Paper Info
Title
Modelling and identifying collaborative situations in a collocated multi-display groupware setting
Abstract
Detecting the presence or absence of collaboration during group work is important for providing help and feedback during sessions. We propose an approach which automatically distinguishes between the times when a co-located group of learners, using a problem solving computer-based environment, is engaged in collaborative, non-collaborative or somewhat collaborative behaviour. We exploit the available data, audio and application log traces, to automatically infer useful aspects of the group collaboration and propose a set of features to code them. We then use a set of classifiers and evaluate whether their results accurately match the observations made on videorecordings. Results show up to 69.4% accuracy (depending on the classifier) and that the error rate for extreme misclassification (e.g. when a collaborative episode is classified as non-collaborative, or vice-versa) is less than 7.6%. We argue that this technique can be used to show the teacher and the learners an overview of the extent of their collaboration so they can become aware of it.
Year
DOI
Venue
2011
10.1007/978-3-642-21869-9_27
AIED
Keywords
Field
DocType
collaborative behaviour,available data,application log trace,co-located group,error rate,group work,group collaboration,extreme misclassification,collaborative situation,computer-based environment,collocated multi-display groupware setting,collaborative episode,data mining,collaborative learning
Collaborative learning,Computer science,Collaborative software,Word error rate,Group work,Exploit,Artificial intelligence,Group collaboration,Classifier (linguistics),Machine learning
Conference
Volume
ISSN
Citations 
6738
0302-9743
13
PageRank 
References 
Authors
0.86
12
4
Name
Order
Citations
PageRank
Roberto Martinez124033.05
James R. Wallace229623.17
Judy Kay31937169.27
Kalina Yacef479880.57