, smart, and adaptive systems underpinned by analytics and analysis. We seek to shed some light on the backend methods so that educators can benefit.
This Research Topic is focused on the analysis and analytics underpinning smart and adaptive learning, with a focus on mathematics education. Each problem/domain in adaptive/smart learning has its own analytical method that helps and creates new solutions to a problem. For example, it is not enough to say a smart algorithm was applied in robotics education to help primary school students to achieve better mathematics performance, but analyze the method using a 360-degree view to understand if the method was scalable, replicable and demonstrable in other settings or is unique to this domain. In a machine learning example, tremendous change is taking place whereby assistive technologies are having an impact on sustainable and inclusive learning. We need to highlight the impacts and evaluate these new players in the education sector by using analytics in light of the Sustainable Development Goals (SDGs). Big data and data analytics are making a powerful impact that needs to be understood and also disseminated. This kind of view is both needed and is missing in the current literature.
The aim of this Research Topic is to bring out the mathematical and analytical underpinnings of smart/adaptive/online learning. Topics are not limited by application domain or research area but must have a special focus on the mathematical methods and models of analytics/or analysis.
The topics we are interested in are:
• Smart learning analytics
• Modeling interaction between learning design and outcomes
• Mathematical models in educational environments
• Analysis of mathematical methods from Internet of Things applied to education
• Educational data mining
• Data Mining and big data analysis of education
• Intelligent systems for education and their analytical underpinnings
• Deep learning in education
• Machine learning models in learning
• Diagnostic and predictive analytics in educational processes
• Privacy based methods in education
• Computational models in education.
• Smart assessment and testing
• Smart education analytics
• Economics of smart education
• Small Personal Online Courses (SPOC) and its evaluation models
• Assessment and testing in smart e-learning
• Gamified models in smart learning
• Smart learner modeling
• Assistive technologies for mathematics.
• Activity recognition in Education
• Mathematics of Augmented and Virtual Reality
• Design Analytics of Smart Pedagogy
• Multimodal learning analytics
• Sentiment and emotional modeling in Smart learning
• Social learning analytics
The authors should follow the concept of reproducible research and publish both data and algorithms. The underlying data should be made accessible so it can be used by other authors, thus allowing comparison with other methods. Moreover, the underlying mathematical algorithms should be clearly described, documented, and made publicly available.
Teaching and learning are passing through an era of exciting change, evolving from basic online learning serving small segments of students, to large scale MOOCs and adaptive and AI-supported learning permutations. As a subject, mathematics has witnessed a plethora of challenges and concerns at every level of education and is exposed to further investigation and revamp in light of the dynamic eduscape and new tools and technologies. To ensure that mathematics learning is systematic, adaptive, and personalized, educators have begun to deploy various analytics and analysis tools. Machine and deep learning are in the vanguard of artificial intelligence methods that have transformed every life domain, including the education sector. This Research Topic seeks to bring out the different trends in the usage of analytical and applied methods in various domains across the spectrum of education, with an emphasis on mathematics. From a tourism perspective where mathematics content and learning need is one-off, to primary schools where the need is for a solid knowledge of mathematics basics and fundamentals, to a higher education environment where the mathematics content keeps changing dynamically, we need assistive, smart, and adaptive systems underpinned by analytics and analysis. We seek to shed some light on the backend methods so that educators can benefit.
This Research Topic is focused on the analysis and analytics underpinning smart and adaptive learning, with a focus on mathematics education. Each problem/domain in adaptive/smart learning has its own analytical method that helps and creates new solutions to a problem. For example, it is not enough to say a smart algorithm was applied in robotics education to help primary school students to achieve better mathematics performance, but analyze the method using a 360-degree view to understand if the method was scalable, replicable and demonstrable in other settings or is unique to this domain. In a machine learning example, tremendous change is taking place whereby assistive technologies are having an impact on sustainable and inclusive learning. We need to highlight the impacts and evaluate these new players in the education sector by using analytics in light of the Sustainable Development Goals (SDGs). Big data and data analytics are making a powerful impact that needs to be understood and also disseminated. This kind of view is both needed and is missing in the current literature.
The aim of this Research Topic is to bring out the mathematical and analytical underpinnings of smart/adaptive/online learning. Topics are not limited by application domain or research area but must have a special focus on the mathematical methods and models of analytics/or analysis.
The topics we are interested in are:
• Smart learning analytics
• Modeling interaction between learning design and outcomes
• Mathematical models in educational environments
• Analysis of mathematical methods from Internet of Things applied to education
• Educational data mining
• Data Mining and big data analysis of education
• Intelligent systems for education and their analytical underpinnings
• Deep learning in education
• Machine learning models in learning
• Diagnostic and predictive analytics in educational processes
• Privacy based methods in education
• Computational models in education.
• Smart assessment and testing
• Smart education analytics
• Economics of smart education
• Small Personal Online Courses (SPOC) and its evaluation models
• Assessment and testing in smart e-learning
• Gamified models in smart learning
• Smart learner modeling
• Assistive technologies for mathematics.
• Activity recognition in Education
• Mathematics of Augmented and Virtual Reality
• Design Analytics of Smart Pedagogy
• Multimodal learning analytics
• Sentiment and emotional modeling in Smart learning
• Social learning analytics
The authors should follow the concept of reproducible research and publish both data and algorithms. The underlying data should be made accessible so it can be used by other authors, thus allowing comparison with other methods. Moreover, the underlying mathematical algorithms should be clearly described, documented, and made publicly available.