The Open UniversitySkip to content
 

Discovering student interactions with a collaborative learning forum that predict group collaboration problems

Liu, Shuangyan and Joy, Mike (2011). Discovering student interactions with a collaborative learning forum that predict group collaboration problems. In: ICERI2011 Proceedings: 4th International Conference of Education, Research and Innovation, IATED, pp. 557–564.

Full text available as:
[img]
Preview
PDF (Accepted Manuscript) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (226kB) | Preview
URL: http://www.iated.org/iceri2011/
Google Scholar: Look up in Google Scholar

Abstract

This paper investigates the role of various student interactions with a learning forum in order to ascertain the existence of different group collaboration problems. A particular focus of interest has been learning forums, since forums have become broadly adopted tools to support online group collaboration. The types of collaboration problems were drawn from previous research that identified the main student-induced collaboration problems.

A data set was collected for 87 undergraduates who participated in a web-based computer science group project. It consists of two kinds of data. The first is student interaction data which were collected from a learning forum system on which the group project was undertaken. The second is the data relating to assessment of group collaboration problems, and were gathered through a questionnaire delivered to the students who participated in the group project.

Multinomial logistic regression analysis has been applied for modelling the relationship between a response variable corresponding to the existence of a group collaboration problem and several predictor variables representing various student interactions with a learning forum.

A set of predictive models were produced by the regression analysis, each representing a statistically significant combination of student interactions that predict the existence of one of the collaboration problems in question. The findings reveal that indicators including the number of posts that were created and replied to by individual students, and the number of times that a student viewed a discussion on a learning forum, contribute significantly in predicting the collaboration problems which were identified. The results also demonstrate that how the existence of a problem fluctuates with the alterations in the value of an indicator variable.

The goodness-of-fit of the identified predictive models was measured by the Pearson chi-square test and the results of this test indicate that the models fit the sample data well. The average rate of correct classification by the models was approximately 80%, which means the regression method performs well on the sample data set.

The outcomes of this research can help teachers to assess problems in web-based collaborative group work and also can be used to develop tools for automatically diagnosing group collaboration problems in web-based collaborative learning environments.

Item Type: Conference or Workshop Item
ISBN: 84-615-3324-0, 978-84-615-3324-4
ISSN: 2340-1095
Keywords: group collaboration problems prediction; learning forum; undergraduate group project; multinomial logistical regression; predictive model
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Related URLs:
Item ID: 42143
Depositing User: Shuangyan Liu
Date Deposited: 11 Mar 2015 14:35
Last Modified: 04 Oct 2016 20:26
URI: http://oro.open.ac.uk/id/eprint/42143
Share this page:

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk