Many are the ways to learn identifying multi-modal behavioral profiles of collaborative learning in constructivist activities

Abstract

Understanding the way learners engage with learning technologies, and its relation with their learning, is crucial for motivating design of effective learning interventions. Assessing the learners’ state of engagement, however, is non-trivial. Research suggests that performance is not always a good indicator of learning, especially with open-ended constructivist activities. In this paper, we describe a combined multi-modal learning analytics and interaction analysis method that uses video, audio and log data to identify multi-modal collaborative learning behavioral profiles of 32 dyads as they work on an open-ended task around interactive tabletops with a robot mediator. These profiles, which we name Expressive Explorers, Calm Tinkerers, and Silent Wanderers, confirm previous collaborative learning findings. In particular, the amount of speech interaction and the overlap of speech between a pair of learners are behavior patterns that strongly distinguish between learning and non-learning pairs. Delving deeper, findings suggest that overlapping speech between learners can indicate engagement that is conducive to learning. When we more broadly consider learner affect and actions during the task, we are better able to characterize the range of behavioral profiles exhibited among those who learn. Specifically, we discover two behavioral dimensions along which those who learn vary, namely, problem solving strategy (actions) and emotional expressivity (affect). This finding suggests a relation between problem solving strategy and emotional behavior; one strategy leads to more frustration compared to another. These findings have implications for the design of real-time learning interventions that support productive collaborative learning in open-ended tasks.

Designing a MOOC on Computational Thinking, Programming and Robotics for Early Childhood Educators and Primary School Teachers: A Pilot Test Evaluation

“…These changes are now being considered by the team, which intends to maintain the focus on continuous self-regulation, which will be joined by peer regulation resulting from sharing within the group in the collective space to be created. We believe that this can also expand and stimulate learning of a collaborative nature that can be advantageous for different profiles of participants [34].…”

Being in-sync: A multimodal framework on the emotional and cognitive synchronization of collaborative learners

“…Building on this, socioemotional aspects of collaborative learning are intricate, and there is a need for further investigating its inner workings, i.e., the emotional "in-sync" patterns in peer interactions with the help of multimodal data. As suggested by Nasir et al (2022), multimodal data can precisely detect learners' productive learning behavior from non-productive behaviors with its rich information. However, the processes of collecting, analyzing, and interpreting multimodal data are challenging.…”

“…Moreover, it is feasible to evaluate knowledge convergence within a group of learners, i.e., whether two or more learners have learned equivalent amounts of knowledge by analyzing the coefficient of variation on the group level or share knowledge on the same concepts, which could be regarded as two different measures of being cognitively "insync" (Weinberger et al, 2007). Nonetheless, the validity of pre-and post-tests and the notion of knowledge as cognitive residue have been heavily discussed, resulting in fewer studies evaluating learning only through the pre-and post-tests method (Nasir et al, 2022). The issues that come along with pre-and post-test measurement are, for instance, having test items of similar difficulty and discriminatory power in both tests.…”

Gordon Pask’s second-order cybernetics and Lev Vygotsky’s cultural historical theory: Understanding the role of the internet in developing human thinking

“…While Knowledge Forum may spur collaboration, it does not provide autonomous responses like CASTE and THOUGHTSTICKER did, and their functionalities stand apart from machine feedback loops of internet tools. While robot tools supporting collaboration by regulating the variety of interactions have also been created (Nasir et al, 2022), they provide finite feedback that may not simulate the ubiquitous influence that personal devices have on our activity and thinking.…”

“…We then describe how algorithms in Pask’s digital courseware, like course assembly and tutorial environment (CASTE) and THOUGHTSTICKER, which employed a mixture of hypertext and intelligent teaching models to provide feedback that was qualitatively relevant to learners, have been generalized and supplemented by corporate interests on the internet. Only a few intelligent tools (teaching systems, robot support) exhibiting functionalities close to Paskian devices exist in the corpus of technology-assisted learning, but may not resemble the ubiquitous effects of the internet (Nasir et al, 2022; Wilson & Scott, 2017). While specialized educational technologies using hypertext have become popularized, these may not autonomously respond to learners (Scardamalia, 2004), standing apart from the internet.…”