Quantifying Collaboration Quality in Face-to-Face Classroom Settings Using MMLA

Chejara, Pankaj; Prieto, Luis P.; Ruiz‐Calleja, Adolfo; Rodríguez‐Triana, María Jesús; Shankar, S.; Kasepalu, Reet

doi:10.1007/978-3-030-58157-2_11

Cited by 12 publications

(6 citation statements)

References 14 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We identified nineteen papers that provided machine learning evidence on the outcome of an MMLA system. The papers cover a wide range of areas including predicting learning retention (Hwang et al, 2011); expertise and academic performance (Chango et al, 2019;Giannakos et al, 2019;Luz, 2013); performance in problem-solving in coding (Mangaroska et al, 2020); in Maths (Ochoa et al, 2013); in collaborative activities (Chejara et al, 2020;; in openended project-based activities (Spikol et al, 2018;; in face-to-face collaborative problem-solving activities (Cukurova, Zhou, et al, 2020) and to predict students' dialogue acts (Ezen-Can et al, 2015) and oral presentation skills (Munoz et al, 2018). More from the teachers perspective, ML was used to process multimodal data to identify teachers' key instructional segments to assess their instruction (Donnelly et al, 2016) and to extract orchestration graphs including teaching activities and their social plane over time (Prieto et al, 2018).…”

Section: Existing Evidence On the Use Of Mmla To Support Educational Outcomesmentioning

confidence: 99%

The evidence of impact and ethical considerations of Multimodal Learning Analytics: A Systematic Literature Review

Alwahaby¹,

Cukurova²,

Papamitsiou³

et al. 2021

Preprint

View full text Add to dashboard Cite

There is a growing interest in the research and use of multimodal data in learning analytics. This paper presents a systematic literature review of multimodal learning analytics (MMLA) research to assess i) the available evidence of impact on learning outcomes in real-world contexts and ii) explore the extent to which ethical considerations are addressed. A few recent literature reviews argue for the promising value of multimodal data in learning analytics research. However, our understanding of the challenges associated with MMLA research from real-world teaching and learning environments is limited. To address this gap, this paper provides an overview of the evidence of impact and ethical considerations stemming from an analysis of the relevant MMLA research published in the last decade. The search of the literature resulted in 663 papers, of which 100 were included in the final synthesis. The results show that the evidence of real-world impact on learning outcomes is weak, and ethical aspects of MMLA work are rarely addressed. We discuss our results through the lenses of two theoretical frameworks for evidence of impact types and ethical dimensions of MMLA. We conclude that for MMLA to stay relevant and become part of mainstream education, future research should directly address the gaps identified in this review.

show abstract

Section: Existing Evidence On the Use Of Mmla To Support Educational Outcomesmentioning

confidence: 99%

The evidence of impact and ethical considerations of Multimodal Learning Analytics: A Systematic Literature Review

Alwahaby¹,

Cukurova²,

Papamitsiou³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…From Etherpad logs, we extracted the number of characters added or deleted by each student in the group. In our prior work, we found that our prototype's simple features (e.g., speaking time, number of characters) were significant in estimating collaboration quality (further details, see Chejara et al, 2020). Figure 3 illustrates a part of CoTrack's dashboard showing speaking time and social network, which we presented to teachers to investigate their decision-making process during CL.…”

Section: Cotrack Dashboardmentioning

confidence: 99%

Do Teachers Find Dashboards Trustworthy, Actionable and Useful? A Vignette Study Using a Logs and Audio Dashboard

et al. 2021

Self Cite

View full text Add to dashboard Cite

Monitoring and guiding multiple groups of students in face-to-face collaborative work is a demanding task which could possibly be alleviated with the use of a technological assistant in the form of learning analytics. However, it is still unclear whether teachers would indeed trust, understand, and use such analytics in their classroom practice and how they would interact with such an assistant. The present research aimed to find out what the perception of in-service secondary school teachers is when provided with a dashboard based on audio and digital trace data when monitoring a collaborative learning activity. In a vignette study, we presented twenty-one in-service teachers with videos from an authentic collaborative activity, together with visualizations of simple collaboration analytics of those activities. The teachers perceived the dashboards as providers of useful information for their everyday work. In addition to assisting in monitoring collaboration, the involved teachers imagined using it for picking out students in need, getting information about the individual contribution of each collaborator, or even as a basis for assessment. Our results highlight the need for guiding dashboards as only providing new information to teachers did not compel them to intervene and additionally, a guiding dashboard could possibly help less experienced teachers with data-informed assessment.

