Using learning analytics to scale the provision of personalised feedback

Pardo, Abelardo; Jovanović, Jelena; Dawson, Shane; Gašević, Dragan; Mirriahi, Negin

doi:10.1111/bjet.12592

Cited by 264 publications

(182 citation statements)

References 34 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…Thanks to teachers' early involvement and trials, we quickly moved away from conceptualising AI components that only automate the support that students require in this setting, to a hybrid approach where analysis of students' interactions is used both to provide feedback to students directly whenever possible and for driving the TA tool visualisations. This is consistent with the emerging view of AI as augmenting or assisting human intelligence (Baker, ; Gorban, Grechuk, & Tyukin, ; Holstein et al , ; Pardo, Jovanovic, Dawson, Gašević, & Mirriahi, ).…”

Section: Discussionsupporting

confidence: 87%

Intelligent analysis and data visualisation for teacher assistance tools: The case of exploratory learning

Mavrikis¹,

Geraniou²,

Santos³

et al. 2019

Brit J Educational Tech

View full text Add to dashboard Cite

While it is commonly accepted that Learning Analytics (LA) tools can support teachers' awareness and classroom orchestration, not all forms of pedagogy are congruent to the types of data generated by digital technologies or the algorithms used to analyse them. One such pedagogy that has been so far underserved by LA is exploratory learning, exemplified by tools such as simulators, virtual labs, microworlds and some interactive educational games. This paper argues that the combination of intelligent analysis of interaction data from such an Exploratory Learning Environment (ELE) and the targeted design of visualisations has the benefit of supporting classroom orchestration and consequently enabling the adoption of this pedagogy to the classroom. We present a case study of LA in the context of an ELE supporting the learning of algebra. We focus on the formative qualitative evaluation of a suite of Teacher Assistance tools. We draw conclusions relating to the value of the tools to teachers and reflect with transferable lessons for future related work. What is already known about this topic Learning Analytics (LA) tools can support teachers' orchestration but most of the work so far has focus mostly on instructionist pedagogies or Computer‐Supported Collaborative Learning. Exploratory Learning Environments (ELEs) encourage students to freely explore a domain and follow a variety of solutions and have the potential to lead to more engagement and deeper learning. The freedom in ELEs introduces orchestration challenges that hinder the adoption of such pedagogies in classroom. What this paper adds A set of usage scenarios for LA tools for exploratory environments derived from teacher input and design and methodological guidelines based on a reflection from the study. Showcases a suite of Teacher Assistance tools purposefully designed for teachers' orchestration requirements during Exploratory Learning. Empirical evidence of the perceived usefulness of these tools and feedback from a large number of teachers thanks to a methodology of re‐using previously collected classroom data. Implications for practice and/or policy A methodology for involving teachers in the design and evaluation of LA. Highlights teacher training needs for LA. Teachers should be provided with tools that help them orchestrate different activities including ones with digital tools underpinned by a constructionist pedagogy.

show abstract

Section: Discussionsupporting

confidence: 87%

Intelligent analysis and data visualisation for teacher assistance tools: The case of exploratory learning

Mavrikis¹,

Geraniou²,

Santos³

et al. 2019

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…The rise of learning analytics has not created these problems, but it has focused attention upon them. One option is to use analytics to supplement, rather than replace, human understanding, exploring how technology can augment human intelligence (Pardo, Jovanovic, Dawson, Gašević, & Mirriahi, 2019). An alternative approach is to use analytics to investigate why a learning event or program did or did not succeed, rather than to focus on the success of individual students (Liu, Rogers, & Pardo, 2015).…”

Section: Safeguardingmentioning

confidence: 99%

Ethical Challenges for Learning Analytics

Ferguson

2019

Learning Analytics

View full text Add to dashboard Cite

show abstract

“…Learning analytics and educational data mining have also become an important part of the discussion around learning at scale, particularly in light of the need to provide targeted and timely feedback to a growing body of students. As students interact with educational technologies, according to Pardo et al [40], they generate data that can offer a picture of their personal learning performance and needs, followed by the tailoring of personal feedback. In the setting of an undergraduate engineering course, Pardo et al describe how an approach that combined instructor knowledge with digital traces of student interaction around technology allowed for the generation of regular and personalized e-mail feedback messages that met with a positive response from learners and provided evidence of improved academic performance within mid-term examinations.…”

Section: Towards Digital Multimodal Feedbackmentioning

confidence: 99%

To Boldly Go: Feedback as Digital, Multimodal Dialogue

Lamb

2018

MTI

View full text Add to dashboard Cite

This article is concerned with digital, multimodal feedback that supports learning and assessment within education. Drawing on the research literature alongside a case study from a postgraduate program in digital education, I argue that approaching feedback as an ongoing dialogue presented in richly multimodal and digital form can support opportunities for learning that are imaginative, critical, and in-tune with our increasingly digitally-mediated society. Using the examples of a reflective blogging exercise and an assignment built in the Second Life virtual world, I demonstrate how the tutor's emphasis on providing feedback in multimodal form, alongside more conventional print-based approaches, inspired and emboldened students towards the creation of apt and sophisticated coursework. At the same time, the crafting of multimodal feedback carries resource implications and can sit uncomfortably with some deep-rooted assumptions around language-based representations of academic knowledge. This article should be seen in the context of a growing pedagogic and institutional interest in feedback around assessment, alongside the emergence of new ways of communicating and consuming academic content in richly multimodal ways. In this setting, multimodality, technology, and interaction refers to the digitally-mediated dialogue that takes place between the student and tutor around assessment.

show abstract

Using learning analytics to scale the provision of personalised feedback

Cited by 264 publications

References 34 publications

Intelligent analysis and data visualisation for teacher assistance tools: The case of exploratory learning

Intelligent analysis and data visualisation for teacher assistance tools: The case of exploratory learning

Ethical Challenges for Learning Analytics

To Boldly Go: Feedback as Digital, Multimodal Dialogue

Contact Info

Product

Resources

About