International Journal of Computer-Supported Collaborative Learning

The use of computational scaffolding is a crucial strategy to foster students’ regulation of learning skills, which is associated with increased learning achievement. However, most interventions treat the regulatory processes as individual actions isolated from a social context. This view contradicts the most recent research that points to the importance of studying the regulatory phenomenon from a social-cognitive perspective, where students’ interactions influence their regulation of the learning process. This work explores these problems and presents multiple scaffolds to promote Self-regulation of Learning (SRL), co-regulation, and socially shared regulation of learning (SSRL) embedded within a computer-supported collaborative learning environment. A single-blind randomized controlled trial was performed with students (n = 71) enrolled in an online introductory programming course. Students were randomly assigned to three groups: 1) SRL-only support, 2) SRL, co-regulation, and SSRL support, and 3) a no support control group. The findings revealed that students who received regulatory support achieved higher course grades than the control group. However, only students who received SSRL and co-regulation support achieved superior performance in collaborative activities, confirming the importance of this type of regulation. Even though students did not increase in SRL aptitude, the intervention provided support for achieving higher grades in the course.

Collaborative problem solving (CPS) enables student groups to complete learning tasks, construct knowledge, and solve problems. Previous research has argued the importance of examining the complexity of CPS, including its multimodality, dynamics, and synergy from the complex adaptive systems perspective. However, there is limited empirical research examining the adaptive and temporal characteristics of CPS, which may have led to an oversimplified representation of the real complexity of the CPS process. To expand our understanding of the nature of CPS in online interaction settings, the present research collected multimodal process and performance data (i.e., speech, computer screen recordings, concept map data) and proposed a three-layered analytical framework that integrated AI algorithms with learning analytics to analyze the regularity of groups’ collaboration patterns. The results surfaced three types of collaborative patterns in groups, namely the behaviour-oriented collaborative pattern (Type 1) associated with medium-level performance, the communication-behaviour-synergistic collaborative pattern (Type 2) associated with high-level performance, and the communication-oriented collaborative pattern (Type 3) associated with low-level performance. This research further highlighted the multimodal, dynamic, and synergistic characteristics of groups’ collaborative patterns to explain the emergence of an adaptive, self-organizing system during the CPS process. According to the empirical research results, theoretical, pedagogical, and analytical implications were discussed to guide the future research and practice of CPS.

Early research on online PBL explored student satisfaction, effectiveness, and design. The temporal aspect of online PBL has rarely been addressed. Thus, a gap exists in our knowledge regarding how online PBL unfolds: when and for how long a group engages in collaborative discussions. Similarly, little is known about whether and what sequence of interactions could predict higher achievement. This study aims to bridge such a gap by implementing the latest advances in temporal learning analytics to analyze the sequential and temporal aspects of online PBL across a large sample (n = 204 students) of qualitatively coded interactions (8,009 interactions). We analyzed interactions at the group level to understand the group dynamics across whole problem discussions, and at the student level to understand the students’ contribution dynamics across different episodes. We followed such analyses by examining the association of interaction types and the sequences thereof with students’ performance using multilevel linear regression models. The analysis of the interactions reflected that the scripted PBL process is followed a logical sequence, yet often lacked enough depth. When cognitive interactions (e.g., arguments, questions, and evaluations) occurred, they kindled high cognitive interactions, when low cognitive and social interactions dominated, they kindled low cognitive interactions. The order and sequence of interactions were more predictive of performance, and with a higher explanatory power as compared to frequencies. Starting or initiating interactions (even with low cognitive content) showed the highest association with performance, pointing to the importance of initiative and sequencing.

In this article we discuss some of the ethical dimensions of design-based research, which we believe should feature more prominently in CSCL scholarship. We begin by sketching out why it is important for CSCL researchers to articulate their visions of the good and how this can be accomplished in a systematic way. We then outline how ethical discourses can take shape at the various stages of design-based research and how the ethical and empirical dimensions of DBR can inspire and shape one another. These considerations can help CSCL researchers move closer to consider how sociopolitical issues feature in their work, as has been increasingly called on by scholars.

Learning engagement has gained increasing attention in the field of education. Previous studies have adopted conventional methods to analyze learning engagement, but these methods cannot provide timely feedback for learners. This study analyzed automated group learning engagement via deep neural network models in a computer-supported collaborative learning (CSCL) context. A quasi-experimental research design was implemented to examine the effects of the automated group learning engagement analysis and feedback approach on collaborative knowledge building, group performance, socially shared regulation, and cognitive load. In total, 120 college students participated in this study; they were assigned to 20 experimental groups and 20 control groups of three students each. The students in the experimental groups adopted the automated group learning engagement analysis and feedback approach, whereas those in the control groups used the traditional online collaborative learning approach. Both quantitative and qualitative data were collected and analyzed in depth. The results indicated significant differences in group learning engagement, group performance, collaborative knowledge building, and socially shared regulation between the experimental and control groups. The proposed approach did not increase the cognitive load for the experimental groups. The implications of the findings can potentially contribute to improving group learning engagement and group performance in CSCL.