show abstract

“…Aunque son múltiples las complicaciones que surgen (e.g., en relación a la recogida, integración, análisis y visualización de datos multimodales), muchos son ya los investigadores trabajando en esta problemática (conocida en inglés como Multimodal Learning Analytics) (Vieira, Parsons & Byrd, 2018;Samuelsen, Chen & Wasson, 2019;Crescenzi-Lanna, 2020;Du et al, 2021). Entre las propuestas existentes podemos encontrar sistemas que proporcionan retroalimentación al alumno sobre sus habilidades de presentación en público que toman como fuente la voz, la posición y el movimiento (Ochoa et al, 2020); herramientas para la regulación de la colaboración basadas en la conversación y el texto co-creado por los alumnos (Chejara et al, 2020); herramientas para evaluar el rendimiento cognitivo utilizando aspectos fisiológicos y faciales (Sharma et al, 2020); y aplicaciones que utilizan sensores de movimiento y posición para dar soporte al aprendizaje en el trabajo, como puede ser el caso de la medicina y la enfermería (Di Mitri et al, 2019;Echeverría et al, 2018). Sin embargo, las soluciones disponibles no son aún asequibles (Crescenzi-Lanna, 2020), no han sido suficientemente evaluadas (Ifenthaler & Yau, 2020) o no son operativas para su uso en la práctica diaria (Vieira, Parsons & Byrd, 2018;Romero & Ventura, 2020;Pargman & McGrath, 2021).…”

Section: Analíticas De Aprendizaje Para Informar La Toma De Decisione...unclassified

Construir el conocimiento en la era digital: retos y reflexiones

Marimon-Martí¹,

Cabero‐Almenara²,

Quintero³

et al. 2022

Red

Self Cite

View full text Add to dashboard Cite

This work is the revised version of a report on the new knowledge construction and creation models prepared by the authors within the framework of the International Forum on Education and Technology held in 2021 (FIET 2021). Based on the conclusions on this same theme from the first edition of the Forum held in 2014, the report identifies five major areas of development around which some of the most important challenges faced by emerging models of construction and creation of knowledge in digital contexts: the democratization of education and the taking into consideration of issues related to diversity in a broad sense; the impact of the COVID-19 pandemic and its implications regarding the uses of ICT in education; the existence of multiple and diverse contexts for the construction and creation of knowledge, their interrelation and their necessary articulation; content curation, its impact on educational practices and its implications for teacher training and for student learning; and learning analytics and their role in decision-making aimed at improving teaching effectiveness and optimizing learning. These five areas are reviewed successively, identifying, in each of them, the issues that, in the opinion of the authors, are most significant and relevant and, consequently, should be the object of special attention in research and educational innovation in the coming years. years. By way of conclusion, the progress made between 2014 and 2021 is synthesized, the pending challenges are identified and some of the most salient features are pointed out that, in light of the analyzes presented in the report, should characterize the emerging models of construction and knowledge creation. The work also includes two annexes dedicated, respectively, to presenting a glossary of some terms used in the report and five relevant and significant research products from the five mentioned development areas. Este trabajo identifica cinco grandes ámbitos de desarrollo en torno a los cuales se articulan algunos de los retos más importantes que enfrentan los modelos emergentes de construcción y creación de conocimiento en contextos digitales: la democratización de la educación y la toma en consideración de las cuestiones relacionadas con la diversidad en un sentido amplio; el impacto de la pandemia de la COVID-19 y sus implicaciones en lo que concierne a los usos de las TIC en la educación; la existencia de múltiples y diversos contextos de construcción y creación de conocimiento, su interrelación y su necesaria articulación; la curación de contenidos, su impacto en las prácticas educativas y sus implicaciones para la formación del profesorado y para el aprendizaje del alumnado; y las analíticas de aprendizaje y su papel en la toma de decisiones orientadas a mejorar la eficacia de la enseñanza y optimizar el aprendizaje. Estos cinco ámbitos son revisados sucesivamente identificando, en cada uno de ellos, las cuestiones que, a juicio de los autores, son más significativas y relevantes y, en consecuencia, deberían ser objeto de especial atención en la investigación y la innovación educativa en los próximos años. A modo de conclusión, se identifican los retos pendientes y se señalan algunos de los rasgos más destacados que, a la luz de los análisis presentados en el informe, deberían caracterizar los modelos emergentes de construcción y creación de conocimiento. El trabajo incluye, además, dos anexos dedicados, respectivamente, a presentar un glosario de algunos términos utilizados en el informe y cinco productos de investigación relevantes y significativos de los cinco ámbitos de desarrollo mencionados.

show abstract

Quantifying Collaboration Quality in Face-to-Face Classroom Settings Using MMLA

Cited by 12 publications

References 14 publications

The evidence of impact and ethical considerations of Multimodal Learning Analytics: A Systematic Literature Review

The evidence of impact and ethical considerations of Multimodal Learning Analytics: A Systematic Literature Review

Do Teachers Find Dashboards Trustworthy, Actionable and Useful? A Vignette Study Using a Logs and Audio Dashboard

Construir el conocimiento en la era digital: retos y reflexiones

Contact Info

Product

Resources

About