One approach that has been gaining significant attention among chemistry education scholars and practitioners is the employment of game-based learning to teach least-learned and difficult topics at various educational levels. One reason for this is that it promotes active, constructive learning and makes learning science a fun experience through…

This study contributes to a growing body of scholarship at the intersection of bilingual education and education policy and examines reclassification, or the transition out of formal English language services in schools, as one potential lever in accelerating or decelerating multilingual learners' science learning. More specifically, it traces…

Learning style (LS), either visual or verbal, has become debatable in the f ield of education vis-à-vis its relation to student success. However, it remains a valuable research theme for improving learning activities in the teaching of highly visual science fields, including biology, physics, and chemistry. Previous studies have primarily focused…

This paper introduces an approach that uses latent class analysis to identify cut scores (LCA-CS) and categorize respondents based on context scales derived from largescale assessments like PIRLS, TIMSS, and NAEP. Context scales use Likert scale items to measure latent constructs of interest and classify respondents into meaningful ordered…

This study examined the efficiency of using the same rating scale categories in measuring affective constructs for students with distinctive levels of achievement. Data used in this study came from the Trends in Mathematics and Science Study (TIMSS) 2011, as a case, on the three scales that were designed to measure eighth graders' attitudes…

This article presents a latent class model for multilevel data to identify latent subgroups and estimate heterogeneous treatment effects. Unlike sequential approaches that partition data first and then estimate average treatment effects (ATEs) within classes, we employ a Bayesian procedure to jointly estimate mixing probability, selection, and…

Understanding whether or not different types of students master various attributes can aid future learning remediation. In this study, two-level diagnostic classification models (DCMs) were developed to represent the probabilistic relationship between external latent classes and attribute mastery patterns. Furthermore, variational Bayesian (VB)…

Educational Data Mining (EDM) is an important tool in the field of classification of educational data that helps researchers and education planners analyse and model available educational data for specific needs such as developing educational strategies. Trends International Mathematics and Science Study (TIMSS) which is a notable study in…

According to the Felder and Silverman Learning Styles Model (FSM), students have learning preferences regarding how information is obtained, processed, perceived and understood. The Index of Learning Styles (ILS) is an online questionnaire created by Felder and Soloman to classify students according to their learning styles. With a priori…

Artificial Intelligence is widely used across contexts and for different purposes, including the field of education. However, a review of the literature showcases that while there exist various review studies on the use of AI in education, missing remains a review focusing on science education. To address this gap, we carried out a systematic…

There has been increasing interest in exploring heterogeneous treatment effects using machine learning (ML) methods such as causal forests, Bayesian additive regression trees, and targeted maximum likelihood estimation. However, there is little work on applying these methods to estimate treatment effects in latent classes defined by…

Families are active agents in school systems and apply different strategies of educational advantage to help their children succeed at school. These strategies are planned and enacted by families with their children in mind, but they are always a response to the broader education system design. This article explores how through their strategies…

In cognitive diagnosis assessment (CDA), the impact of misspecified item-attribute relations (or "Q-matrix") designed by subject-matter experts has been a great challenge to real-world applications. This study examined parameter estimation of the CDA with the expert-designed Q-matrix and two refined Q-matrices for international…

Automated scoring of free drawings or images as responses has yet to be used in large-scale assessments of student achievement. In this study, we propose artificial neural networks to classify these types of graphical responses from a TIMSS 2019 item. We are comparing classification accuracy of convolutional and feed-forward approaches. Our…

Knowledge space theory (KST) is a mathematical framework for modeling and assessing student knowledge. While KST has successfully served as the foundation of several learning systems, recent advancements in machine learning provide an opportunity to improve on purely KST-based approaches to assessing student knowledge. As such, in this work we…