Although AI transformer models have demonstrated notable capability in automated scoring, it is difficult to examine how and why these models fall short in scoring some responses. This study investigated how transformer models' language processing and quantification processes can be leveraged to enhance the accuracy of automated scoring. Automated…

Double-scoring constructed-response items is a common but costly practice in mixed-format assessments. This study explored the impacts of Targeted Double-Scoring (TDS) and random double-scoring procedures on the quality of psychometric outcomes, including student achievement estimates, person fit, and student classifications under various…

Recent curricular interventions in engineering education have focused on encouraging students to develop an entrepreneurial mindset (EM) to equip them with the skills needed to generate innovative ideas and address complex global problems upon entering the workforce. Methods to evaluate these interventions have been inconsistent due to the lack of…

Globalization and increases in the numbers of English language learners have led to a growing demand for English proficiency assessments of spoken language. In this paper, we describe the development of an automatic pronunciation scorer built on state-of-the-art deep neural network models. The model is trained on a bespoke human-rated dataset that…

Mixed-format assessments made up of multiple-choice (MC) items and constructed response (CR) items that are scored using rater judgments include unique psychometric considerations. When these item types are combined to estimate examinee achievement, information about the psychometric quality of each component can depend on that of the other. For…

For predicting and improving the quality of essays, text analytic metrics (surface, syntactic, morphological, and semantic features) can be used to provide formative feedback to the students in higher education. In this study, the goal was to identify a sufficient number of features that exhibit a fair proxy of the scores given by the human raters…

Standardized observation systems seek to reliably measure a specific conceptualization of teaching quality, managing rater error through mechanisms such as certification, calibration, validation, and double-scoring. These mechanisms both support high quality scoring and generate the empirical evidence used to support the scoring inference (i.e.,…

This study compares how the generative AI (GenAI) large language model (LLM) ChatGPT performs in grading university exams compared to human teachers. Aspects investigated include consistency, large discrepancies and length of answer. Implications for higher education, including the role of teachers and ethics, are also discussed. Three…

There is a vast body of literature documenting the positive impacts that rater training and calibration sessions have on inter-rater reliability as research indicates several factors including frequency and timing play crucial roles towards ensuring inter-rater reliability. Additionally, increasing amounts research indicate possible links in…

The validity of the Kappa coefficient of chance-corrected agreement has been questioned when the prevalence of specific rating scale categories is low and agreement between raters is high. The researchers proposed the Lambda Coefficient of Rater-Mediated Agreement as an alternative to Kappa to address these concerns. Lambda corrects for chance…

Trend scoring constructed response items (i.e. rescoring Time A responses at Time B) gives rise to two-way data that follow a product multinomial distribution rather than the multinomial distribution that is usually assumed. Recent work has shown that the difference in sampling model can have profound negative effects on statistics usually used to…

In response to the call for promoting three-dimensional science learning (NRC, 2012), researchers argue for developing assessment items that go beyond rote memorization tasks to ones that require deeper understanding and the use of reasoning that can improve science literacy. Such assessment items are usually performance-based constructed…

Scoring mathematics exam papers accurately is vital for fostering students' engagement and interest in the subject. Incorrect scoring practices can erode motivation and lead to the development of false self-confidence. Therefore, the implementation of appropriate scoring methods is essential for the success of mathematics education. This study…

Different sources of assessment evidence are reviewed during International Baccalaureate (IB) grade awarding to convert marks into grades and ensure fair results for students. Qualitative and quantitative evidence are analysed to determine grade boundaries, with statistical evidence weighed against examiner judgement and teachers' feedback on…

This document describes a set of best practices for developing, implementing, and maintaining the critical process of scoring constructed-response tasks. These practices address both the use of human raters and automated scoring systems as part of the scoring process and cover the scoring of written, spoken, performance, or multimodal responses.…