METS: Multimodal Learning Analytics of Embodied Teamwork Learning

Zhao, Linxuan; Swiecki, Zachari; Gašević, Dragan; Yan, Lixiang; Dix, Samantha; Jaggard, Hollie; Wotherspoon, Rosie; Osborne, Abra; Li, Xinyu; Alfredo, Riordan; Martínez-Maldonado, Roberto

doi:10.1145/3576050.3576076

Cited by 16 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the unique affordances of unifying descriptions and quantitative representation, QE has a rising interest in learning analytics. For example, Epistemic Network Analysis models behaviors captured in learning environments connected via temporal co-occurrence, which supports interpretations of learner strategy differences and their relationship to outcomes [12,15,48]. For example, Fougt et al [15] distinguish student proficiency levels in higher education writing assessment to support grading via keywords.…”

Section: Quantitative Ethnography Methods In Learning Analyticsmentioning

confidence: 96%

Revealing Networks: Understanding Effective Teacher Practices in AI-Supported Classrooms using Transmodal Ordered Network Analysis

Borchers,

Wang,

Karumbaiah

et al. 2024

Proceedings of the 14th Learning Analytics and Knowledge Conference

View full text Add to dashboard Cite

Learning analytics research increasingly studies classroom learning with AI-based systems through rich contextual data from outside these systems, especially student-teacher interactions. One key challenge in leveraging such data is generating meaningful insights into effective teacher practices. Quantitative ethnography bears the potential to close this gap by combining multimodal data streams into networks of co-occurring behavior that drive insight into favorable learning conditions. The present study uses transmodal ordered network analysis to understand effective teacher practices in relationship to traditional metrics of in-system learning in a mathematics classroom working with AI tutors. Incorporating teacher practices captured by position tracking and human observation codes into modeling significantly improved the inference of how efficiently students improved in the AI tutor beyond a model with tutor log data features only. Comparing teacher practices by student learning rates, we find that students with low learning rates exhibited more hint use after monitoring. However, after an extended visit, students with low learning rates showed learning behavior similar to their high learning rate peers, achieving repeated correct attempts in the tutor. Observation notes suggest conceptual and procedural support differences can help explain visit effectiveness. Taken together, offering early conceptual support to students with low learning rates could make classroom practice with AI tutors more effective. This study advances the scientific understanding of effective teacher practice in classrooms learning with AI tutors and methodologies to make such practices visible.

show abstract

Section: Quantitative Ethnography Methods In Learning Analyticsmentioning

confidence: 96%

Revealing Networks: Understanding Effective Teacher Practices in AI-Supported Classrooms using Transmodal Ordered Network Analysis

Borchers,

Wang,

Karumbaiah

et al. 2024

Proceedings of the 14th Learning Analytics and Knowledge Conference

View full text Add to dashboard Cite

show abstract

“…Over the past few years, a growing body of research on SSLA has been published, spanning leading learning analytics Zhao et al, 2023), AI in education (Chng et al, 2020;, educational technology (Yan, Martinez-Maldonado, Zhao, Dix, et al, 2023;Yan, Martinez-Maldonado, Gallo Cordoba, et al, 2022), and human-computer interaction (Saquib et al, 2018;Fernandez-Nieto et al, 2022) venues. Existing research has illustrated the potential of SSLA for investigating different educational constructs (e.g., team collaboration (An et al, 2018) and spatial pedagogy ) in a wide range of learning contexts (e.g., early education (Saquib et al, 2018) and clinical simulations ).…”

Section: Sslamentioning

confidence: 99%

“…Tier 2 can be considered transparent to general learning analytics experts and enthusiasts. For Tier 3, we also included students as one of the important stakeholders because SSLA may directly influence students' reflective practices (Zhao et al, 2023;Yan, Martinez-Maldonado, Zhao, Dix, et al, 2023).…”

Section: Additional Analysis (Rq4)mentioning

confidence: 99%

“…These insights regarding students' social dynamics have been used to generate diagnostic analytics for exploring the relationships among social behaviours and learning constructs (Stehlé et al, 2013;Nguyen et al, 2020) and motivate the development of descriptive (Saquib et al, 2018) and predictive analytics models (Yan, Martinez-Maldonado, Gallo Cordoba, et al, 2022) (further elaborated on in Section 4.3). SSLA was also used to inform on team dynamics (n = 7) in clinical simulations, such as the positioning strategies (Echeverria et al, 2018;Fernandez-Nieto, Martinez-Maldonado, Echeverria, et al, 2021), non-verbal communication (Zhao et al, 2022), verbal communication (Zhao et al, 2023), and task-related actions (Martinez-Maldonado, Echeverria, Fernandez Nieto, et al, 2020;Yan, Martinez-Maldonado, Zhao, Dix, et al, 2023;Li et al, 2023) that a team adopted when taking care of deteriorating patients. These team-related insights have shown practical value in supporting teachers to guide post hoc reflective practices (Yan, Martinez-Maldonado, Zhao, Dix, et al, 2023;Fernandez-Nieto, Martinez-Maldonado, Echeverria, et al, 2021).…”

Section: Educational Constructsmentioning

confidence: 99%

“…In comparison, SSLA focuses specifically on capturing educational insights in non-computer mediated contexts from the socio-spatial perspective, which adopts a unique set of theoretical foundations and methodologies (e.g., spatial pedagogy (Lim et al, 2012) and instructional proxemics (Chin et al, 2017)). With the rapid proliferation of the use of sensing technologies for supporting learning activities, various studies have started to look at the socio-spatial learning aspects but spread around different fields (e.g., among learning analytics Zhao et al, 2023), educational technologies (Yan, Martinez-Maldonado, Zhao, Dix, et al, 2023;Yan, Martinez-Maldonado, Gallo Cordoba, et al, 2022), and human-computer interaction research (Saquib et al, 2018;Fernandez-Nieto et al, 2022)). A systematic literature review would be timely to identify the research trends and gaps in SSLA in order to provide direction to this strand of research.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Socio-spatial Learning Analytics in Co-located Collaborative Learning Spaces:

Yan,

Zhao,

Gašević

et al. 2023

Learning Analytics

View full text Add to dashboard Cite

Socio-spatial learning analytics (SSLA) is an emerging area within learning analytics research that seeks to un-cover valuable educational insights from individuals’ social and spatial data traces. These traces are capturedautomatically through sensing technologies in physical learning spaces, and the research is commonly based onthe theoretical foundations of social constructivism and cultural anthropology. With its growing empirical basis, asystematic literature review is timely in order to provide educational researchers and practitioners with a detailedsummary of the emerging works and the opportunities enabled by SSLA. This paper presents a systematic review of25 peer-reviewed articles on SSLA published between 2011 and 2023. Descriptive, network, and thematic analyseswere conducted to identify the citation networks, essential components, opportunities, and challenges enabled bySSLA. The findings illustrated that SSLA provides the opportunity to (1) contribute unobtrusive and unsupervisedresearch methodologies, (2) support educators’ classroom orchestration through visualizations, (3) support learnerreflection with continuous and reliable evidence, (4) develop novel theories about social and collaborative learning,and (5) empower educational stakeholders with the quantitative data to evaluate different learning spaces. Thesefindings could support learning analytics and educational technology scholars and practitioners to better understandand utilize SSLA to support future educational research and practice.

show abstract