In this Information-explosion era, machine learning (ML) is indispensable for analyzing complex data in medicine, engineering and manufacturing, environmental science, materials science, and biology. These discipline fields have experienced a growing development in the last decade, driven mainly by new techniques for obtaining, processing, and modeling data. In this regard, ML has attracted many researchers in educational studies, integrating educational knowledge with data-driven techniques to extract relevant features from a large number of measurements. This trend has become more pronounced as the volume of educational data has increased exponentially from experimental and observational studies. The structural complexity of educational data ranges from simple observations to complex clusters, and national and regional survey data is often regarded as a massive volume of information stored in varied structures. Pursuing approaches for analyzing large-scale learning, assessment, biometric, or psychological data often involves researchers working in teams and contributing to multidisciplinary fields such as computational psychometrics that fuses theory-based psychometrics and data-driven ML-based computational models.
The current Research Topic comprises the application of ML to identify patterns and establish relationships to predict educational outcomes through data analysis. ML methods are usually classified into three categories, Supervised Learning, Unsupervised Learning, and Reinforcement Learning. ML enables machines to learn to make decisions from data with minimal or no human input and automatically govern the learning process. Researchers often employ ML methodologies to effectively interpret massively complex datasets. The application of ML in educational research is expected to provide unprecedented opportunities to enhance students’ learning outcomes, reduce intervention costs, and positively improve teaching quality. This topic involves applications of new approaches for discovering knowledge to support the decision-making process in an educational setting. It is related to developing innovative methods for analyzing data that come from an educational background and using those methods to better understand to stakeholders.
In this Research Topic, we will mainly focus on how ML can facilitate educational research in systematic reviews and primary and secondary data analysis utilizing models such as Random Forest, Bayesian Additive Regression Trees, Support Vector Machine, Neural Networks or Deep Learning, etc.
We want to invite you to submit Original research articles, Review or Mini-Review articles, and Perspective articles, related to themes that include (but are not limited to):
• Developing and integrating machine learning approaches for causal inference
• Data-Driven AI-based computational models for analyzing assessment data
• Educational data mining
• Educational evaluation with machine learning techniques
• Applications of machine learning algorithms
• Predicting students' progression with advanced statistical models
• Integrative approach in data analysis
• Modeling educational data
• Systematic review on machine learning applications
• Artificial intelligence for predicting educational outcomes
• Perspectives on the possibilities and challenges of applying ml in educational studies
• Reinforcement learning for education
In this Information-explosion era, machine learning (ML) is indispensable for analyzing complex data in medicine, engineering and manufacturing, environmental science, materials science, and biology. These discipline fields have experienced a growing development in the last decade, driven mainly by new techniques for obtaining, processing, and modeling data. In this regard, ML has attracted many researchers in educational studies, integrating educational knowledge with data-driven techniques to extract relevant features from a large number of measurements. This trend has become more pronounced as the volume of educational data has increased exponentially from experimental and observational studies. The structural complexity of educational data ranges from simple observations to complex clusters, and national and regional survey data is often regarded as a massive volume of information stored in varied structures. Pursuing approaches for analyzing large-scale learning, assessment, biometric, or psychological data often involves researchers working in teams and contributing to multidisciplinary fields such as computational psychometrics that fuses theory-based psychometrics and data-driven ML-based computational models.
The current Research Topic comprises the application of ML to identify patterns and establish relationships to predict educational outcomes through data analysis. ML methods are usually classified into three categories, Supervised Learning, Unsupervised Learning, and Reinforcement Learning. ML enables machines to learn to make decisions from data with minimal or no human input and automatically govern the learning process. Researchers often employ ML methodologies to effectively interpret massively complex datasets. The application of ML in educational research is expected to provide unprecedented opportunities to enhance students’ learning outcomes, reduce intervention costs, and positively improve teaching quality. This topic involves applications of new approaches for discovering knowledge to support the decision-making process in an educational setting. It is related to developing innovative methods for analyzing data that come from an educational background and using those methods to better understand to stakeholders.
In this Research Topic, we will mainly focus on how ML can facilitate educational research in systematic reviews and primary and secondary data analysis utilizing models such as Random Forest, Bayesian Additive Regression Trees, Support Vector Machine, Neural Networks or Deep Learning, etc.
We want to invite you to submit Original research articles, Review or Mini-Review articles, and Perspective articles, related to themes that include (but are not limited to):
• Developing and integrating machine learning approaches for causal inference
• Data-Driven AI-based computational models for analyzing assessment data
• Educational data mining
• Educational evaluation with machine learning techniques
• Applications of machine learning algorithms
• Predicting students' progression with advanced statistical models
• Integrative approach in data analysis
• Modeling educational data
• Systematic review on machine learning applications
• Artificial intelligence for predicting educational outcomes
• Perspectives on the possibilities and challenges of applying ml in educational studies
• Reinforcement learning for education
