eLearning Papers 40 1 From the field eLearning Papers • ISSN: 1887-1542 • www.openeducationeuropa.eu/en/elearning_papers n.º 40 • January 2015 Learning Analytics, aspects, technology enhanced learning Tags Martin Ebner martin.ebner@tugraz.at Behnam Taraghi b.taraghi@tugraz.at Anna Saranti s0473056@sbox.tugraz.at Social Learning, Computer and Information Services Graz University of Technology Graz, Austria Sandra Schön sandra.schoen@ salzburgresearch.at Innovation Lab, Salzburg Research Forschungsgesellschaft, Salzburg, Austria Seven features of smart learning analytics - lessons learned from four years of research with learning analytics Learning Analycs (LA) is an emerging field; the analysis of a large amount of data helps us to gain deeper insights into the learning process. This contribuon points out that pure analysis of data is not enough. Building on our own experiences from the field, seven features of smart learning analycs are described. From our point of view these features are aspects that should be considered while deploying LA. 1. Introduction Already back in 2006 Retalis et al. proposed their first thoughts on “Learning Analycs” and considered interacon analysis as a promising way to beer understand the learner’s behavior. A couple of years later, further acvies were organized, especially Long and Siemens (Long & Siemens, 2011) predicted that the most important factor shaping the future of higher educaon will be big data and analycs. Since then, scienfic conferences, different reports (e.g. Horizon report, 2011) and public funding referred to Learning Analycs. Nowadays, discussing about the topic Learning Analycs is aracng many researchers worldwide. According to Siemens and Baker (Siemens & Baker, 2012) LA “is the measurement, collecon, analysis and reporng of data about learners and their contexts, for purposes of understanding and opmizing learning and the environments in which it occurs”. Further research publicaons refined the definion towards more students’ acvies (Duval, 2010) or proposed descripve models and frameworks (cf. Siemens 2011; Elias 2011; Greller & Drachsler 2012; Cooper 2012; Cha et al. 2012; Friesen 2013). Within our own work and studies, we worked with LA in diverse contexts of learning in schools and higher educaon. At first glance, the difference between Educaonal Data Mining (EDM) and Learning Analycs is not obvious (Baker et al., 2012). Therefore the last years of research was dominated to explain why LA differs from EDM and why a new research field is absolutely necessary. Furthermore the authors did several field studies using learning analycs (Schön et al., 2012; Ebner & Schön, 2013; Ebner et al., 2013; Taraghi et al., 2013; Taraghi et al., 2014a; Greller et al., 2014; Taraghi et al., 2014b). Against this background we tried to formulate features that we consider as crucial for smart implementaon of LA. From our point of you, these are effecve also in performance support in organizaons as well as for learning support in classrooms. These aspects are independent from the context, but important for the support of learning and learners Authors