Students' learning is ubiquitous. It happens wherever the learner is rather than being constrained to a specific physical or digital learning space (e.g. the classroom or the institutional LMS respectively). A critical question is: how to integrate and coordinate learning analytics to provide continued support to learning across physical and digital spaces? CrossMMLA is the successor to the Learning Analytics Across Spaces (CrossLAK) and MultiModal Learning Analytics (MMLA) series of workshops that were merged in 2017 after successful cross-pollination between the two communities. Although it may be said that
CrossLAK and MMLA perspectives follow different philosophical and practical approaches, they both share a common aim. This aim is: deploying learning analytics innovations that can be used across diverse authentic learning environments whilst learners feature various modalities of interaction or behaviour. 1 1.1
Educational research has revealed the pedagogical benefits of letting students experience different
types of content, "real world" challenges, and physical and social interactions with educators or
other learners
By contrast, we can say that MMLA favours a bottom-up approach where the focus is on the
analytics grounded by learning theory and practice. MMLA can provide insights into learning
processes that happen across multiple contexts between people, devices and resources (both
physical and digital), which often are hard to model and orchestrate
Although CrossLAK and MMLA have some elements that distinguish them from each other, they
both share the common aim of deploying learning analytics innovations that can be used across
diverse authentic learning environments whilst learners feature various modalities of interaction or
behaviour. LA researchers can now perform text, speech, handwriting, sketch, gesture, affective,
neurophysical, or eye gaze analyses
Our aim as a joint CrossMMLA community is to make learning analytics relevant across, physical, digital, and blended learning environments while making the tools more accessible to the wider community. Therefore, researchers and practitioners need to address the larger frame of what is happening across the digital and physical space and between individuals, groups, and the entire class while balancing the data, collection, analysis and visualisation. 2
One of the key aims of the workshop is to attract researchers (from diverse communities) to consider how multimodal learning analytics can be used across diverse learning environments. The intention is to gather interested parties in ubiquitous, mobile and/or face-to-face learning analytics with a focus on multimodal interaction. For this call for contributions, six papers were accepted, tackling present and future challenges, and considerations for the community, from conceptual to technical approaches.
Three activities have been planned for this full-day workshop: the first activity will be a panel discussion focused on intermediate constructs/indicators in CrossMMLA (a recurring topic that emerged in the last workshops). The second activity will be a hands-on ideation task focused on identifying critical systems, tools, standards in MMLA (e.g., towards a unified CrossMMLA stack). Finally, the third activity will be a practical/hands-on MMLA training using multimodal sensors (e.g. multimodal selfies, beacons, etc.) and tools to then explore/analyse the data. Authors’ papers will be presented as posters, with a poster madness session at the beginning of the day with some discussion around the posters during the breaks.