Details

Autor(en) / Beteiligte

• Spikol, Daniel
• Ruffaldi, Emanuele
• Dabisias, Giacomo
• Cukurova, Mutlu

Titel

Supervised machine learning in multimodal learning analytics for estimating success in project‐based learning

Ist Teil von

• Journal of computer assisted learning, 2018-08, Vol.34 (4), p.366-377

Ort / Verlag

Oxford: Wiley-Blackwell

Erscheinungsjahr

2018

Link zum Volltext

Quelle

Wiley Online Library - AutoHoldings Journals

Beschreibungen/Notizen

• Multimodal learning analytics provides researchers new tools and techniques to capture different types of data from complex learning activities in dynamic learning environments. This paper investigates the use of diverse sensors, including computer vision, user‐generated content, and data from the learning objects (physical computing components), to record high‐fidelity synchronised multimodal recordings of small groups of learners interacting. We processed and extracted different aspects of the students' interactions to answer the following question: Which features of student group work are good predictors of team success in open‐ended tasks with physical computing? To answer this question, we have explored different supervised machine learning approaches (traditional and deep learning techniques) to analyse the data coming from multiple sources. The results illustrate that state‐of‐the‐art computational techniques can be used to generate insights into the "black box" of learning in students' project‐based activities. The features identified from the analysis show that distance between learners' hands and faces is a strong predictor of students' artefact quality, which can indicate the value of student collaboration. Our research shows that new and promising approaches such as neural networks, and more traditional regression approaches can both be used to classify multimodal learning analytics data, and both have advantages and disadvantages depending on the research questions and contexts being investigated. The work presented here is a significant contribution towards developing techniques to automatically identify the key aspects of students success in project‐based learning environments, and to ultimately help teachers provide appropriate and timely support to students in these fundamental aspects. Lay Description What is currently known about Multimodal learning analytics? Multimodal learning analytics (MMLA) provides new tools and techniques to capture different types of data from complex learning activities in dynamic educational environments where learners interact in groups and with materials. What does the paper add to the subject matter? MMMLA supports how teachers and learners can gain insights and support through the analysis of data (via computer machine learning) about small group work. These insights help educators design better learning situations, and students reflect on group work. The paper adds to the subject matter by comparing different techniques to analyse data. The implications of the study findings for practitioners? MMLA and the state‐of‐the‐art computational techniques can be used to generate insights into the "black box" of learning in students' project‐based activities. These insights generated from multimodal data can be used to inform teachers about the key features of project‐based learning and help them support students appropriately in similar pedagogical approaches. The study provides evidence that MMLA techniques and different types of can be the first step towards effective implementation and evaluation of project‐based learning at scale.