AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations

In recent years, artificial intelligence has been leveraged to develop an automatic question generation (AQG) system that places formative practice questions alongside textbook content in an ereader platform. Engaging with formative practice while reading is a highly effective learning strategy. AQG...

Full description

Saved in:
Bibliographic Details
Main Authors: Rachel Van Campenhout, Benny G. Johnson, Michelle Clark, Melissa Deininger, Shannon Harper, Kelly Odenweller, Erin Wilgenbusch
Format: Article
Language:English
Published: Croatian Communications and Information Society (CCIS) 2025-06-01
Series:Journal of Communications Software and Systems
Subjects:
Online Access:https://jcoms.fesb.unist.hr/10.24138/jcomss-2024-0120/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850276844551536640
author Rachel Van Campenhout
Benny G. Johnson
Michelle Clark
Melissa Deininger
Shannon Harper
Kelly Odenweller
Erin Wilgenbusch
author_facet Rachel Van Campenhout
Benny G. Johnson
Michelle Clark
Melissa Deininger
Shannon Harper
Kelly Odenweller
Erin Wilgenbusch
author_sort Rachel Van Campenhout
collection DOAJ
description In recent years, artificial intelligence has been leveraged to develop an automatic question generation (AQG) system that places formative practice questions alongside textbook content in an ereader platform. Engaging with formative practice while reading is a highly effective learning strategy. AQG made it possible to scale this method to thousands of textbooks and millions of students for free. Previous research studies used aggregated data from all questions answered by all students to complete the largest evaluation of the performance metrics for automatically generated questions. However, these studies also indicated that when assigned in a classroom setting, student behavior and question performance metrics would differ. In this study, we evaluate data collected from 19 course sections taught by four faculty members at Iowa State University to gain a broader understanding of how students engage with these AI-generated practice questions when part of their university courses. Implementation strategies for the courses, student engagement, and question performance metrics are analyzed, and student feedback gathered from surveys and course evaluations are presented. Implications for further use in higher education classrooms are discussed.
format Article
id doaj-art-ffa13cf9d62749d18cd4b64aa7302d57
institution OA Journals
issn 1845-6421
1846-6079
language English
publishDate 2025-06-01
publisher Croatian Communications and Information Society (CCIS)
record_format Article
series Journal of Communications Software and Systems
spelling doaj-art-ffa13cf9d62749d18cd4b64aa7302d572025-08-20T01:50:06ZengCroatian Communications and Information Society (CCIS)Journal of Communications Software and Systems1845-64211846-60792025-06-0121217818810.24138/jcomss-2024-0120AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty ObservationsRachel Van CampenhoutBenny G. JohnsonMichelle ClarkMelissa DeiningerShannon HarperKelly OdenwellerErin WilgenbuschIn recent years, artificial intelligence has been leveraged to develop an automatic question generation (AQG) system that places formative practice questions alongside textbook content in an ereader platform. Engaging with formative practice while reading is a highly effective learning strategy. AQG made it possible to scale this method to thousands of textbooks and millions of students for free. Previous research studies used aggregated data from all questions answered by all students to complete the largest evaluation of the performance metrics for automatically generated questions. However, these studies also indicated that when assigned in a classroom setting, student behavior and question performance metrics would differ. In this study, we evaluate data collected from 19 course sections taught by four faculty members at Iowa State University to gain a broader understanding of how students engage with these AI-generated practice questions when part of their university courses. Implementation strategies for the courses, student engagement, and question performance metrics are analyzed, and student feedback gathered from surveys and course evaluations are presented. Implications for further use in higher education classrooms are discussed.https://jcoms.fesb.unist.hr/10.24138/jcomss-2024-0120/automatic question generationperformance metricsquestion difficultypersistencenatural learning contextstudent behavior
spellingShingle Rachel Van Campenhout
Benny G. Johnson
Michelle Clark
Melissa Deininger
Shannon Harper
Kelly Odenweller
Erin Wilgenbusch
AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
Journal of Communications Software and Systems
automatic question generation
performance metrics
question difficulty
persistence
natural learning context
student behavior
title AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
title_full AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
title_fullStr AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
title_full_unstemmed AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
title_short AI-Generated Questions in Context: A Contextualized Investigation Using Platform Data, Student Feedback, and Faculty Observations
title_sort ai generated questions in context a contextualized investigation using platform data student feedback and faculty observations
topic automatic question generation
performance metrics
question difficulty
persistence
natural learning context
student behavior
url https://jcoms.fesb.unist.hr/10.24138/jcomss-2024-0120/
work_keys_str_mv AT rachelvancampenhout aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT bennygjohnson aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT michelleclark aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT melissadeininger aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT shannonharper aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT kellyodenweller aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations
AT erinwilgenbusch aigeneratedquestionsincontextacontextualizedinvestigationusingplatformdatastudentfeedbackandfacultyobservations