Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11805
Title: Emotional Dynamics in Asynchronous Math Discussions: Analyzing the Impact of Negative Emotions on Learning Outcomes
Authors: Kim, Taehyun
Liu, Zifeng
Xing, Wanli
Li, Hai
Oh, Hyunju
Keywords: Learning Sciences
Issue Date: 2025
Publisher: International Society of the Learning Sciences
Citation: Kim, T., Liu, Z., Xing, W., Li, H., & Oh, H. (2025). Emotional Dynamics in Asynchronous Math Discussions: Analyzing the Impact of Negative Emotions on Learning Outcomes. In Rajala, A., Cortez, A., Hofmann, R., Jornet, A., Lotz-Sisitka, H., & Markauskaite, L. (Eds.), Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025 (pp. 781-789). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025
Abstract: This study investigates the role of negative emotions in asynchronous online math discussions and their impact on learning. Using data from 402 students and 3,084 discussion posts, the study employs sentiment analysis and machine learning to categorize emotions. Findings reveal that low levels of negative emotions can enhance learning by fostering active engagement, while higher levels correlate with lower performance. Topic modeling and sequential pattern mining show that students with low negative emotions engage more productively, focusing on both 'Help-seeking behaviors' and 'Understanding.' In contrast, high negative emotions lead to shorter interactions and focusing primarily on 'Help-seeking behaviors.' Sequential analysis indicates that low negative emotions often transition to neutral or positive states, supporting continued engagement, while high negative emotions result in repetitive negative sequences and disengagement. These findings underscore the importance of understanding negative emotions and providing appropriate support in asynchronous learning environments to foster engagement and improve outcomes.
Description: Long Paper
URI: https://doi.org/10.22318/icls2025.183564
https://repository.isls.org//handle/1/11805
Appears in Collections:ISLS Annual Meeting 2025

Files in This Item:
File SizeFormat 
ICLS2025_781-789.pdf433.76 kBAdobe PDFView/Open


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