How to Aggregate Lesson Observation Data into Learning Analytics Datasets?

The technological environment that supports the learning process tends to be the main data source for Learning Analytics. However, this trend leaves out those parts of the learning process that are not computer-mediated. To overcome this problem, involving additional data gathering techniques such as ambient sensors, audio and video recordings, or even observations could enrich datasets. This paper focuses on how the data extracted from the observations can be integrated with data coming from activity tracking, resulting in a multimodal dataset. The paper identifies the need for theoretical and pedagogical semantics in multimodal learning analytics, and examines the xAPI potential for the multimodal data gathering and aggregation. Finally, we propose an approach for pedagogy-driven observational data identification. As a proof of concept, we have applied the approach in two research works where observations had been used to enrich or triangulate the results obtained for traditional data sources. Through these examples, we illustrate some of the challenges that multimodal dataset may present when including observational data

Special issue on: Learning Analytics (Editorial)

Maria Jesus Rodriguez Triana

With the general technological advances of the recent years, current learning environments amass an abundance of data. Albeit such data offer the chance of better understand the learning process, stakeholders – learners, teachers and institutions – often need additional support to make sense of it (Dyckhoff et al., 2013; Macfadyen and Dawson, 2012). The acknowledgement of these needs is at the heart of the recent emergence of Learning Analytics (LA), a research area that draws from multiple disciplines such as educational science, information and computer science, sociology, psychology, statistics and educational data mining (Buckingham Shum and Ferguson, 2012). This multidisciplinarity in LA has motivated the work done by Ferguson (2012), which provides a first review of the drivers, development and challenges of this novel and young research area. Our understanding of learning analytics is based on the definition from the Society for Learning Analytics (SoLAR – Society for Learning Analytics1) which specifies that “Learning analytics is the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs”. Since 2011, the Horizon reports list Learning Analytics as a hot topic in higher education and indicate the importance of data for this field (Johnson et al., 2011). Learning analytics are able to provide a fresh view on understanding of teaching and learning by observing patterns of complex data (Johnson et al., 2012). Furthermore, it will influence the evolution of higher education in a great measure. Nowadays, learners have access to a huge amount of online information having themselves the possibility of being content creators and information sharers. Therefore the quantity of available information grows in an exponential way, once that each and every citizen can access and produce information. For these purposes, learners have at their disposal many online resources, including LMSs, VLEs, MOOCs and many other online tools that facilitate the learning process and the development of competences. Taking into account these online learning facilities and therefore the learners’ acquisition of knowledge, it is also easier to measure and analyse their experiences by using learning analytics tools. Different online courses and institutions provide dashboards with information about student experiences, flaws and successes. Although the investigation of behavioural specific data makes learning analytics complex, the time comes to utilise personalised learning environments adapted to students learning paths, skills, previous knowledge, competences and motivation.

2013

Towards Open Data in Digital Education Platforms

Juan Carlos Farah, Denis Gillet, Maria Jesus Rodriguez Triana, Joana Catarina Soares Machado

Despite the traction gained by the open data movement and the rise of big data and learning analytics in education, there is limited support for researchers in education to generate, access, and share experimental data using openly-available digital education platforms. To explore how this gap could be addressed and elicit requirements, we conducted a survey with 40 researchers in the field of technology-enhanced learning, examining their experience and needs handling research data. Drawing on the results of our survey, we devised a set of features that educational platforms should provide to address the identified requirements, enabling researchers in education to run studies within typical learning environments, adhere to legal and ethical frameworks concerning privacy, and share their data confidently with a wider audience. We then categorized these features into five stages that represent the user flow, namely (1) Bootstrapping Research Studies, (2) Ensuring Consent, (3) Gathering Data, (4) Managing Data Sets, and (5) Supporting Open Research and Collaboration. Our aim is to guide forthcoming research and developments to relieve researchers of the burdens of conducting data-sensitive experiments, support the adoption of best practices, and pave the way for open data policies in digital education.

IEEE2019

AngeLA: Putting the Teacher in Control of Student Privacy in the Online Classroom

Denis Gillet, Sten Govaerts, Andrii Vozniuk

Learning analytics (LA) is often considered as a means to improve learning and learning environments by measuring student behaviour, analysing the tracked data and acting upon the results. The use of LA tools implies recording and processing of student activities conducted on software platforms. This paper proposes a flexible, contextual and intuitive way to provide the teacher with full control over student activity tracking in online learning environments. We call this approach AngeLA, inspired by an angel guarding over LA privacy. AngeLA mimics in a virtual space the privacy control mechanism that works well in a physical room: if a person is present in a room, she is able to observe all activities happening in the room. AngeLA serves two main purposes: (1) it increases the awareness of teachers about the activity tracking and (2) provides an intuitive way to manage the activity tracking permissions. This approach can be applied to various learning environments and social media platforms. We have implemented AngeLA in Graasp, a social platform that fosters collaborative activities.

2014

Special issue on: Learning Analytics (Editorial)

Maria Jesus Rodriguez Triana

2013