We could have called it the “Learning Analytics Research Week” at DTIC. It was my pleasure to host several activities around learning analytics research last week.
Dr. Roberto Martínez-Maldonado from the Connected Intelligence Centre (CIC) at the University of Technology, Sydney (UTS) has been the first visiting academic with an Erasmus+ International Mobility Grant (Erasmus+ KA107) at UPF. Within the activities of his visit, he instructed seminars devoted to PhD students. They included a hands-on workshop on multidimensional activity data visualization. The workshop engaged participants in crafting participatory data stories through the development of rapid low fidelity prototypes of collaborative work data. The workshop briefly introduced a series of concepts (such as multimodal data visualisation, learning analytics, HCI interaction data capture and visual metaphors). Then, the workshop focused on analysing a multi-user, multi-modal dataset that imposes particular challenges for visualisation design. The purpose for the attendees was to generate out-of-the-box ideas for visualising this particular Learning Analytics dataset, aimed at telling a story about collaborative group processes.
Roberto Martínez-Maldonado also gave a DTIC Research Seminar titled “Multi-modal sequence mining and analytics of face-to-face collaborative learning”, where he introduced his work aimed at analysing aspects of students’ activity when learning collaboratively using digital ecologies enriched with sensors for identifying users, and also at multi-display settings. This strand of research is seeking out to automatically distinguish, discover and distil salient common patterns of interaction within groups, by mining the logs of students’ actions, detected speech, changes in group’s artefacts, etc. The talk showcased a number of group situations where multiple people are engaged in creative tasks that require design thinking and sense making. Multiple data mining techniques have been used in these scenarios to generate understanding of collaborative group processes including: classification, sequence pattern mining, process mining and clustering techniques.
Dr. Abelardo Pardo, Senior Lecturer at the School of Electrical and Information Engineering, The University of Sydney, also visited the DTIC last week. He gave a DTIC Research Seminar with the title “Feedback at scale with a little help from my algorithms”. In his talk, Abelardo Pardo explained that despite the importance of formative feedback to improve educational experiences, providing adequate feedback in the right form, at the right time, at the right level is still challenging and risky. Academics in higher education institutions are increasingly under pressure to solve the tension between larger student cohorts in active learning scenarios and the quality of feedback given to students. The increasing amount of tasks that are mediated by technology offers the possibility to obtain a detailed digital footprint of the students. The talk explored some ideas about how to combine educational technology, data collection and prediction algorithms with current tasks carried out by instructors to amplify their effect in active learning scenarios.
These activities are connected with the strategic research program on Data Science associated to the “Maria de Maetzu” distinction awarded to the DTIC. Learning Analytics research partly funded by this program was also presented at the 6th International Learning Analytics & Knowledge Conference (LAK’16) recently held in Edinburgh.