Bernstein, Seth; Denny, Paul; Leinonen, Juho; Kan, Lauren; Hellas, Arto; Littlefield, Matt; Sarsa, Sami; Macneil, Stephen

doi:10.1145/3649217.3653533

dc.contributor.author	Bernstein, Seth
dc.contributor.author	Denny, Paul
dc.contributor.author	Leinonen, Juho
dc.contributor.author	Kan, Lauren
dc.contributor.author	Hellas, Arto
dc.contributor.author	Littlefield, Matt
dc.contributor.author	Sarsa, Sami
dc.contributor.author	Macneil, Stephen
dc.date.accessioned	2024-08-07T08:45:58Z
dc.date.available	2024-08-07T08:45:58Z
dc.date.issued	2024
dc.identifier.citation	Bernstein, S., Denny, P., Leinonen, J., Kan, L., Hellas, A., Littlefield, M., Sarsa, S., & Macneil, S. (2024). "Like a Nesting Doll" : Analyzing Recursion Analogies Generated by CS Students Using Large Language Models. In <i>ITiCSE 2024 : Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1</i> (pp. 122-128). ACM. <a href="https://doi.org/10.1145/3649217.3653533" target="_blank">https://doi.org/10.1145/3649217.3653533</a>
dc.identifier.other	CONVID_221088858
dc.identifier.uri	https://jyx.jyu.fi/handle/123456789/96532
dc.description.abstract	Grasping complex computing concepts often poses a challenge for students who struggle to anchor these new ideas to familiar experiences and understandings. To help with this, a good analogy can bridge the gap between unfamiliar concepts and familiar ones, providing an engaging way to aid understanding. However, creating effective educational analogies is difficult even for experienced instructors. We investigate to what extent large language models (LLMs), specifically ChatGPT, can provide access to personally relevant analogies on demand. Focusing on recursion, a challenging threshold concept, we conducted an investigation analyzing the analogies generated by more than 350 first-year computing students. They were provided with a code snippet and tasked to generate their own recursion-based analogies using ChatGPT, optionally including personally relevant topics in their prompts. We observed a great deal of diversity in the analogies produced with student-prescribed topics, in contrast to the otherwise generic analogies, highlighting the value of student creativity when working with LLMs. Not only did students enjoy the activity and report an improved understanding of recursion, but they described more easily remembering analogies that were personally and culturally relevant.	en
dc.format.extent	754
dc.format.mimetype	application/pdf
dc.language.iso	eng
dc.publisher	ACM
dc.relation.ispartof	ITiCSE 2024 : Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1
dc.rights	CC BY 4.0
dc.subject.other	analogies
dc.subject.other	large language models
dc.subject.other	computing education
dc.title	"Like a Nesting Doll" : Analyzing Recursion Analogies Generated by CS Students Using Large Language Models
dc.type	conferenceObject
dc.identifier.urn	URN:NBN:fi:jyu-202408075408
dc.contributor.laitos	Informaatioteknologian tiedekunta	fi
dc.contributor.laitos	Faculty of Information Technology	en
dc.type.uri	http://purl.org/eprint/type/ConferencePaper
dc.relation.isbn	979-8-4007-0600-4
dc.type.coar	http://purl.org/coar/resource_type/c_5794
dc.description.reviewstatus	peerReviewed
dc.format.pagerange	122-128
dc.type.version	publishedVersion
dc.rights.copyright	© 2024 the Authors
dc.rights.accesslevel	openAccess	fi
dc.relation.conference	Conference on Innovation and Technology in Computer Science Education
dc.subject.yso	tietojenkäsittelytieteet
dc.subject.yso	käsitteet
dc.subject.yso	analogia
dc.subject.yso	chattibotit
dc.subject.yso	korkeakouluopetus
dc.subject.yso	tekoäly
dc.format.content	fulltext
jyx.subject.uri	http://www.yso.fi/onto/yso/p21029
jyx.subject.uri	http://www.yso.fi/onto/yso/p2267
jyx.subject.uri	http://www.yso.fi/onto/yso/p17856
jyx.subject.uri	http://www.yso.fi/onto/yso/p39028
jyx.subject.uri	http://www.yso.fi/onto/yso/p1246
jyx.subject.uri	http://www.yso.fi/onto/yso/p2616
dc.rights.url	https://creativecommons.org/licenses/by/4.0/
dc.relation.doi	10.1145/3649217.3653533
jyx.fundinginformation	This research was partially supported by the Research Council of Finland (Academy Research Fellow grant number 356114).
dc.type.okm	A4