NotesFAQContact Us
Collection
Advanced
Search Tips
Audience
Laws, Policies, & Programs
What Works Clearinghouse Rating
Showing 1 to 15 of 22 results Save | Export
Peer reviewed Peer reviewed
Direct linkDirect link
Po-Chun Huang; Ying-Hong Chan; Ching-Yu Yang; Hung-Yuan Chen; Yao-Chung Fan – IEEE Transactions on Learning Technologies, 2024
Question generation (QG) task plays a crucial role in adaptive learning. While significant QG performance advancements are reported, the existing QG studies are still far from practical usage. One point that needs strengthening is to consider the generation of question group, which remains untouched. For forming a question group, intrafactors…
Descriptors: Automation, Test Items, Computer Assisted Testing, Test Construction
Peer reviewed Peer reviewed
Direct linkDirect link
Hei-Chia Wang; Yu-Hung Chiang; I-Fan Chen – Education and Information Technologies, 2024
Assessment is viewed as an important means to understand learners' performance in the learning process. A good assessment method is based on high-quality examination questions. However, generating high-quality examination questions manually by teachers is a time-consuming task, and it is not easy for students to obtain question banks. To solve…
Descriptors: Natural Language Processing, Test Construction, Test Items, Models
Olney, Andrew M. – Grantee Submission, 2022
Multi-angle question answering models have recently been proposed that promise to perform related tasks like question generation. However, performance on related tasks has not been thoroughly studied. We investigate a leading model called Macaw on the task of multiple choice question generation and evaluate its performance on three angles that…
Descriptors: Test Construction, Multiple Choice Tests, Test Items, Models
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Mohammad Hmoud; Hadeel Swaity; Eman Anjass; Eva María Aguaded-Ramírez – Electronic Journal of e-Learning, 2024
This research aimed to develop and validate a rubric to assess Artificial Intelligence (AI) chatbots' effectiveness in accomplishing tasks, particularly within educational contexts. Given the rapidly growing integration of AI in various sectors, including education, a systematic and robust tool for evaluating AI chatbot performance is essential.…
Descriptors: Artificial Intelligence, Man Machine Systems, Natural Language Processing, Test Construction
Kate E. Walton; Cristina Anguiano-Carrasco – ACT, Inc., 2024
Large language models (LLMs), such as ChatGPT, are becoming increasingly prominent. Their use is becoming more and more popular to assist with simple tasks, such as summarizing documents, translating languages, rephrasing sentences, or answering questions. Reports like McKinsey's (Chui, & Yee, 2023) estimate that by implementing LLMs,…
Descriptors: Artificial Intelligence, Man Machine Systems, Natural Language Processing, Test Construction
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Edmund De Leon Evangelista – Contemporary Educational Technology, 2025
The rapid advancement of artificial intelligence (AI) technologies, particularly OpenAI's ChatGPT, has significantly impacted higher education institutions (HEIs), offering opportunities and challenges. While these tools enhance personalized learning and content generation, they threaten academic integrity, especially in assessment environments.…
Descriptors: Artificial Intelligence, Integrity, Educational Strategies, Natural Language Processing
Peer reviewed Peer reviewed
Direct linkDirect link
Haug, Tobias; Mann, Wolfgang; Holzknecht, Franz – Sign Language Studies, 2023
This study is a follow-up to previous research conducted in 2012 on computer-assisted language testing (CALT) that applied a survey approach to investigate the use of technology in sign language testing worldwide. The goal of the current study was to replicate the 2012 study and to obtain updated information on the use of technology in sign…
Descriptors: Computer Assisted Testing, Sign Language, Natural Language Processing, Language Tests
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Andrew M. Olney – Grantee Submission, 2023
Multiple choice questions are traditionally expensive to produce. Recent advances in large language models (LLMs) have led to fine-tuned LLMs that generate questions competitive with human-authored questions. However, the relative capabilities of ChatGPT-family models have not yet been established for this task. We present a carefully-controlled…
