2012 | OriginalPaper | Buchkapitel
Time Series Analysis of Collaborative Activities
verfasst von : Irene-Angelica Chounta, Nikolaos Avouris
Erschienen in: Collaboration and Technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Analysis of collaborative activities is a popular research area in CSCW and CSCL fields since it provides useful information for improving the quality and efficiency of collaborative activities. Prior research has focused on qualitative methods for evaluating collaboration while machine learning algorithms and logfile analysis have been proposed for post-assessment. In this paper we propose the use of time series analysis techniques in order to classify synchronous, collaborative learning activities. Time is an important aspect of collaboration, especially when it takes place synchronously, and can reveal the underlying group dynamics. Therefore time series analysis should be considered as an option when we wish to have a clear view of the process and final outcome of a collaborative activity. We argue that classification of collaborative activities based on time series will also reflect on their qualitative aspects. Collaborative sessions that share similar time series, will also share similar qualitative properties.