No abstract

Remote meetings have become the norm for most students learning synchronously at a distance during the ongoing coronavirus pandemic. This has motivated the use of artificial intelligence in education (AIED) solutions to support the teaching and learning practice in these settings. However, the use of such solutions requires new research particularly with regards to the human factors that ultimately shape the future design and implementations. In this paper, we build on the emerging literature on human-centred AIED and explore students' experiences after interacting with a tool that monitors their collaboration in remote meetings (i.e., using Zoom) during 10 weeks. Using the social translucence framework, we probed into the feedback provided by twenty students regarding the design and implementation requirements of the system after their exposure to the tool in their course. The results revealed valuable insights in terms of visibility (what should be made visible to students via the system), awareness (how can this information increase students' understanding of collaboration performance), and accountability (to what extent students take responsibility of changing their behaviours based on the system's feedback); as well as the ethical and privacy aspects related to the use of collaboration analytics tools in remote meetings. This study provides key suggestions for the future design and implementations of AIED systems for remote meetings in educational settings.

Self-Regulated Learning (SRL) competence is imperative to academic achievement. For reflective academic writing tasks, which are common for university assessments, this is especially the case since students are often required to plan the task independently to be successful. The purpose of the current study was to examine different reflection behaviours of postgraduate students that were required to reflect on individual tasks over a fifteen-week-long higher education course. Forty students participated in a standardised questionnaire at the beginning of the course to assess their SRL competence and then participated in weekly individual reflection tasks on Google Docs. We examined students' reflective writing behaviours based on time-series and correlation analysis of fine-grained data retrieved from Google Docs. More specifically, reflection behaviours between students with high SRL and low SRL competence were investigated. The results show that students with high SRL competence tend to reflect more frequently and more systematically than students with low SRL competence. Even though no statistically significant difference in academic performance between the two groups was found, there were statistical correlations between academic performance and individual reflective writing behaviours. We conclude the paper with a discussion on the insights into the temporal reflection patterns of different SRL competence student clusters, the impact of these behaviours on students' academic performance, and potential suggestions for appropriate support for students with different levels of SRL.

Self-Regulated Learning (SRL) competence is an important aspect of online learning. SRL is an internal process, but analytics can offer an externalisation trigger to allow for observable effects on learner behaviours. The purpose of this paper is to explore the relationship between students’ SRL competence and their learning engagement behaviours observed in multimodal data. In a postgraduate course with 42 students, eighteen features from three types of data in seven learning activities were extracted to investigate multi-level SRL competence students’ engagement behaviours. The results revealed that students with different SRL competence clusters might exhibit different behaviours in individual, group, and cohort level learning activities. Also, students with similar SRL competence might exhibit significantly different engagement behaviours in different learning activities, depending on the learning design. Therefore, while using engagement data in AIED systems; the modality of the data, specific analysis techniques used to process it, and the contextual particularities of the learning design should all be explicitly presented. So that, they can be considered in the interpretations of automated decisions about student achievement.

Several studies have shown a positive relationship between measures of gaze behaviours and the quality of student group collaboration over the past decade. Gaze behaviours, however, are frequently employed to investigate i) students' online interactions and ii) calculated as cumulative measures of collaboration, rarely providing insights into the actual process of collaborative learning in real-world settings. To address these two limitations, we explored the sequences of students' gaze behaviours as a process and its relationship to collaborative learning in a face-to-face environment. Twenty-five collaborative learning session videos were included from five groups in a 10-week post-graduate module. Four types of gaze behaviours (i.e., gazing at peers, their laptops, tutors, and undefined objects) were used to label student gaze behaviours and the resulting sequences were analyzed using the Optimal Matching (OM) algorithm and Ward's Clustering. Two distinct types of gaze patterns with different levels of shared understanding and collaboration satisfaction were identified, i) peer-interaction focused (PIF), which prioritise social interaction dimensions of collaboration and ii) resource-interaction focused (RIF) which prioritise resource management and task execution. The implications of the findings for automated detection of students' gaze behaviours with computer vision and adaptive support are discussed.