Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11053
Title: NLP-Enabled Automated Feedback about Science Writing
Authors: Kim, ChanMin
Puntambekar, Sadhana
Lee, Eunseo
Gnesdilow, Dana
Karizaki, Mahsa Sheikhi
Passonneau, Rebecca
Keywords: Learning Sciences
Issue Date: 2024
Publisher: International Society of the Learning Sciences
Citation: Kim, C., Puntambekar, S., Lee, E., Gnesdilow, D., Karizaki, M. S., & Passonneau, R. (2024). NLP-Enabled Automated Feedback about Science Writing. In Lindgren, R., Asino, T. I., Kyza, E. A., Looi, C. K., Keifert, D. T., & Suárez, E. (Eds.), Proceedings of the 18th International Conference of the Learning Sciences - ICLS 2024 (pp. 2431-2432). International Society of the Learning Sciences.
Abstract: Eighth grade students received automated feedback from PyrEval - an NLP tool - about their science essays. We examined essay quality change when revised. Regardless of prior physics knowledge, essay quality improved. Grounded in literature on AI explainability and trust in automated feedback, we also examined which PyrEval explanation predicted essay quality change. Essay quality improvement was predicted by high- and medium-accuracy feedback.
Description: Poster
URI: https://doi.org/10.22318/icls2024.712073
https://repository.isls.org//handle/1/11053
Appears in Collections:ISLS Annual Meeting 2024

Files in This Item:
File SizeFormat 
ICLS2024_2431-2432.pdf692.38 kBAdobe PDFView/Open


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