Learning Analytics & Personal Visualization
Personal Learning Visualization (PLV) is using advanced visualization techniques from the fields of Information Visualization and Visual Analytics, in order to facilitate the sense-making process, for an individual’s learning performance. In this theme learners become producers and consumers of the data, and are essentially immersed in a world of ubiquitous information that influences their learning process.
J. C. Roberts, C. Headleand, D. Perkins, and P. D. Ritsos, “Personal Visualisation for Learning,” in Personal Visualization: Exploring Data in Everyday Life Workshop, IEEE Conference on Visualization (VIS), Chicago, IL, USA, 2015.
Learners have personal data, such as grades, feedback and statistics on how they fair or compare with the class. But, data focusing on their personal learning is lacking, as it does not get updated regularly (being updated at the end of a taught session) and the displayed information is generally a single grade. Consequently, it is difficult for students to use this information to adapt their behavior, and help them on their learning journey. Yet, there is a rich set of data that could be captured and help students learn better. What is required is dynamically, regularly updated personal data, that is displayed to students in a timely way. Such ‘personal data’ can be presented to the student through ‘personal visualizations’ that engender ‘personal learning’. In this paper we discuss our journey into developing learning systems and our resulting experience with learners. We present a vision, to integrate new technologies and visualization solutions, in order to encourage and develop personal learning that employs the visualization of personal learning data.
P. D. Ritsos and J. C. Roberts, “Towards more Visual Analytics in Learning Analytics,” in EuroVis Workshop on Visual Analytics (EuroVA), Swansea, UK, 2014, pp. 61–65.
Learning Analytics is the collection, management and analysis of students’ learning. It is used to enable teachers
to understand how their students are progressing and for learners to ascertain how well they are performing.
Often the data is displayed through dashboards. However, there is a huge opportunity to include more comprehensive
and interactive visualizations that provide visual depictions and analysis throughout the lifetime of the
learner, monitoring their progress from novices to experts. We therefore encourage researchers to take a comprehensive
approach and re-think how visual analytics can be applied to the learning environment, and develop more
interactive and exploratory interfaces for the learner and teacher.
J. C. Roberts, J. Jackson, C. Headleand, and P. D. Ritsos, “Creating Explanatory Visualizations of Algorithms for Active Learning,” in Posters presented at the IEEE Conference on Visualization (IEEE VIS 2016), Baltimore, MD, USA, 2016.
Visualizations have been used to explain algorithms to learners, in order to help them understand complex processes. These ‘explanatory visualizations’ can help learners understand computer algorithms and data-structures. But most are created by an educator and merely watched by the learner. In this paper, we explain how we get learners to plan and develop their own explanatory visualizations of algorithms. By actively developing their own visualizations learners gain a deeper insight of the algorithms that they are explaining. These depictions can also help other learners understand the algorithm.