Abstract
The small private online course (SPOC)-based blended learning is becoming increasingly significant for college campus courses in the current COVID-19 pandemic scenario. It is critical to predicting students’ performance for providing personalized intervention and guidance in the blended learning environment, however, it has been shown in few studies that learning performance is predicable in situations related to teaching context. In this paper, we implemented one whole semester blended learning course based on Xuexitong and traditional classroom to examine the predictability of student performance. Multiple linear regression model was utilized to analyze the impact of online and offline learning activities on student performance. Nonlinear models including GBDT, SVR and KNN were contrasted to check whether the predictions were generalized. The experiment reveals that learning data from off line and online activities that are part of blended learning can be used to predict students’ performance. The attributes that influence most in our course were Class. Attendance, Online. Task, Lab.Projects Score, Online. Time and Online. Peer-review Grade. The results can help to learn about students learning situations and provide personalized intervention.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Voci, E., Young, K.: Blended learning working in a leadership development programme. Ind. Commer. Train. 33(5), 157–161 (2001). https://doi.org/10.1108/00197850110398927
Singh, H.: Building effective blended learning programs. Educ. Technol. 6(43), 51–54 (2003)
Alexander, B., et al.: Horizon Report 2019 Higher Education Edition. EDU19 (2019)
Fox, A.: From moocs to spocs. Commun. ACM 12(56), 38–40 (2013). https://doi.org/10.1145/2535918
Guo, Y., Liu, H., Hao, A., Liu, S., Zhang, X., Liu, H.: Blended learning model via small private online course improves active learning and academic performance of embryology. Clin. Anat. 35(2), 211–221 (2022). https://doi.org/10.1002/ca.23818
Zhang, X., Yu, J., Yang, Y., Feng, C.: A flipped classroom method based on a small private online course in a flipped classroom method based on a small private online course in physiology. Adv. Physiol. Educ. 3(43), 345–349 (2019). https://doi.org/10.1152/advan.00143.2018
Chango, W., Cerezo, R., Romero, C.: Multi-source and multimodal data fusion for predicting academic performance in blended learning university courses. Comput. Electr. Eng. 89, 106908 (2021). https://doi.org/10.1016/j.compeleceng.2020.106908
Wan, H., Ding, J., Gao, X., Yu, Q., Liu, K.: Predicting performance in a small private online course. In: Proceedings of the 10th International Conference on Educational Data Mining, pp. 25–28. International Educational Data Mining Society (IEDMS), Wu Han (2017)
Yu, C.: SPOC-MFLP: a multi-feature learning prediction model for SPOC students using machine learning. J. Appl. Sci. Eng. 21(2), 279–290 (2018). https://doi.org/10.6180/jase.201806_21(2).0016
Rage, R.C., Raga, J.D.: Early prediction of student performance in blended learning courses using deep neural networks. In: 2019 International Symposium on Educational Technology (ISET), pp. 39–43. IEEE Press, New York (2019). https://doi.org/10.1109/ISET.2019.00018
Xu, Z., Yuan, H., Liu, Q.: Student performance prediction based on blended learning. IEEE Trans. Educ. 64(1), 66–73 (2021). https://doi.org/10.1109/TE.2020.3008751
Guo, P.: MOOC and SPOC, which one is better? EURASIA J. Math. Sci. Technol. Educ. 8(13), 5961–5967 (2021). https://doi.org/10.12973/eurasia.2017.01044a
Statsmodels. Statsmodels (2019). https://www.statsmodels.org/stable/index.html
SciPy. SciPy (2018). https://docs.scipy.org/doc/scipy/reference/stats.html
Acknowledgment
The authors would like to thank Southwest University Teaching Reform Research Project (No. SWU19808039) for financially supporting this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xuan, W., Yanmei, L., Fan, L., Xiangliang, L. (2023). Predicting Students Performance in SPOC-Based Blended Learning. In: Hong, W., Weng, Y. (eds) Computer Science and Education. ICCSE 2022. Communications in Computer and Information Science, vol 1812. Springer, Singapore. https://doi.org/10.1007/978-981-99-2446-2_51
Download citation
DOI: https://doi.org/10.1007/978-981-99-2446-2_51
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2445-5
Online ISBN: 978-981-99-2446-2
eBook Packages: Computer ScienceComputer Science (R0)