Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/12459
Title: Bridging curriculum and creativity: NLP-powered semantic analysis for knowledge building
Other Titles: Bridging Curriculum and Creativity: NLP-Powered Semantic Analysis for Knowledge Building
Authors: Khanlari, Ahmad
Keywords: CSCL
Issue Date: 2026
metadata.dc.format.pagerange: 139-147
Publisher: International Society of the Learning Sciences
Citation: Khanlari, A. (2026). Bridging curriculum and creativity: NLP-powered semantic analysis for knowledge building. In Rosé, C., Gweon, G., Asterhan, C., & Keune, A. (Eds.), Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026 (pp. 139-147). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning - CSCL 2026
Abstract: Knowledge Building is a collaborative approach that treats ideas as improvable knowledge artifacts and engages learners in advancing collective understanding. To support this, educators need analytics that reveal deep discourse patterns. This paper introduces a semantic analysis tool for Knowledge Building that uses natural language processing to illuminate conceptual dynamics in student-generated content. The tool takes a glossary of curriculum terms and student notes, preprocesses text with spaCy, and computes semantic similarities using a transformer model. By analyzing word-to-term relationships, it identifies curriculum coverage, related concepts beyond official terms, and evidence of conceptual growth. We outline the tool’s design, demonstrate its outputs through network visualizations, and discuss implications for formative assessment, curriculum design, and longitudinal tracking, positioning it as a flexible analytic for studying and fostering knowledge-creating discourse.
Description: LONG
URI: https://doi.org/10.22318/cscl2026.638463
https://repository.isls.org/handle/1/12459
ISBN: 979-8-9906980-6-2
ISSN: 2543-0157
Appears in Collections:ISLS Annual Meeting 2026

Files in This Item:
File SizeFormat 
CSCL2026_139-147.pdf520.72 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.