Descriptors: Test Construction, Multiple Choice Tests, Test Items, Algorithms
Peer reviewed Peer reviewed
Direct linkDirect link
Thinley Wangdi; Karma Sonam Rigdel; Tashi Dawa; Kinga Tshering – Issues in Educational Research, 2025
In the last two years, there has been a significant increase in research studies on ChatGPT and its role in educational assessment. However, there is no comprehensive systematic literature review (SLR) on the potential use of ChatGPT for educational assessment, particularly with a focus on its practices and limitations. To address this gap, our…
Descriptors: Artificial Intelligence, Man Machine Systems, Natural Language Processing, Evaluation Methods
Peer reviewed Peer reviewed
Direct linkDirect link
Micir, Ian; Swygert, Kimberly; D'Angelo, Jean – Journal of Applied Testing Technology, 2022
The interpretations of test scores in secure, high-stakes environments are dependent on several assumptions, one of which is that examinee responses to items are independent and no enemy items are included on the same forms. This paper documents the development and implementation of a C#-based application that uses Natural Language Processing…
Descriptors: Artificial Intelligence, Man Machine Systems, Accuracy, Efficiency
Peer reviewed Peer reviewed
Direct linkDirect link
Shuqiong Luo; Di Zou – European Journal of Education, 2025
Recent AI-based language learning research highlights learners' crucial role, yet university learner readiness in ChatGPT-based English learning remains unexplored. Accordingly, this current research attempted to develop and validate a tool to evaluate university learner readiness for ChatGPT-assisted English learning (LRCEL) to address the…
Descriptors: College Students, Readiness, Artificial Intelligence, Natural Language Processing
Peer reviewed Peer reviewed
Direct linkDirect link
Shin, Jinnie; Gierl, Mark J. – International Journal of Testing, 2022
Over the last five years, tremendous strides have been made in advancing the AIG methodology required to produce items in diverse content areas. However, the one content area where enormous problems remain unsolved is language arts, generally, and reading comprehension, more specifically. While reading comprehension test items can be created using…
Descriptors: Reading Comprehension, Test Construction, Test Items, Natural Language Processing
Peer reviewed Peer reviewed
Direct linkDirect link
Naveed Saif; Sadaqat Ali; Abner Rubin; Soliman Aljarboa; Nabil Sharaf Almalki; Mrim M. Alnfiai; Faheem Khan; Sajid Ullah Khan – Educational Technology & Society, 2025
In the swiftly evolving landscape of education, the fusion of Artificial Intelligence's ingenuity with the dynamic capabilities of chat-bot technology has ignited a transformative paradigm shift. This convergence is not merely a technological integration but a profound reshaping of the fundamental principles of pedagogy, fundamentally redefining…
Descriptors: Artificial Intelligence, Technology Uses in Education, Readiness, Technological Literacy
Peer reviewed Peer reviewed
Direct linkDirect link
Rao, Dhawaleswar; Saha, Sujan Kumar – IEEE Transactions on Learning Technologies, 2020
Automatic multiple choice question (MCQ) generation from a text is a popular research area. MCQs are widely accepted for large-scale assessment in various domains and applications. However, manual generation of MCQs is expensive and time-consuming. Therefore, researchers have been attracted toward automatic MCQ generation since the late 90's.…
Descriptors: Multiple Choice Tests, Test Construction, Automation, Computer Software
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Carmen Köhler; Johannes Hartig – Contemporary Educational Technology, 2024
Since ChatGPT-3.5 has been available to the public, the potentials and challenges regarding chatbot usage in education have been widely discussed. However, little evidence exists whether and for which purposes students even apply generative AI tools. The first main purpose of the present study was to develop and test scales that assess students'…
Descriptors: Artificial Intelligence, College Students, Natural Language Processing, Technology Uses in Education
Previous Page | Next Page »
Pages: 1  |  2