Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10069
Title: Building a Science Concept Recognition System Using NLP From Elementary Students’ Science Storybooks
Authors: Kong, Lingchen
Pinto, Wallace Nascimento
Shin, Jinnie
Keywords: Learning Sciences
Issue Date: 2023
Publisher: International Society of the Learning Sciences
Citation: Kong, L., Pinto, W. N., & Shin, J. (2023). Building a science concept recognition system using NLP from elementary students’ science storybooks. In Blikstein, P., Van Aalst, J., Kizito, R., & Brennan, K. (Eds.), Proceedings of the 17th International Conference of the Learning Sciences - ICLS 2023 (pp. 1883-1884). International Society of the Learning Sciences.
Abstract: Despite the benefits of reading instructions, limited studies exist on recommending suitable learning resources for children’s science education. To create a recommendation framework, identifying science learning resources that encompass science concepts that are adequate for the grade level is vital. In this study, we collected 52 science books for grades 3 to 5, extracting science concepts using named-entity recognition algorithms. Our findings could identify close to 3,000 science concepts entities across various science topic categories.
Description: Poster
URI: https://doi.org/10.22318/icls2023.112181
https://repository.isls.org//handle/1/10069
Appears in Collections:ISLS Annual Meeting 2023

Files in This Item:
File SizeFormat 
ICLS2023_1883-1884.pdf174.42 kBAdobe PDFView/Open


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