Machine learning methods for predictive analytics have great potential for uncovering trends in educational data. However, simple linear models still appear to be most widely used, in part, because of their interpretability. This study aims to address the issues of interpretability of complex machine learning classifiers by conducting feature…

This paper addresses dynamical interdependence among the actions of group members. I assume that the actions of each member can be represented as nodes of a dynamical network and then collect the nodes into disjoint subsets (components) representing the individual group members. Interdependence among group members' actions can then be defined with…

Violations of normality and homogeneity are common in educational data. When this occurs, the use of parametric statistics may be inappropriate. A generalized form of nonparametric analyses based on the Puri and Sen L statistic provides an alternative approach. Using a chi-square distribution, this technique is easy to apply and has significant…

Online information is not regulated for quality of content or accuracy; therefore, content found online is not always complete, accurate, or unbiased. While media-literacy education exists, educators often only see the final result of students' online research in the form of the assignment or a works cited page. For teachers to address the media…

This study developed a learning system that allows teachers to edit assignments designed to teach students the text structure strategy through the use of four phases: instructing, modeling, practicing, and reflecting. A 7-week instructional experiment was conducted in which 84 12th-grade students learned the text structure strategy using this…

New educational technologies present an opportunity to help teachers monitor and support their students remotely in Science, Technology, Engineering, and Mathematics (STEM). However, most technologies do not have the capacity to comprehensively assess and report on students' critical 21st century practice competencies (such as those described in…

Systematic endeavors to take computer science (CS) and computational thinking (CT) to scale in middle and high school classrooms are underway with curricula that emphasize the enactment of authentic CT skills, especially in the context of programming in block-based programming environments. There is, therefore, a growing need to measure students'…

Due to the COVID-19 restrictions, high-schools in Spain are having both online and in-class lectures. As a result, the students can use not only the information provided by the teachers in class, but they can also use several other methods such as videos and online examples that allow the students to have materials from different places. In this…

This study implemented a data-driven approach to identify Chinese high school students' common errors in a Java-based introductory programming course using the data in an automated assessment tool called the Mulberry. Students' error-related behaviors were also analyzed, and their relationships to success in introductory programming were…

Open, flexible and distance learning has become part of mainstream education in China. Using a blended learning program in a Chinese high school as the case, this study adopted data-mining approaches to establish predictive models using personality traits. Results showed that, for students with high OE and low extraversion, and students who are…

The integration of computational modelling in science classrooms provides a unique opportunity to promote key 21st century skills including computational thinking (CT) and collaboration. The open-ended, problem-solving nature of the task requires groups to grapple with the combination of two domains (science and computing) as they collaboratively…

It is challenging to utilize learning analytic technologies to examine gameplay log data for game-embedded assessment in the field of game-based learning. Analytical approaches based on a new perspective focusing on complicated contextual data are imperative in the current scenario. A relatively new concept called precision education, which…

"Biometrics" are physical or behavioral human characteristics that can be used to identify a person. It is widely known that keystroke or typing dynamics for short, fixed texts (e.g., passwords) could serve as a behavioral biometric. In this study, we investigate whether keystroke data from essay responses can lead to a reliable…

Understanding the factors that influence students' results in hybrid learning environments is becoming increasingly important in today's educational environment. The goal of this research is to examine factors that influence students' academic performance as well as their level of participation in blended learning environments. A comprehensive…

This paper investigates the role of the physical classroom environment, coupled with a technology environment that includes real-time agents and data analytics, to support the orchestration of complex collaborative inquiry designs in a high school physics classroom. This design-based research contributes to the wider domain of scripting and…