METS: Multimodal Learning Analytics of Embodied Teamwork Learning Linxuan Zhao Monash University Australia Zachari Swiecki Monash University Australia Dragan Gašević Monash University Australia Lixiang Yan Monash University Australia Samantha Dix Monash University Australia Hollie Jaggard Monash University Australia Rosie Wotherspoon Monash University Australia Abra Osborne Monash University Australia Xinyu Li Monash University Australia Riordan Alfredo Monash University Australia Roberto Martinez-Maldonado Monash University Australia Figure 1: Embodied teamwork in an immersive healthcare simulation where a team of students constantly reconfgure themselves into sub-groups (e.g., see simultaneous, coded dialogue unfolding at the left and right of the learning space) to complete a joint task. Abstract Embodied team learning is a form of group learning that occurs in co-located settings where students need to interact with oth- ers while actively using resources in the physical learning space to achieve a common goal. In such situations, communication dy- namics can be complex as team discourse segments can happen in parallel at diferent locations of the physical space with varied team member confgurations. This can make it hard for teachers to assess the efectiveness of teamwork and for students to refect on their own experiences. To address this problem, we propose METS (Multimodal Embodied Teamwork Signature), a method to model team dialogue content in combination with spatial and temporal data to generate a signature of embodied teamwork. We present Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. LAK 2023, March 13ś17, 2023, Arlington, TX, USA © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. ACM ISBN 978-1-4503-9865-7/23/03. . . $15.00 https://doi.org/10.1145/3576050.3576076 a study in the context of a highly dynamic healthcare team sim- ulation space where students can freely move. We illustrate how signatures of embodied teamwork can help to identify key difer- ences between high and low performing teams: i) across the whole learning session; ii) at diferent phases of learning sessions; and iii) at particular spaces of interest in the learning space. CCS Concepts · Applied computing → Collaborative learning; Computer- assisted instruction. Keywords Healthcare simulation, Collaborative learning, Communication, Teamwork, Multimodality ACM Reference Format: Linxuan Zhao, Zachari Swiecki, Dragan Gašević, Lixiang Yan, Samantha Dix, Hollie Jaggard, Rosie Wotherspoon, Abra Osborne, Xinyu Li, Rior- dan Alfredo, and Roberto Martinez-Maldonado. 2023. METS: Multimodal Learning Analytics of Embodied Teamwork Learning. In LAK23: 13th Inter- national Learning Analytics and Knowledge Conference (LAK 2023), March 13ś17, 2023, Arlington, TX, USA. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3576050.3576076 186