Learning Analytics
Learning analytics are data analytical techniques that collect, measure, analyze, and report data of students’ learning processes and outcomes in a certain educational environment (Johnson et al. 2011; Bienkowski et al. 2012; Buckingham Shum, 2012). The computational techniques that can be used for learning analytics are not much different from business intelligence and analytics, including traditional statistical data analysis/visualization and data mining (VanLehn et al. 2005; Anaya & Boticario, 2009; Baker & Yacef, 2009; Baker, 2011). Application areas of learning analytics include modeling of learning behaviors, modeling of learning process, profiling students, analyzing leaning components, modeling of personalization, and assessing students’ learning (Bienkowski et al. 2012). The critical factors of learning analytics include learning objectives, educational data, stakeholders (students, teachers, and institution), instruments, constraints, and internal limitations (competence of interpretation of data) (Greller & Drachsler, 2012). Challenges of big data (Wang & Wang, 2015), including technical resources, innovative analytical tools, and issues of privacy/ethics, are all applicable to implementation of learning analytics. Research into learning analytics is still in an early stage of development. A new journal dedicated to learning analytics has been launched recently (Gasevic et al. 2014). Theories or methodologies of learning analytics beyond the concept are expected to emerge in the academic literature.