Computational Methods for the Analysis of Learning and Knowledge Building Communities

Abstract

Learning analytics (LA) features an inherent interest in algorithms and computational methods of analysis. This makes LA an interesting eld of study for computer scientists and mathematically inspired researchers. A differentiated view of the different types of approaches is relevant not only for “technologists” but also for the design and interpre- tation of analytics applications. The “trinity of methods” includes analytics of 1) network structures including actor–actor (social) networks but also actor–artefact networks, 2) processes using methods of sequence analysis, and 3) content using text mining or other techniques of artefact analysis. A summary picture of these approaches and their roots is given. Two recent studies are presented to exemplify challenges and potential bene ts of using advanced computational methods that combine different methodological approaches.