Evaluating Student-Facing Learning Dashboards of Affective States

Sedrakyan, Gayane; Leony, Derick; Muñoz‐Merino, Pedro J.; Kloos, Carlos Delgado; Verbert, Katrien

doi:10.1007/978-3-319-66610-5_17

Cited by 15 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Di Mitri et al (2016) observe the levels of productivity, stress, challenge and the potential impact on learning. This is an emergent research area for LADs that also focuses on biofeedback perspectives that can be achieved based on physiological data analytics collected from wearable sensors 1 as well as dashboard feedback on emotions (Leony et al, 2017;Sedrakyan, Leony, Muñoz-Merino, Kloos, & Verbert, 2017). Other examples may include network analytics (e.g., understanding the influence of social networks, behavior of using devices/software, etc.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts

Sedrakyan

Mannens

Verbert

2019

Journal of Computer Languages

Self Cite

View full text Add to dashboard Cite

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights  little is known theoretically on the dashboard design principles  earlier research links design and educational science concepts to design feedback  we extend earlier research by linking dashboard design and visualization concepts  general recommendations are derived to guide the choice of visual representations  a case example is given showing visualizations per intended feedback / goal

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts

Sedrakyan

Mannens

Verbert

2019

Journal of Computer Languages

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, some of the older work in this area has focused on how to represent students' possibly incomplete and inaccurate knowledge. More recent work has focused on, for example, how to decompose knowledge targeted in instruction so that the student's performance on activities in the system (i.e., the targeted knowledge) can be accurately tracked [45,46].…”

Section: A History Of Olmsmentioning

confidence: 99%

Open learner models and learning analytics dashboards

Bodily

Kay

Aleven

et al. 2018

Proceedings of the 8th International Conference on Learning Analytics and Knowledge

Self Cite

125

View full text Add to dashboard Cite

This paper aims to link Learning Analytics Dashboards (LADs) to the corpus of research on Open Learner Models (OLMs), as both have similar goals. We conducted a systematic review of work on OLMs and compare this with LADs for learners in terms of (i) data use and modelling, (ii) key publication venues, (iii) authors and articles, (iv) key themes, and (v) system evaluation. We highlight the similarities and differences between the research on LADs and OLMs. Our key contribution is a bridge between these two areas as a foundation for building upon the strengths of each. We report the following key results from the review: in reports of new OLMs, almost 60% are based on a single type of data; 30-40% use behavioural metrics, support input from the user, or have complex models; and just 6% involve multiple applications. Key associated themes include intelligent tutoring systems, learning analytics, and selfregulated learning. Notably, compared with LADs, OLM research is more likely to be interactive (81% of papers compared with 31% for LADs), report evaluations (76% versus 59%), use assessment data (100% versus 37%), provide a comparison standard for students (52% versus 38%), but less likely to use behavioural metrics (33% against 75% for LADs). In OLM work, there was a heightened focus on learner control and access to their own data. CCS CONCEPTS • Human-centered computing~Visualization application domains • Human-centered computing~Visualization systems and tools

show abstract

“…These results indicate that most LAD target outcomes refer to monitoring processes such as awareness of learning performance (Park & Jo, 2015), emotional states (Sedrakyan et al, 2017) or general awareness related to learning progress, patterns and strategies (Aljohani et al, 2019; Aljohani & Davis, 2013; Baneres et al, 2019; Bodily, 2018; Park & Jo, 2015; Seanosky et al, 2017; Sedrakyan et al, 2017). Other papers described reflection‐related target outcomes that focused on learners’ consideration of their performance (Broos, Peeters, et al, 2017; Broos, Verbert, et al, 2017; Muldner et al, 2015; Van Horne et al, 2018), behaviour and collaboration (Clayphan et al, 2017; Hill, 2018; Lkhagvasuren et al, 2016; Michel et al, 2012), learning (Cha & Park, 2019; Mejia et al, 2016; Michel et al, 2017) and reflective sense‐making (Vovides & Inman, 2016).…”

Section: Resultsmentioning

confidence: 96%

“…While colour‐coded messages (Baneres et al, 2019; Broos, Verbert, et al, 2017) and traffic light metaphors (Cha & Park, 2019; Raza et al, 2019; Ullmann et al, 2019) represented the most frequent types of designs; other types of visualisation elements such as social network representations (Vovides & Inman, 2016), plant images (Muldner et al, 2015), timeline (Sedrakyan et al, 2017), avatars (Charleer et al, 2016) and speedometer metaphor (Michel et al, 2017) were also used.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Staying on target: A systematic literature review on learner‐facing learning analytics dashboards

Valle

Antonenko

Dawson

et al. 2021

Brit J Educational Tech

View full text Add to dashboard Cite

The advances in technology to capture and process unprecedented amounts of educational data has boosted the interest in Learning Analytics Dashboard (LAD) applications as a way to provide meaningful visual information to administrators, parents, teachers and learners. Despite the frequent argument that LADs are useful to support target users and their goals to monitor and act upon the information provided, little is known about LADs’ theoretical underpinnings and the alignment (or lack thereof) between LADs intended outcomes and the measures used to evaluate their implementation. However, this knowledge is necessary to illuminate more efficient approaches in the development and implementation of LAD tools. Guided by the self‐regulated learning perspective and using the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) framework, this systematic literature review addressed this gap by examining whether and how learner‐facing LAD’s target outcomes align with the domain measures used to evaluate their implementations. Out of the 1297 papers retrieved from 15 databases, 28 were included in the final quantitative and qualitative analysis. Results suggested an intriguing lack of alignment between LADs’ intended outcomes (mostly cognitive domain) and their evaluation (mostly affective measures). Based on these results and on the premise that LADs are designed to support learners, a critical recommendation from this study is that LADs’ target outcomes should guide the selection of measures used to evaluate the efficacy of these tools. This alignment is critical to enable the construction of more robust guidelines to inform future endeavours in the field. What is already known about this topic There has been an increased interest and investment in learning analytics dashboards to support learners as end‐users. Learner‐facing learning analytics dashboards are designed with different purposes, functionalities and types of data in an attempt to influence learners’ behaviour, achievement and skills. What this paper adds This paper reports trends and opportunities regarding the design of learner‐facing learning analytics dashboards, contexts of implementation, as well as types and features of learner‐facing learning analytics dashboard studies. The paper discusses how affect and motivation have been largely overlooked as target outcomes in learner‐facing learning analytics dashboards. Implications for practice and/or policy Based on the evidence gathered through the review, this paper makes recommendations for theory (eg, inclusion of motivation as an important target outcome). The paper makes recommendations related to the design, implementation and evaluation of learning analytics dashboards. The paper also highlights the need for further integration between learner‐facing learning analytics dashboards and open learner models.

show abstract

Evaluating Student-Facing Learning Dashboards of Affective States

Cited by 15 publications

References 38 publications

Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts

Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts

Open learner models and learning analytics dashboards

Staying on target: A systematic literature review on learner‐facing learning analytics dashboards

Contact Info

Product

Resources

About