There is much ongoing interest in big data and the role it can play in decision-making in diverse areas of science,commerce and entertainment. By employing a combination of modern artificial intelligence, machine learning and statistics techniques, extremely large and complex data sets can be ‘mined’ in a variety of ways to reveal relationships, patterns and insights not easily discoverable through standard database management tools and data processing applications. In education, datamining approaches have been applied to the analysis of electronic stores or repositories of student data for anumber of years now (Romero & Ventura, 2007), but this has been occurring largely at the institutional or sector level. Such applications, which are sometimes referred toas ‘academic analytics’ (Campbell, DeBlois, & Oblinger2007; Goldstein & Katz, 2005), have not become mainstream, being relevant mainly to governments,funding agencies and institutional administrators ratherthan students and teachers (Siemens et al., 2011). Morerecently, a new field known as learning analytics (Long& Siemens, 2011; Siemens et al., 2011) has emerged thatseeks to generate knowledge ‘about learners and theircontexts, for purposes of understanding and optimizinglearning and the environments in which it occurs’(Siemens, 2011, para. 5). This knowledge can beemployed for a range of purposes, among which are toallow learners to reflect on their activity and progress inrelation to that of others as well as to assist teachers andsupport staff in predicting, identifying and supportinglearners who may require additional attention andintervention (Powell & MacNeill, 2012).
- Learning analytics
- Virtual environments
- Virtual courses
Lee, M. J. W., Kirschner, P. A., & Kester, L. (2016). Learning analytics in massively multi-user virtual environments and courses. Journal of Computer Assisted Learning, 32(3), 187-189. https://doi.org/10.1111/jcal.12139