Increased use of computer-based assessments has facilitated data collection processes that capture both response product data (i.e., correct and incorrect) and response process data (e.g., time-stamped action sequences). Evidence suggests a strong relationship between respondents' correct/incorrect responses and their problem-solving proficiency…

This dissertation examines the effectiveness of machine learning algorithms and feature engineering techniques for analyzing process data and predicting test performance. The study compares three classification approaches and identifies item-specific process features that are highly predictive of student performance. The findings suggest that…

The automated classification of examination questions based on Bloom's Taxonomy (BT) aims to assist the question setters so that high-quality question papers are produced. Most studies to automate this process adopted the machine learning approach, and only a few utilised the deep learning approach. The pre-trained contextual and non-contextual…

This study, framed by dignity-focused language policy and intersectional anti-adultism, investigates how 74 adults misclassified as English learners (ELs) during U.S. K-12 education conceptualize essential knowledge for educating bilingual students. Through semi-structured interviews, participants stressed two key areas for schools that serve…

Autism spectrum disorder (ASD) is characterized by impairments in many functional areas requiring long-term interventions to promote autonomy. This study aims to map The Sensory Profile™ 2 (SP-2), one of the most widely used assessment tools in children with ASD, with the International Classification of Functioning, Disability and Health for…

False alarming, or detecting an error when there is not one, is a pervasive problem across numerous industries. The present study investigated the role of elaboration, or additional information about non-error differences in complex visual displays, for mitigating false error responding. In Experiment 1, learners studied errors and non-error…

Recent developments in the use of large-language models have led to substantial improvements in the accuracy of content-based automated scoring of free-text responses. The reported accuracy levels suggest that automated systems could have widespread applicability in assessment. However, before they are used in operational testing, other aspects of…

In scholarly research, racial categories are typically taken for granted. However, race categories vary over time and geography and reflect the social beliefs of the people who use them. Informed by quantitative critical race theory analysis, we interrogate how race categories align (or not) with 24,000 U.S. higher education students' responses to…

Applications of polytomous IRT models in applied fields (e.g., health, education, psychology) are abound. However, little is known about the impact of the number of categories and sample size requirements for precise parameter recovery. In a simulation study, we investigated the impact of the number of response categories and required sample size…

This study explored student engagement typology in Chinese universities and examined variations in the ability development across student types. Using data generated by a survey study covering 8461 undergraduate students at 53 Chinese universities, this research applied latent profile analysis to construct a Chinese student engagement typology. We…

Educational feedback is a crucial factor in the student's learning journey, as through it, students are able to identify their areas of deficiencies and improve self-regulation. However, the literature shows that this is an area of great dissatisfaction, especially in higher education. Providing effective feedback becomes an increasingly…

Research in science education has established the significance of collaborative concept mapping as a powerful strategy in fostering conceptual learning. During such collaboration, students talk about concept map features (i.e., concepts to include, linking words, and cross-links) in constructing a joint map. The quality of the concept map produced…

The author of this article describes an exercise for introductory economics courses in which students are exposed to the breadth of economic study using JEL codes. JEL codes have historically been used to classify economic subject matter and ultimately document the ever-evolving scope of economics. This discussion assignment provides an…

This non-experimental causal-comparative study aims to explore the possible effect of expertise on learning experience design (LXD) deviation identification and the classification of these deviations in alignment with provided learning experience design constructs within a learning technology. Additionally, this study challenges Nielsen's (1993)…

Shadowing is the act of vocalizing the speech one is listening to as simultaneously as possible. The primary function of shadowing is learners' listening skill and pronunciation skill development. Despite the importance of second language (L2) listening skills, this pedagogical technique has not received focal attention in the field. In this…