Skip to main content

Sequential Three-Way Decisions for Reducing Uncertainty in Dropout Prediction for Online Courses

  • 383 Accesses

Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 449)

Abstract

Massive Open Online Courses (MOOCs) allow accessing qualitative online educational resources for huge amounts of online students. In this context, the dropout phenomenon is known as a nasty problem faced by several existing studies proposing methods and techniques to make predictions on students who are at risk of dropping out. Although the majority of such studies adopt traditional classification algorithms based on supervised methods, the present work proposes a sequential approach based on Three-Way Decisions and Neighborhood Rough Sets. The underlying idea is to exploit weekly data in order to classify, with high levels of precision, students who are likely going towards dropout or not. In cases of uncertainty, the classification decision is deferred to the next week, when new data is available. Such an approach has the advantage to preserve resources and avoiding wasting them with students erroneously classified at risk of dropout. The sequential application of the approach makes the recall increase as new data is gathered.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-99584-3_5
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   219.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-99584-3
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   279.99
Price excludes VAT (USA)
Fig. 1.

References

  1. Adams, A., Liyanagunawardena, T., Williams, S.: MOOCs: a systematic study of the published literature 2008–2012. Int. Rev. Res. Open Dist. Learn. 14, 202–227 (2013)

    Google Scholar 

  2. Alamri, A., et al.: Predicting MOOCs dropout using only two easily obtainable features from the first week’s activities. In: Coy, A., Hayashi, Y., Chang, M. (eds.) ITS 2019. LNCS, vol. 11528, pp. 163–173. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22244-4_20

    CrossRef  Google Scholar 

  3. Blundo, C., Fenza, G., Fuccio, G., Loia, V., Orciuoli, F.: A time-driven FCA-based approach for identifying students’ dropout in MOOCs. Int. J. Intell. Syst. 37(4), 2683–2705 (2021)

    CrossRef  Google Scholar 

  4. Deng, R., Benckendorff, P., Gannaway, D.: Progress and new directions for teaching and learning in MOOCs. Comput. Educ. 129, 48–60 (2019)

    CrossRef  Google Scholar 

  5. Impey, C., Formanek, M.: MOOCs and 100 days of COVID: enrollment surges in massive open online astronomy classes during the coronavirus pandemic. Soc. Sci. Humanit. Open 4(1), 100177. ISSN 2590-2911 (2021)

    Google Scholar 

  6. Jupyter. https://jupyter.org/

  7. Knowledge Discovery and Data Mining. MOOC dataset from KDD cup 2015 (2015). http://data-mining.philippe-fournier-viger.com/the-kddcup-2015-dataset-download-link/

  8. Kumar, S.U., Inbarani, H.H.: A novel neighborhood rough set based classification approach for medical diagnosis. Procedia Comput. Sci. 47, 351–359. ISSN 1877-0509 (2015)

    Google Scholar 

  9. Liu, T.-Y., Li, X.: Finding out reasons for low completion in MOOC environment: an explicable approach using hybrid data mining methods. DEStech Trans. Soc. Sci. Educ. Hum. Sci. 376–384 (2017)

    Google Scholar 

  10. Menardi, G., Torelli, N.: Training and assessing classification rules with imbalanced data. Data Min. Knowl. Discov. 28, 92–122 (2014)

    MathSciNet  CrossRef  Google Scholar 

  11. Numpy. https://numpy.org/

  12. Pandas. https://pandas.pydata.org/

  13. Pawlak, Z.: Rough set approach to knowledge-based decision support. Eur. J. Oper. Res. 99(1), 48–57 (1997)

    CrossRef  Google Scholar 

  14. Python 3. https://www.python.org/

  15. Qian, Y., et al.: Local rough set: a solution to rough data analysis in big data. Int. J. Approximate Reasoning 97, 38–63. ISSN 0888-613X (2018)

    Google Scholar 

  16. Shao, M.-W., Leung, Y., Wu, W.-Z.: Rule acquisition and complexity reduction in formal decision contexts. Int. J. Approximate Reasoning 55(1, Part 2), 259–274. ISSN 0888-613X (2014). Special issue on Decision-Theoretic Rough Sets

    Google Scholar 

  17. Sun, B., Chen, X., Zhang, L., Ma, W.: Three-way decision making approach to conflict analysis and resolution using probabilistic rough set over two universes. Inf. Sci. 507, 809–822 (2019)

    MathSciNet  CrossRef  Google Scholar 

  18. Wang, Q., Qian, Y., Liang, X., Guo, Q., Liang, J.: Local neighborhood rough set. Knowl. Based Syst. 153, 53–64 (2018)

    CrossRef  Google Scholar 

  19. Wang, W., Yu, H., Miao, C.: Deep model for dropout prediction in MOOCs. In: ICCSE 2017: Proceedings of the 2nd International Conference on Crowd Science and Engineering, pp. 26–32 (2017)

    Google Scholar 

  20. Xing, W., Du, D.: Dropout prediction in MOOCs: using deep learning for personalized intervention. J. Educ. Comput. Res. 57, 073563311875701 (2018)

    Google Scholar 

  21. XuetanX. https://www.xuetangx.com/

  22. Yao, Y.: Three-way decisions with probabilistic rough sets. Inf. Sci. 180(3), 341–353. ISSN 0020-0255 (2010)

    Google Scholar 

  23. Yao, Y.: Granular computing and sequential three-way decisions. In: Lingras, P., Wolski, M., Cornelis, C., Mitra, S., Wasilewski, P. (eds.) RSKT 2013. LNCS (LNAI), vol. 8171, pp. 16–27. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41299-8_3

    CrossRef  Google Scholar 

  24. Yao, Y., Deng, X.: Sequential three-way decisions with probabilistic rough sets. In: Proceedings of the 10th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2011, pp. 120–125 (2011)

    Google Scholar 

  25. Zhang, J., Li, T., Ruan, D., Liu, D.: Neighborhood rough sets for dynamic data mining. Int. J. Intell. Syst. 27, 317–342 (2012)

    CrossRef  Google Scholar 

  26. Zhang, T., Yuan, B.: Visualizing MOOC user behaviors: a case study on XuetangX. In: Yin, H., et al. (eds.) IDEAL 2016. LNCS, vol. 9937, pp. 89–98. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46257-8_10

    CrossRef  Google Scholar 

Download references

Acknowledgement

Thanks to Tiziana Coppola for the initial discussion on the used dataset.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Francesco Orciuoli .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Blundo, C., Fenza, G., Fuccio, G., Loia, V., Orciuoli, F. (2022). Sequential Three-Way Decisions for Reducing Uncertainty in Dropout Prediction for Online Courses. In: Barolli, L., Hussain, F., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2022. Lecture Notes in Networks and Systems, vol 449. Springer, Cham. https://doi.org/10.1007/978-3-030-99584-3_5

Download citation