Work

Learning analytics in massively multi‐user virtual environments and courses

Year: 2016
Type: article
Abstract: There is much ongoing interest in big data and the role it \ncan play in decision-making in diverse areas of science, \ncommerce and entertainment. By employing a \ncombination of modern artificial intelligence, machine \nlearning and statistics techniques, extremely large and \ncomplex data sets can be ‘mined’ in a variety of ways \nto reveal relationships, patterns and insights not easily \ndiscoverable through standard database management \ntools and data processing applications. In education, data \nmining approaches have been applied to the analysis of \nelectronic stores or repositories of student data for a \nnumber of years now (Romero & Ventura, 2007), but this \nhas been occurring largely at the institutional or sector \nlevel. Such applications, which are sometimes referred to \nas ‘academic analytics’ (Campbell, DeBlois, & Oblinger \n2007; Goldstein & Katz, 2005), have not become \nmainstream, being relevant mainly to governments, \nfunding agencies and institutional administrators rather \nthan students and teachers (Siemens et al., 2011). More \nrecently, a new field known as learning analytics (Long \n& Siemens, 2011; Siemens et al., 2011) has emerged that \nseeks to generate knowledge ‘about learners and their \ncontexts, for purposes of understanding and optimizing \nlearning and the environments in which it occurs’ \n(Siemens, 2011, para. 5). This knowledge can be \nemployed for a range of purposes, among which are to \nallow learners to reflect on their activity and progress in \nrelation to that of others as well as to assist teachers and \nsupport staff in predicting, identifying and supporting \nlearners who may require additional attention and \nintervention (Powell & MacNeill, 2012). \nOccurring in parallel is the burgeoning
Language: English
Open Access status: bronze
OpenAlex ID: W2310297207
FWCI: 0.753
Cites: 9
Cited by: 6
Related to: 10