Multimodal Learning Analytics research with young children: A systematic review

Abstract

Learning Analytics and Multimodal Learning Analytics are changing the way of analysing the learning process while students interact with an educational content. This paper presents a systematic literature review aimed at describing practices in recent Multimodal Learning Analytics and Learning Analytics research literature in order to identify tools and strategies useful for the assessment of the progress and behaviour of children under 6 years old in respect of their learning. The purpose is to provide guidance for Multimodal Learning Analytics research with children under 6 years old to assess their engagement in a task, their emotions, attention, understanding and achievement of a goal. The current state of knowledge on Multimodal Learning Analytics research suggests how performance analytics, face and speech recognition systems, eye tracking, Kinect analytics and wristbands could be used with children. The results show the complexity of collecting data using non‐invasive methodologies with children under 6 years old. Ethical implications related to multimodal data from audio, visual, biometric and quantitative measures of child behaviour are discussed.

The promise and challenges of multimodal learning analytics

“…In the same vein, Crescenzi‐Lanna (2020) conducted a systematic literature review on MMLA studies with children under six years and analysed the selected contributions based on the degree of performance analytics (students’ understanding and engagement), use of machine learning, use of eye‐tracking, Kinect, biometrics, human‐coded quantitative and qualitative data. The results indicated that, despite its complexity and the various ethical and practical challenges they may lead to (eg, ethical considerations for the participation of children, parental involvement, potential surveillance issues), multimodal data have valuable contributions on the performance of analytics and face and speech recognition systems in the context of supporting young children’s’ learning.…”

“…The results indicated that, despite its complexity and the various ethical and practical challenges they may lead to (eg, ethical considerations for the participation of children, parental involvement, potential surveillance issues), multimodal data have valuable contributions on the performance of analytics and face and speech recognition systems in the context of supporting young children’s’ learning. Crescenzi‐Lanna (2020) also provides a commentary on some of these issues (eg, children interacting with a “wizard‐of‐oz,” obtrusive exposure to studies).…”

Challenges and opportunities of multimodal data in human learning: The computer science students' perspective

“…Most of current MLA systems and studies are aimed at supporting researchers to model learner behaviours (see reviews by Crescenzi‐Lanna, 2020; Di Mitri et al, 2018; Noroozi et al, 2019) or offer technical infrastructures to interconnect sensors and systems (Huertas Celdrán et al, 2020; Shankar et al, 2020, 2018). On the one hand, some researchers attribute this dearth of actual MLA interfaces for learners to the intrinsic complexity of multimodal data (Martinez‐Maldonado, Echeverria, et al, 2020; Worsley et al, 2016).…”

A Learning Analytics Conceptual Framework for Augmented Reality-Supported Educational Case Studies

“…The recent advancements in the field of computing have enabled educators and practitioners to increase the effectiveness of instructional design and allowed them to collect and analyze large-scale digital datasets. One proposed solution to investigate and explore such topics involves the collection and interpretation of so-called 'big data', which are processed with the aid of machine learning (ML) models and educational data mining (EDM) techniques [6][7][8]. The so-called learning analytics (LA) discipline is an emerging field, with rapid growth over the last five years, which aims at assisting researchers and instructors to better understand learners' needs by collecting and interpreting large-scale data in a systematic and independent way.…”