Learning analytics is an emerging but rapidly growing field seen as offering unquestionable benefit to higher education institutions and students alike. Indeed, given its huge potential to transform the student experience, it could be argued that higher education has a duty to use learning analytics. In the flurry of excitement and eagerness to develop ever slicker predictive systems, few pause to consider whether the increasing use of student data also leads to increasing concerns. This chapter argues that the issue is not whether higher education should use student data, but under which conditions, for what purpose, for whose benefit, and in ways in which students may be actively involved. The authors explore issues including the constructs of general data and student data, and the scope for student responsibility in the collection, analysis and use of their data. An example of student engagement in practice reviews the policy created by the Open University in 2014. The chapter concludes with an exploration of general principles for a new deal on student data in learning analytics.
TopIntroduction
It is easy to be seduced by the lure of our ever-increasing access to student data to address and mitigate against the myriad of challenges facing higher education institutions (HEIs) (Greenwood, Stopczynski, Sweat, Hardjono & Pentland, 2015; Stiles, 2012; Watters, 2013; Wishon & Rome, 2012). Challenges include, inter alia, changes in funding regimes and regulatory frameworks necessitating greater accountability to a widening range of stakeholders such as national governments, accreditation and quality assurance bodies, employers and students (Altbach, Reisberg, & Rumbley, 2009) (also see Bowen & Lack, 2013; Carr, 2012; Christensen, 2008; Hillman, Tandberg, & Fryar, 2015; New Media Consortium, 2015; Shirky, 2014). Though anything but a recent development (see e.g., Hartley, 1995), funding increasingly follows performance rather than preceding it (Hillman et al., 2015). The continuous decrease of public funding for higher education increases the pressures on higher education institutions to not only be accountable to an increasing number of stakeholders, but also to ensure the effectiveness of their teaching and student support strategies. There are also increasing concerns that HEIs have not solved, nor done enough to attempt to solve, the ‘revolving door’ syndrome whereby many students either fail to complete their courses or programmes or take much longer than planned (Subotzky & Prinsloo, 2011; Tait, 2015).
As teaching and learning increasingly move online and digital, the amount of digital data available for harvesting, analysis and use increases. HEIs’ access to and use of student data is thought to have the potential to revolutionise learning (Van Rijmenam, 2013) with the expectation that it will change ‘everything’ (Wagner & Ice, 2012), that student data is the new black (Booth, 2012) and the new oil (Watters, 2013). The current emphasis on the ‘potential’ of learning analytics without (as of yet) definitive evidence that learning analytics does indeed provide appropriate and actionable evidence (Clow, 2013a, 2013b; Essa, 2013; Feldstein, 2013; Selwyn, 2014), can produce and sustain a number of ‘blind spots’ (Selwyn & Facer, 2013).
In a climate of expectation then that the increased collection and analysis of student data can provide much needed intelligence to both increase our understanding of the challenges and issues facing HEIs and may further assist in formulating more effective responses; there are also concerns that data1 and increasingly Big Data, is not an unqualified good (Boyd and Crawford, 2012, 2013; Kitchen, 2014a). The harvesting, analysis and use of student data must also be seriously considered amidst the discourses surrounding privacy, student surveillance, the nature of evidence in education, and so forth (Biesta, 2007, 2010; Eynon, 2013; Prinsloo & Slade, 2013; Selwyn & Facer, 2013; Wagner & Ice, 2012).