Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Kroeze, Karel A.; Berg, Stéphanie Martine van den; Veldkamp, Bernard P.; Jong, Ton de

doi:10.1109/tlt.2021.3103331

Cited by 9 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(F) Automated Assessment : AI-based technological advancements and sophistication facilitate large-scale assessment processes using automated and computer-based assessment tools like CourseMarker [71] , DOMjudge [72] , and Formative [73] . Significant research has also leveraged mechanisms like concept mapping [74] for automated self-assessment through tools such as HIMATT [75] , Betty's Brain [76] , Conlon's Reasonable Fallible Analyzer (RFA) [77] and COMPASS [78] .…”

Section: Technology Intervention In Tertiary Education: Current Scenariomentioning

confidence: 99%

A Collaborative Metaverse based A-La-Carte Framework for Tertiary Education (CO-MATE)

Joshi¹,

Pramod²

2023

Heliyon

View full text Add to dashboard Cite

Section: Technology Intervention In Tertiary Education: Current Scenariomentioning

confidence: 99%

A Collaborative Metaverse based A-La-Carte Framework for Tertiary Education (CO-MATE)

Joshi¹,

Pramod²

2023

Heliyon

View full text Add to dashboard Cite

Assessing concept mapping competence using item expansion‐based diagnostic classification analysis

Xia,

Zhan,

Chan

et al. 2023

J Res Sci Teach

View full text Add to dashboard Cite

Concept mapping is widely used as a tool for assessing students' understanding of science. To fully realize the diagnostic potential of concept mapping, a scoring method that not only provides an objective and accurate assessment of students' drawn concept maps but also provides a detailed understanding of students' proficiency and deficiencies in knowledge is necessary. However, few of the existing scoring methods focus on the latent constructs (e.g., knowledge, skills, and cognitive processes) that guide the creation of concept maps. Instead, they focus on the completeness of the concept map by assigning a composite score, which makes it difficult to generate targeted diagnostic feedback information for advancing students' learning. To apply the diagnostic classification model to the quantitative analysis of concept maps, this study introduced the novel application of the item expansion‐based diagnostic classification analysis (IE‐DCA) for this purpose. The IE‐DCA can not only assess students' concept mapping abilities along a continuum but also classify students according to their concept mapping attributes when constructing the concept maps. The application and benefits of this approach were illustrated using a physics concept‐mapping item related to particle and rigid body. Results showed that the estimated attribute profiles via the IE‐DCA provided more detailed information about students' latent constructs than the composite score. Overall, this study illustrates the feasibility and potential of applying IE‐DCA to analyze concept maps. Future applications of IE‐DCS in other assessments in science education are discussed.

show abstract

Applying Machine Learning to Augment the Design and Assessment of Immersive Learning Experience

Dai

2024

Machine Learning in Educational Sciences

View full text Add to dashboard Cite

Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Cited by 9 publications

References 40 publications

A Collaborative Metaverse based A-La-Carte Framework for Tertiary Education (CO-MATE)

A Collaborative Metaverse based A-La-Carte Framework for Tertiary Education (CO-MATE)

Assessing concept mapping competence using item expansion‐based diagnostic classification analysis

Applying Machine Learning to Augment the Design and Assessment of Immersive Learning Experience

Contact Info

Product

Resources

About