Learning analytics beyond the LMS

Abstract

We present a Connected Learning Analytics (CLA) toolkit, which enables data to be extracted from social media and imported into a Learning Record Store (LRS), as defined by the new xAPI standard. A number of implementation issues are discussed, and a mapping that will enable the consistent storage and then analysis of xAPI verb/object/activity statements across different social media and online environments is introduced. A set of example learning activities are proposed, each facilitated by the Learning Analytics beyond the LMS that the toolkit enables.

Privacy-driven Design of Learning Analytics Applications – Exploring the Design Space of Solutions for Data Sharing and Interoperability

“…They concluded that the way forward cannot simply be to introduce a choice between opt-in or opt-out as "Only by increasing the transparency around learning analytics activities will HEIs gain the trust and fuller co-operation of students" (2015, p. 8). Kitto, Cross, Waters, & Lupton (2015), the authors of the second paper, discussed privacy vs. data ownership and proposed a technical solution, the Connected Learning Analytics Toolkit, as a radically different solution to current systems in the market since "Many of the ethical problems that arise from within the privacy perspective evaporate when students are given full access to their data" (p. 5). Kitto et al (2015) referenced a work by Pardo and Siemens (2014) that advocates a contextual approach with respect to information privacy; sometimes we want our information to be public, sometimes not.…”

The Role of a Reference Synthetic Data Generator within the Field of Learning Analytics.

“…As a standards-based learner activity collection is increasingly adopted within higher education, synthetic xAPI data generation will become increasingly necessary. The xAPI recipes mentioned by Kitto et al (2015) are a starting point for a generator. The improvement of the test plans held by the Apereo Foundation is a potential solution for a reference implementation.…”

“…However, the recipes around how to use those data structures do not yet cover the majority of learning scenarios and are not widely adopted. An example of defining relevant recipes is that of Kitto et al (2015). However, this research needs further expansion and adoption of recipes to cover a much greater range of situations.…”

“…Applying synthetic data to the systems again avoids privacy issues and allows data to be created that model the full range of outcomes, some of which may not yet have been created by "real" students. For example, the full ontology and the recipes describing new types of interactions have yet to be defined for learning management systems (Kitto, Cross, Waters, & Lupton, 2015). The synthetic data themselves can be considered self-descriptive, giving the trainees valuable context information during simulations of their working environment.…”

Learning pulse

“…Looking only at clickstreams, keystrokes and LMS data alone gives a partial representation of the learning activity, which naturally occurs across several platforms [25]. Several authors have pointed out the need to explore data "beyond the LMS" [15] to be able to get more meaningful information of the learning process. We believe that an interesting alternative could be found in the Internet of Things (IoT) and sensor community.…”