Learning interactions have been regarded in the context of Technology-Enhanced Learning as an important unit of analysis and  they have been studied by the community of educational researchers from various perspectives (Anderson 2003a; 2003; Garisson 2005) Most of the research is based on the data collected through learner-reported surveys (Miyazoe Anderson 2010; Garison R.D (2005), educational data mining techniques (Zaiane 2002;Tang and McCalla 2005), qualitative text analysis (Muirhead 2000) or social network analysis (Dowson et al 2011). We argue that each of the approaches alone is neither sufficient nor relevant for researchers aiming at conducting large-scale learning analytics in Digital Learning Ecosystems (DLE). We see DLE as the third-generation virtual learning environment, replacing traditional Learning Management Systems. While in LMS (e.g. Moodle) all learning interactions take place within a single closed Web information system and the data is stored in one centralised database, the situation changes radically in DLE. DLE consists of a large and distributed set of dynamically evolving online tools and services, which are selected and used by different groups of learners and facilitators. We have built a prototype of DLE called Dippler (Laanpere et al 2012), it consists of three interconnected components: a central learning flow management service, institutional course management environment and a personal blog-based e-portfolio for each learner. Learners can integrate external social media tools, services and content to their e-portfolios through simple technologies such as RSS-feeds, embedding, linking and widgets.
In order to add learning analytics functionalities to DLE like Dippler, there are two necessary steps to be taken: (1) harvesting, storing and monitoring interaction-related data with rich semantics and (2) identifying methods and tools for analyzing and visualizing the data.
Harvesting, storing and monitoring the data on learning interactions poses challenges due to the very nature of DLE concept – it’s a distributed learning environment where different social tools are selected, used, added and removed from the learner side. Four types of learning interactions take place in such settings: learner-teacher, learner-learner, learner-content and content-content (e.g. aggregators). The current version of Dippler documents these interactions in the form of Activity Stream, which is based on the Activity Base Schema (activitystrea.ms). Dippler’s Activity Stream displays the main types of interactions in the form of a proposition, containing the Actor (a user), the Action (a verb from restricted vocabulary), the Object (a target of the Activity) and timestamp. As most of the Objects and Activities are linked to the domain-related categories (keywords organized in tree structure), it opens the potential for a different kind of learning analytics not currently supported in the traditional LMS. In order to analyze learning interactions in Dippler from the perspective of learning theories (e.g. Communities of Inquiry)(Garison et al 2000, 2001), we need to expand the current Activity Schema of Dippler to contain semantics from Anderson’s model of Communities of Inquiry.

1. Anderson, T. (2003). Modes of interaction in distance education: Recent developments and research questions. In M. Moore (Ed.) Handbook of Distance Education. (p. 129-144). Mahwah, NJ.: Erlbaum. 2. Anderson, T. (2003a). Getting the mix right again: An updated and theoretical rationale for interaction. International Review of Research in Open and Distance Learning, 4(2). 3. Dawson S, Bakharia A, Lockyer L, Heathcote E, (2011) ‘Seeing’ networks: visualising and evaluating student learning networks – report, retrieved January 31, 2013 http://www.olt.gov.au/system/files/resources/CG9_994_Lockyer_Report_2011.pdf Education, 3(2), 1–6. 4. Garison D. R. (2005). Facilitating Cognitive Presence in Online Learning: Interaction Is Not Enough, The American Journal of Distance Education, 19(3), 133–148 5. Garrison, D. R., Anderson, T., & Archer, W. (2000). Critical inquiry in a text-based environment: Computer conferencing in higher education. The Internet and Higher Education, 2(2–3), 87–105. 6. Garrison, D. R., Anderson, T., & Archer, W. (2001). Critical thinking, cognitive presence, and computer conferencing in distance education. The American Journal of Distance Education, 15(1), 7–23 7. Laanpere M., Põldoja H., Normak P. (2012). Designing Dippler — a Next-Generation TEL System. Tatnall, A., Ruohonen, M., Ley, T., Laanpere, M. (Toim.). Open and Social Technologies for Networked Learning (00 - 10). New York: Springer Verlag 8. Miyazoe, T. Anderson, T (2010) Empirical Research on Learners' Perceptions: Interaction Equivalency Theorem in Blended Learning European Journal of Open, Distance and E-Learning, n1 9. Muirhead B., (2000), Enhancing Social Interaction in Computer-Mediated Distance Education, Educational Technology & Society - ETS , vol. 3, no. 4 10. Tang, T., McCalla, G. (2005) Smart recommendation for an evolving elearning system: architecture and experiment, International Journal on E-Learning , 4 (1), 105–129. 11. Zaiane, O. (2001). Web usage mining for a better web-based learning environment. Proceedings of Conference on Advanced Technology for Education , 60–64.