Abstract
In recent years, technology enhanced learning platforms became widely accessible. In particular, the number of Massive Open Online Courses (MOOCs) has—and still is—constantly growing. This widespread adoption of MOOCs triggered the development of specialized solutions, that emphasize or enhance various aspects of traditional MOOCs. Despite this significant diversity in approaches to implementing MOOCs, many of the solutions share a plethora of common problems. For example, high dropout rate is an on-going problem that still needs to be tackled in the majority of MOOCs. In this paper, we set out to analyze dropout problem for a number of different systems with the goal of contributing to a better understanding of rules that govern how MOOCs in general and dropouts in particular evolve. To that end, we report on and analyze MOOCs from Universidad Galileo and Curtin University. First, we analyze the MOOCs of each system independently and then build a model and predict dropouts across the two systems. Finally, we identify and discuss features that best predict if users will drop out or continue and complete a MOOC using Boosted Decision Trees. The main contribution of this paper is a unified model, which allows for an early prediction of at-risk or dropout users across different systems. Furthermore, we also identify and discuss the most indicative features of our model. Our results indicate that users’ behaviors during the initial phase of MOOCs relate to their final results.
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
Notes
- 1.
- 2.
- 3.
- 4.
A complete description of edX logs can be found at http://edx.readthedocs.io.
References
Balakrishnan, G., Coetzee, D.: Predicting student retention in massive open online courses using hidden Markov models. Electrical Engineering and Computer Sciences, University of California at Berkeley (2013)
Boyer, S., Veeramachaneni, K.: Transfer learning for predictive models in massive open online courses. In: Conati, C., Heffernan, N., Mitrovic, A., Verdejo, M.F. (eds.) AIED 2015. LNCS, vol. 9112, pp. 54–63. Springer, Cham (2015). doi:10.1007/978-3-319-19773-9_6
Chapelle, O., Vapnik, V., Bousquet, O., Mukherjee, S.: Choosing multiple parameters for support vector machines. Mach. Learn. 46(1–3), 131–159 (2002)
Chen, Y.W., Lin, C.J.: Combining SVMs with various feature selection strategies. In: Guyon, I., Nikravesh, M., Gunn, S., Zadeh, L.A. (eds.) Feature Extraction, pp. 315–324. Springer, Heidelberg (2006). doi:10.1007/978-3-540-35488-8_13
Clow, D.: MOOCs and the funnel of participation. In: Proceedings of the Third International Conference on Learning Analytics and Knowledge, pp. 185–189. ACM (2013)
Coffrin, C., Corrin, L., de Barba, P., Kennedy, G.: Visualizing patterns of student engagement and performance in MOOCs. In: Proceedings of the Fourth International Conference on Learning Analytics and Knowledge, pp. 83–92. ACM (2014)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)
Guetl, C., Chang, V., Hernández Rizzardini, R., Morales, M.: Must we be concerned with the massive drop-outs in MOOC? An attrition analysis of open courses. In: Proceedings of the International Conference Interactive Collaborative Learning, ICL 2014 (2014)
Guo, X., Yin, Y., Dong, C., Yang, G., Zhou, G.: On the class imbalance problem. In: Fourth International Conference on Natural Computation, ICNC 2008, vol. 4, pp. 192–201. IEEE (2008)
Guruler, H., Istanbullu, A., Karahasan, M.: A new student performance analysing system using knowledge discovery in higher educational databases. Comput. Educ. 55(1), 247–254 (2010)
Gütl, C., Rizzardini, R.H., Chang, V., Morales, M.: Attrition in MOOC: lessons learned from drop-out students. In: Uden, L., Sinclair, J., Tao, Y.-H., Liberona, D. (eds.) LTEC 2014. CCIS, vol. 446, pp. 37–48. Springer, Cham (2014). doi:10.1007/978-3-319-10671-7_4
Japkowicz, N., et al.: Learning from imbalanced data sets: a comparison of various strategies. In: AAAI Workshop on Learning from Imbalanced Data Sets, Menlo Park, CA, vol. 68, pp. 10–15 (2000)
Jiang, S., Williams, A., Schenke, K., Warschauer, M., O’dowd, D.: Predicting MOOC performance with week 1 behavior. In: Educational Data Mining 2014 (2014)
Jordan, K.: Initial trends in enrolment and completion of massive open online courses. Int. Rev. Res. Open Distrib. Learn. 15(1), 133–160 (2014)
Kizilcec, R.F., Piech, C., Schneider, E.: Deconstructing disengagement: analyzing learner subpopulations in massive open online courses. In: Proceedings of the Third International Conference on Learning Analytics and Knowledge, pp. 170–179. ACM (2013)
Li, N., Kidziński, Ł., Jermann, P., Dillenbourg, P.: MOOC video interaction patterns: what do they tell us? In: Conole, G., Klobučar, T., Rensing, C., Konert, J., Lavoué, É. (eds.) EC-TEL 2015. LNCS, vol. 9307, pp. 197–210. Springer, Cham (2015). doi:10.1007/978-3-319-24258-3_15
Liyanagunawardena, T.R., Adams, A.A., Williams, S.A.: MOOCs: a systematic study of the published literature 2008–2012. Int. Rev. Res. Open Distrib. Learn. 14(3), 202–227 (2013)
Sinharay, S.: An ncme instructional module on data mining methods for classification and regression. Educ. Meas. Issues Pract. 35(3), 38–54 (2016)
Vitiello, M., Walk, S., Hernández, R., Helic, D., Gütl, C.: Classifying students to improve MOOC dropout rates. In: Research Track, p. 501 (2016)
Xing, W., Chen, X., Stein, J., Marcinkowski, M.: Temporal predication of dropouts in MOOCs: reaching the low hanging fruit through stacking generalization. Comput. Hum. Behav. 58, 119–129 (2016)
Yousef, A.M.F., Chatti, M.A., Wosnitza, M., Schroeder, U.: A cluster analysis of MOOC stakeholder perspectives. RUSC Univ. Knowl. Soc. J. 12(1), 74–90 (2015)
Acknowledgments
The authors would like to thank the MOOC Maker Project (http://www.moocmaker.org/), Universidad Galileo and Curtin University for providing the datasets for the analysis and the Graz University of Technology and Curtin University for supporting the research visits of Massimo Vitiello and Christian Guetl.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Vitiello, M., Walk, S., Chang, V., Hernandez, R., Helic, D., Guetl, C. (2017). MOOC Dropouts: A Multi-system Classifier. In: Lavoué, É., Drachsler, H., Verbert, K., Broisin, J., Pérez-Sanagustín, M. (eds) Data Driven Approaches in Digital Education. EC-TEL 2017. Lecture Notes in Computer Science(), vol 10474. Springer, Cham. https://doi.org/10.1007/978-3-319-66610-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-66610-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66609-9
Online ISBN: 978-3-319-66610-5
eBook Packages: Computer ScienceComputer Science (R0)