Alan Berg

Ethical and privacy issues in the application of learning analytics

The large-scale production, collection, aggregation, and processing of information from various learning platforms and online environments have led to ethical and privacy concerns regarding potential harm to individuals and society. In the past, these types of concern have impacted on areas as diverse as computer science, legal studies and surveillance studies. Within a European consortium that brings together the EU project LACE, the SURF SIG Learning Analytics, the Apereo Foundation and the EATEL SIG dataTEL, we aim to understand the issues with greater clarity, and to find ways of overcoming the issues and research challenges related to ethical and privacy aspects of learning analytics practice. This interactive workshop aims to raise awareness of major ethics and privacy issues. It will also be used to develop practical solutions to advance the application of learning analytics technologies.

The dutch xAPI experience

We present the collected experiences since 2012 of the Dutch Special Interest Group (SIG) for Learning Analytics in the application of the xAPI standard. We have been experimenting and exchanging best practices around the application of xAPI in various contexts. The practices include different design patterns centered around Learning Record Stores. We present three projects that apply xAPI in very different ways and publish a consistent set of xAPI recipes.

LAK17 hackathon: getting the right information to the right people so they can take the right action

The hackathon is intended to be a practical hands-on workshop involving participants from academia and commercial organizations with both technical and practitioner expertise. It will consider the outstanding challenge of visualizations which are effective for the intended audience: informing action, not likely to be misinterpreted, and embodying contextual appropriacy, etc. It will surface particular issues as workshop challenges and explore responses to these challenges as visualizations resting upon interoperability standards and API-oriented open architectures.

Combining Learning Analytics with Job Market Intelligence to Support Learning at the Workplace

Numerous research articles are concerned with the issues surrounding the deployment of e-portfolios. Without proper mentorship, well-designed e-portfolios and stable systems, the learner’s experience is often negative. In this chapter, we review how to combine two large-scale big data infrastructures – the JISC UK national experimental learning analytics (LA) and the Cedefop’s European Job Market Intelligence (JMI) infrastructure – to provide optimised and just-in-time advice. LA is a new data-driven field and is rich in methods and analytical approaches. The focus of LA is the optimisation of the learning environment by capturing and analysing the learner’s online digital traces. JMI digests vacancy data providing a broad overview of the job market including new and emerging skill demands. We look towards a future where we populate e-portfolios with authentic job market-related tasks providing transferable long-term markers of attainment. We populate through entity extraction running ensembles of machine learning algorithms across millions of job descriptions. We enhance the process with LA allowing us to approximate the skill level of the learner and select the tasks within the e-portfolio most appropriate for that learner relative to their local and temporal workplace demands.

Ethical and privacy issues in the design of learning analytics applications

Issues related to Ethics and Privacy have become a major stumbling block in application of Learning Analytics technologies on a large scale. Recently, the learning analytics community at large has more actively addressed the EP4LA issues, and we are now starting to see learning analytics solutions that are designed not only as an afterthought, but also with these issues in mind. The 2nd EP4LA@LAK16 workshop will bring the discussion on ethics and privacy for learning analytics to a the next level, helping to build an agenda for organizational and technical design of LA solutions, addressing the different processes of a learning analytics workflow.

Learning Analytics Pilot with Coach2 - Searching for Effective Mirroring

Coach2 project investigated usability and effectiveness of Learning Analytics in a group of Bachelor courses in the area of Computer Science. An advanced architecture was developed and implemented, including a standalone Learning Record Store for data storage and easy access to miscellaneous data, Machine Learning techniques for determining relevant predictors, and a dashboard for informing learners. The overall approach was based on mirroring, the idea that learners see themselves operating in the context of their peers. The results were informative in terms of pro’s and con’s regarding the design and approach. The treatment showed tendencies, but finding statistical significant results turned out difficult. This paper reports on the Coach2 project.