Predicting Learners’ Behaviours to Get It Wrong

  • Niels HellerEmail author
  • François Bry
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 804)


One of the most vexing aspects of tertiary education is the learning behaviour of many beginners: Late drop-outs after much time has already been invested in attending a course, incomplete homework even though completed homework is a sufficient condition for success at examinations, and misconceptions that are not overcome early enough. This article presents three predictors related to these learning-impairing behaviours that have been built from data collected with a learning platform and by examining homework assignments, and developed as Hidden Markov Model, by relying on Collaborative Filtering, and by using Multiple Linear Regression. The sensitivities and specificities of the first two predictors are above 70% and the \(R^2\)-error of the third predictor is about 20%. Considering the large numbers of unknown parameters like course-independent learning, this quality is satisfying. The predictors have been developed for fostering a better learning by raising the learners’ consciousness of the deficiencies of their learning. In other words, the predictors aim at “getting it wrong”. The article reports on the predictors and their evaluation.


Learning analytics Behaviour prediction User modelling and adaptation in TEL Evidence-based studies 


  1. 1.
    Abdous, M., Wu, H., Yen, C.J.: Using data mining for predicting relationships between online question theme and final grade. J. Educ. Technol. Soc. 15(3), 77 (2012)Google Scholar
  2. 2.
    Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat. 41(1), 164–171 (1970)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bry, F., Pohl, A.Y.S.: Large class teaching with Backstage. J. Appl. Res. High. Educ. 9(1), 105–128 (2017)CrossRefGoogle Scholar
  4. 4.
    Christensen, R.: Plane Answers to Complex Questions: The Theory of Linear Models. Springer Science & Business Media, Berlin (2011)CrossRefGoogle Scholar
  5. 5.
    Confrey, J.: Chapter 1: a review of the research on student conceptions in mathematics, science, and programming. Rev. Res. Educ. 16(1), 3–56 (1990)CrossRefGoogle Scholar
  6. 6.
    Cripps, A.: Using artificial neural nets to predict academic performance. In: Proceedings of the 1996 ACM Symposium on Applied Computing, pp. 33–37. ACM (1996)Google Scholar
  7. 7.
    Dejaeger, K., Goethals, F., Giangreco, A., Mola, L., Baesens, B.: Gaining insight into student satisfaction using comprehensible data mining techniques. Eur. J. Oper. Res. 218(2), 548–562 (2012)CrossRefGoogle Scholar
  8. 8.
    Dekker, G., Pechenizkiy, M., Vleeshouwers, J.: Predicting students drop out: A case study. In: Educational Data Mining 2009 (2009)Google Scholar
  9. 9.
    Giesbers, B., Rienties, B., Tempelaar, D., Gijselaers, W.: Investigating the relations between motivation, tool use, participation, and performance in an e-learning course using web-videoconferencing. Comput. Hum. Behav. 29(1), 285–292 (2013)CrossRefGoogle Scholar
  10. 10.
    Guo, W.W.: Incorporating statistical and neural network approaches for student course satisfaction analysis and prediction. Expert Syst. Appl. 37(4), 3358–3365 (2010)CrossRefGoogle Scholar
  11. 11.
    Halawa, S., Greene, D., Mitchell, J.: Dropout prediction in MOOCs using learner activity features. eLearning Papers 37 (2014)Google Scholar
  12. 12.
    Linden, G., Smith, B., York, J.: recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 7(1), 76–80 (2003)CrossRefGoogle Scholar
  13. 13.
    Lykourentzou, I., Giannoukos, I., Nikolopoulos, V., Mpardis, G., Loumos, V.: Dropout prediction in e-learning courses through the combination of machine learning techniques. Comput. Educ. 53(3), 950–965 (2009)CrossRefGoogle Scholar
  14. 14.
    Pardos, Z.A., Baker, R.S., San Pedro, M.O., Gowda, S.M., Gowda, S.M.: Affective states and state tests: investigating how affect throughout the school year predicts end of year learning outcomes. In: Proceedings of the Third International Conference on Learning Analytics and Knowledge, pp. 117–124. ACM (2013)Google Scholar
  15. 15.
    Pohl, A.: Fostering awareness and collaboration in large-class lectures. Doctoral thesis, Ludwig-Maximilian University of Munich, Germany (2015)Google Scholar
  16. 16.
    Posner, G.J., Strike, K.A., Hewson, P.W., Gertzog, W.A.: Accommodation of a scientific conception: toward a theory of conceptual change. Sci. Educ. 66(2), 211–227 (1982)CrossRefGoogle Scholar
  17. 17.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  18. 18.
    Radatz, H.: Error analysis in mathematics education. J. Res. Math. Educ. 10(3), 163–172 (1979)CrossRefGoogle Scholar
  19. 19.
    Read, J.R.: Children’s misconceptions and conceptual change in science education (2004).
  20. 20.
    Siemens, G. (ed.): 1st International Conference on Learning Analytics and Knowledge 2011 (2010)Google Scholar
  21. 21.
    Tan, M., Shao, P.: Prediction of student dropout in e-learning program through the use of machine learning method. iJet 10(1), 11–17 (2015)MathSciNetGoogle Scholar
  22. 22.
    Tippett, C.D.: Refutation text in science education: a review of two decades of research. Int. J. Sci. Math. Educ. 8(6), 951–970 (2010)CrossRefGoogle Scholar
  23. 23.
    Williams, E.: Student attitudes towards approaches to learning and assessment. Assess. Eval. High. Educ. 17(1), 45–58 (1992)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute for InformaticsLudwig-Maximilian University of MunichMunichGermany

Personalised recommendations