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

Iulia Pasov, Mihai Dascalu, Nicolae Nistor, Stefan Trausan-Matu

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

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 R2 ¼ :796 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.
Original languageEnglish
Title of host publicationThe Interplay of Data, Technology, Place and People for Smart Learning
Subtitle of host publicationProceedings of the 3rd International Conference on Smart Learning Ecosystems and Regional Development
EditorsHendrik Knoche, Elvira Popescu, Antonio Cartelli
PublisherSpringer
Pages177-185
Number of pages9
Publication statusPublished - 1 Jun 2018
Externally publishedYes
Event3rd Int. Conf. on Smart Learning Ecosystems and Regional Development (SLERD 2018): The Interplay of Data, Technology, Place and People for Smart Learning - Aalborg, Denmark
Duration: 23 May 201825 May 2018

Publication series

SeriesSmart Innovation, Systems and Technologies (SIST)
Volume95

Conference

Conference3rd Int. Conf. on Smart Learning Ecosystems and Regional Development (SLERD 2018)
CountryDenmark
CityAalborg
Period23/05/1825/05/18

Keywords

  • CSCL
  • Time series analysis
  • Automated evaluation of participation
  • RAGE

Fingerprint Dive into the research topics of 'Automated Prediction of Student Participation in Collaborative Dialogs Using Time Series Analyses'. Together they form a unique fingerprint.

  • Projects

    Rage: Realising an Applied Gaming Eco-system

    Westera, W., Georgiadis, K., Saveski, G., van Lankveld, G., Bahreini, K., van der Vegt, W., Berkhout, J., Nyamsuren, E., Kluijfhout, E. & Nadolski, R.

    1/02/1531/07/19

    Project: Research

    Cite this

    Pasov, I., Dascalu, M., Nistor, N., & Trausan-Matu, S. (2018). Automated Prediction of Student Participation in Collaborative Dialogs Using Time Series Analyses. In H. Knoche, E. Popescu, & A. Cartelli (Eds.), The Interplay of Data, Technology, Place and People for Smart Learning: Proceedings of the 3rd International Conference on Smart Learning Ecosystems and Regional Development (pp. 177-185). Springer. Smart Innovation, Systems and Technologies (SIST), Vol.. 95