Aim/Purpose: This article investigates the process of identifying and correcting hallucinations in ChatGPT-4's recall of student-written responses as well as its evaluation of these responses, and provision of feedback. Effective prompting is examined to enhance the pre-evaluation, evaluation, and post-evaluation stages. Background: Advanced Large…

In large lecture courses, it can be challenging to imagine assessing student learning in ways other than multiple-choice exams and traditional point-based grading. Inspired by major pedagogical principles shared by Maria Montessori and Thomas Jefferson and supported by current understandings of effective teaching, assessment was reimagined in a…

When providing feedback, teachers are concerned not only with the simple transmission of information, but also with motivational and interpersonal dynamics. To mitigate these concerns, teachers may inflate feedback by reducing negative or increasing positive content. The resulting difference between initial judgments and feedback may be even more…

Automated essay scoring (AES), where natural language processing is applied to score written text, can underpin educational resources in blended and distance learning. AES performance has typically been reported in terms of correlation coefficients or agreement statistics calculated between a system and an expert human examiner. We describe the…

The paper attempts to give an overview of evaluation in higher education institutions with particular emphasis on the faculties of humanities, education and social sciences disciplines at the University of Eswatini (Swaziland) in Southern Africa. It describes the general methodology of evaluation and identifies obstacles and relevant strategies…

Assessment is often used to promote learning, but the mechanisms of how assessment relates to epistemology -- knowledge and knowing -- have been scarcely studied and theorised. In this study, we examine students' epistemic resources in relation assessment in the context of university mathematics education. We draw on the theoretical framework of…

Reflective essays have become common in higher education, especially for modules and programmes focused on the development of practical skills. This paper analyses the efficacy of reflective essays specifically for social research methods education and training. In order to do so, a thematic analysis of qualitative survey data from undergraduate…

The upsurge of ICT media and hybrid modalities for learning that stemmed from the world health crisis seem to be destined to stay. In this new paradigm, self-assessment processes have acquired an even more relevant role in the teaching learning process than they already had. Due to the myriad of academic online resources and information at their…

Research examining students' historical reasoning has heavily relied on evidence in the form of students' written work to make claims about students' ability to reason historically and have argued that the document-based history essay holds the most promise for assessing students' historical thinking (Nokes & De La Paz, 2018). However,…

The process of analyzing student data to determine an appropriate instructional decision is crucial for student academic growth. This article details how teachers can make data-driven decisions to carefully design writing instruction. Steps are presented for teachers to follow throughout the data driven decision-making process in order to meet…

Various studies empirically proved the value of highly informative feedback for enhancing learner success. However, digital educational technology has yet to catch up as automated feedback is often provided shallowly. This paper presents a case study on implementing a pipeline that provides German-speaking university students enrolled in an…

This article investigates the feasibility of using automated scoring methods to evaluate the quality of student-written essays. In 2012, Kaggle hosted an Automated Student Assessment Prize contest to find effective solutions to automated testing and grading. This article: a) analyzes the datasets from the contest -- which contained hand-graded…

This study investigated English as a Foreign Language (EFL) teachers' beliefs concerning the use of an AI grading tool (CoGrader) for essay scoring and feedback. The study also explored the factors which contributed to those beliefs. EFL teachers (n = 10) from public universities (n = 3) in Saudi Arabia participated in this study. The study…

In Automated Essay Scoring (AES) systems, many previous works have studied group fairness using the demographic features of essay writers. However, individual fairness also plays an important role in fair evaluation and has not been yet explored. Initialized by Dwork et al., the fundamental concept of individual fairness is "similar people…

Creating summative assessments that accurately test students' breadth of knowledge and critical thinking can be a difficult task. Instructors often rely upon overly complex quick response questions or constructed response exams. However, students often have negative perceptions of the latter. The authors implemented an approach for administering…