Model for early prediction of dropout in an introduction to programming course

• João Pedro Freire UFRJ
• Flávia M. P. F. Landim UFRJ
• Laura O. Moraes UNIRIO
• Carla A. D. M. Delgado UFRJ
• Carlos Eduardo Pedreira UFRJ

DOI: https://doi.org/10.5753/wei.2024.2526

Abstract

Learning programming is essential for students in various careers. In this article, we used statistical models to predict dropout from introductory programming courses and identify relevant variables in the early identification of students at risk. To build the model, we combined statistical inference with machine learning techniques to achieve both interpretability and performance. The predictions achieved an AUC greater than 0.8 in the weekly models starting from the fourth week of classes, enabling an early warning for instructors. Among the variables involved, it was observed that consistency in solving exercises has a greater influence than the time taken to develop the solution in identifying students with potential dropout risk.

References

Agrusti, F., Mezzini, M., and Bonavolontà, G. (2020). Deep learning approach for predicting university dropout: a case study at roma tre university. Journal of e-Learning and Knowledge Society, 16(1):44–54.

Al-Shabandar, R., Hussain, A. J., Liatsis, P., and Keight, R. (2018). Analyzing learners behavior in moocs: An examination of performance and motivation using a data-driven approach. IEEE Access, 6:73669–73685.

Bravo-Agapito, J., Romero, S. J., and Pamplona, S. (2021). Early prediction of undergraduate student’s academic performance in completely online learning: A five-year study. Computers in Human Behavior, 115:106595.

Burgos, C., Campanario, M. L., de la Peña, D., Lara, J. A., Lizcano, D., and Martínez, M. A. (2018). Data mining for modeling students’ performance: A tutoring action plan to prevent academic dropout. Computers & Electrical Engineering, 66:541–556.

Chen, W., Brinton, C. G., Cao, D., Mason-Singh, A., Lu, C., and Chiang, M. (2019). Early detection prediction of learning outcomes in online short-courses via learning behaviors. IEEE Transactions on Learning Technologies, 12(1):44–58.

Delgado, C., da Silva, J., Mascarenhas, F., and Duboc, A. (2016). The teaching of functions as the first step to learn imperative programming. Anais do Workshop sobre Educação em Computação (WEI), pages 2393–2402.

Dobson, A. and Barnett, A. (2008). An Introduction to Generalized Linear Models. Chapman & Hall/CRC Texts in Statistical Science. CRC Press.

Hu, Y.-H., Lo, C.-L., and Shih, S.-P. (2014). Developing early warning systems to predict students’ online learning performance. Computers in Human Behavior, 36:469–478.

James, G., Witten, D., Hastie, T., and Tibishirani, R. (2021). An Introduction to Statistical Learning with Applications in R. Springer, New York, NY, 2 edition.

Marbouti, F., Diefes-Dux, H. A., and Madhavan, K. (2016). Models for early prediction of at-risk students in a course using standards-based grading. Computers & Education, 103:1–15.

Montgomery, D., Peck, E., and Vining, G. (2013). Introduction to Linear Regression Analysis. Wiley Series in Probability and Statistics. Wiley.

Moraes, L., Delgado, C., Freire, J., and Pedreira, C. (2022). Machine teaching: uma ferramenta didática e de análise de dados para suporte a cursos introdutórios de programação. In Anais do II Simpósio Brasileiro de Educação em Computação, pages 213–223, Porto Alegre, RS, Brasil. SBC.

Qian, Y. and Lehman, J. (2017). Students’ misconceptions and other difficulties in introductory programming: A literature review. ACM Transactions on Computing Education, 18(1).

Xará, G., Moraes, L., Delgado, C., Freire, J., and Farias, C. (2023). Dealing with a large number of students and inequality when teaching programming in higher education. In Anais do XXIX Workshop de Informática na Escola, pages 1230–1242, Porto Alegre, RS, Brasil. SBC.