Abstract
Various stumbles occur when learning programming, which leads to lower learning efficiency and motivation. If such stumbles could be detected automatically, teachers could monitor learners’ progress and support passive students. Stumbles in learning programming can be classified into several types, which could be divided into those that are evident from the source code the learner wrote and those that are expressed in their psychological state. These stumbles could be detected by combining biometric data with code-related metrics. In this study, we propose a method to detect stumbles in learning programming by combining the learner’s heart rate information with code-related metrics. We compared the accuracy of models using only code-related metrics, using only heart rate information, and using a combination of both. The results showed that the code-related model and the multimodal model had the highest accuracy and the multimodal model can detect the most variety of stumbles.
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
Processing. https://processing.org/
Carter, J., Dewan, P.: Design, implementation, and evaluation of an approach for determining when programmers are having difficulty. In: Proceedings of the 16th ACM International Conference on Supporting Group Work (GROUP 2010), pp. 215–224, January 2010
Fritz, T., Begel, A., Müller, S.C., Yigit-Elliott, S., Züger, M.: Using psycho-physiological measures to assess task difficulty in software development. In: Proceedings of the 36th International Conference on Software Engineering (ICSE 2014), pp. 402–413, May 2014
Müller, S.C., Fritz, T.: Using (bio) metrics to predict code quality online. In: 2016 IEEE/ACM 38th International Conference on Software Engineering (ICSE 2016), pp. 452–463, May 2016
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/a:1010933404324
p5.js. https://p5js.org/
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Acknowledgments
This research was supported in part by JST CREST Grant Number JPMJCR18A3.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Oka, H., Ohnishi, A., Terada, T., Tsukamoto, M. (2022). A Stumble Detection Method for Programming with Multi-modal Information. In: Delir Haghighi, P., Khalil, I., Kotsis, G. (eds) Advances in Mobile Computing and Multimedia Intelligence. MoMM 2022. Lecture Notes in Computer Science, vol 13634. Springer, Cham. https://doi.org/10.1007/978-3-031-20436-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-20436-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20435-7
Online ISBN: 978-3-031-20436-4
eBook Packages: Computer ScienceComputer Science (R0)