[HTML][HTML] Examining analytic practices in latent dirichlet allocation within psychological science: sco** review

LJ Hagg, SS Merkouris, GA O'Dea, LM Francis… - Journal of Medical …, 2022 - jmir.org
Background Topic modeling approaches allow researchers to analyze and represent written
texts. One of the commonly used approaches in psychology is latent Dirichlet allocation …

ChatGPT versus human in generating medical graduate exam multiple choice questions—A multinational prospective study (Hong Kong SAR, Singapore, Ireland, and …

BHH Cheung, GKK Lau, GTC Wong, EYP Lee… - PloS one, 2023 - journals.plos.org
Introduction Large language models, in particular ChatGPT, have showcased remarkable
language processing capabilities. Given the substantial workload of university medical staff …

[HTML][HTML] End-to-end generation of multiple-choice questions using text-to-text transfer transformer models

R Rodriguez-Torrealba, E Garcia-Lopez… - Expert Systems with …, 2022 - Elsevier
The increasing worldwide adoption of e-learning tools and widespread increase of online
education has brought multiple challenges, including the ability of generating assessments …

A comparative study of AI-generated (GPT-4) and human-crafted MCQs in programming education

J Doughty, Z Wan, A Bompelli, J Qayum… - Proceedings of the 26th …, 2024 - dl.acm.org
There is a constant need for educators to develop and maintain effective up-to-date
assessments. While there is a growing body of research in computing education on utilizing …

[書籍][B] Advanced methods in automatic item generation

MJ Gierl, H Lai, V Tanygin - 2021 - taylorfrancis.com
Advanced Methods in Automatic Item Generation is an up-to-date survey of the growing
research on automatic item generation (AIG) in today's technology-enhanced educational …

The more, the better? Learning with feedback and instruction

S Wagner, L Sibley, D Weiler, JP Burde, K Scheiter… - Learning and …, 2024 - Elsevier
Background Strategy instruction and formative feedback are powerful instructional strategies
to support learning. However, combining them may not necessarily be effective. Previous …

Are neural topic models broken?

A Hoyle, P Goel, R Sarkar, P Resnik - arxiv preprint arxiv:2210.16162, 2022 - arxiv.org
Recently, the relationship between automated and human evaluation of topic models has
been called into question. Method developers have staked the efficacy of new topic model …

EduQG: A multi-format multiple-choice dataset for the educational domain

A Hadifar, SK Bitew, J Deleu, C Develder… - IEEE …, 2023 - ieeexplore.ieee.org
Natural language processing technology has made significant progress in recent years,
fuelled by increasingly powerful general language models. This has also inspired a sizeable …

A novel approach to generate distractors for multiple choice questions

AP Kumar, A Nayak, M Shenoy, S Goyal - Expert Systems with …, 2023 - Elsevier
Abstract Multiple Choice Questions (MCQs) have been predominantly used as an
assessment tool in the educational domain. The MCQ comprises a question called 'Stem' …

Evaluation of the Open-Ended Green Chemistry Generic Comparison (GC)2 Prompt for Probing Student Conceptions about the Greenness of a Chemical Reaction

K Grieger, A Leontyev - Journal of chemical education, 2024 - ACS Publications
One key limitation for assessing student knowledge of green chemistry is the lack of readily
available assessments capable of eliciting reliable and valid data. Therefore, in this study …