Automated Prediction of Student Participation in Collaborative Dialogs Using Time Series Analyses

  • Iulia Pasov
  • Mihai Dascalu
  • Nicolae Nistor
  • Stefan Trausan-Matu
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 95)


The massive student participation in Computer Supported Collaborative Learning (CSCL) sessions from online classrooms requires intense tutor engagement to track and evaluate individual student participation. In this study, we investigate how the time evolution of messages predicts students’ participation using two models – a linear regression and a Random Forest model. A corpus of 10 chats involving 47 students was scored by 4 human experts and used to evaluate our models. Our analysis shows that students’ pauses length between consecutive messages within a discussion is the strongest participation predictor accounting for \( R^{2} = . 7 9 6 \) variance in the human estimations while using a Random Forest model. Our results provide an extended basis for the automated assessment of student participation in collaborative online discussions.


CSCL Time series analysis Automated evaluation of participation 



This research was partially supported by the 644187 EC2020 Realising an applied Gaming Eco-system (RAGE) project.


  1. 1.
    Murillo Montes de Oca, A., Nistor, N., Dascalu, M., Trausan-Matu, S.: Designing smart knowledge building communities. Int. J. Interact. Des. Archit. 22, 9–21 (2014)Google Scholar
  2. 2.
    Ferschke, O., Howley, I., Tomar, G., Yang, D., Rosé, C.P.: Fostering discussion across communication media in massive open online courses. In: Proceedings of Computer Supported Collaborative Learning, pp. 459–466 (2015)Google Scholar
  3. 3.
    Ferschke, O., Yang, D., Tomar, D., Penstein Rose, C.: Positive impact of collaborative chat participation in an edX MOOC. In: International Conference on Artificial Intelligence in Education, pp. 115–124. Springer, Madrid (2015)Google Scholar
  4. 4.
    Trausan-Matu, D., Dascalu, M., Rebedea, T.: PolyCAFe—automatic support for the polyphonic analysis of CSCL chats. Int. J. Comput. Support. Collaborative Learn. 9(2), 127–156 (2014)CrossRefGoogle Scholar
  5. 5.
    Sfard, A.: On two metaphors for learning and the dangers of choosing just one. Educ. Res. 27(2), 4–13 (1998)CrossRefGoogle Scholar
  6. 6.
    Stahl, G.: Group Cognition: Computer Support for Building Collaborative Knowledge. MIT Press, Cambridge (2006)Google Scholar
  7. 7.
    Trausan-Matu, S., Stahl, G., Sarmiento, J.: Supporting polyphonic collaborative learning. E-Serv. J. 6(1), 58–74 (2007)Google Scholar
  8. 8.
    Nistor, N., Baltes, B., Dascalu, M., Mihaila, D., Trausan-Matu, S.: Participation in virtual academic communities of practice under the influence of technology acceptance and community factors, a learning analytics application. Comput. Hum. Behav. 34, 339–344 (2013). Scholar
  9. 9.
    Dascalu, M., McNamara, D.S., Trausan-Matu, S., Allen, L.K.: Cohesion network analysis of CSCL participation. Behav. Res. Methods, 1–16 (2017)Google Scholar
  10. 10.
    Molomer, S.D., Dascalu, M., Trausan-Matu, S.: Predicting collaboration based on students’ pauses in online CSCL conversations. U.P.B. Sci. Bull. Ser. C 79(2) (2017)Google Scholar
  11. 11.
    Boroujeni, M. S., Sharma, K., Kidzinski, L., Lucignano, L., Dillenbourg, P.: How to quantify student’s regularity? In: European Conference on Technology Enhanced Learning, pp. 277–291. Springer (2016)CrossRefGoogle Scholar
  12. 12.
    Brockwell, P.J., Davis, R.A.: Time Series: Theory and Methods. Springer Science & Business Media, New York (2013)Google Scholar
  13. 13.
    Liaw, A., Wiener, M.: Classification and regression by randomForest. R News 2(3), 18–22 (2002)Google Scholar
  14. 14.
    Webb, N.M.: Sex differences in interaction and achievement in co-operative small groups. J. Educ. Psychol. 75, 33–44 (1984)CrossRefGoogle Scholar
  15. 15.
    Terwel, J., Gillies, R.M., Van den Eeden, P., Hoek, D.: Co-operative learning processes of students: a longitudinal multilevel perspective. Br. J. Educ. Psychol. 71, 619–645 (2001)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Iulia Pasov
    • 1
    • 2
  • Mihai Dascalu
    • 1
    • 3
  • Nicolae Nistor
    • 2
    • 4
  • Stefan Trausan-Matu
    • 1
    • 3
  1. 1.Faculty of Automatic Control and Computer ScienceUniversity “Politehnica” BucharestBucharestRomania
  2. 2.Faculty of Psychology and Educational SciencesLudwig-Maximilians-UniversitätMunichGermany
  3. 3.Academy of Romanian ScientistsBucharestRomania
  4. 4.Richard W. Riley College of Education and LeadershipWalden UniversityMinneapolisUSA

Personalised recommendations