Collaborative Learning Outcomes Research Articles

A Machine Learning Approach to Optimal Group Formation Based on Previous Academic Performance

In today’s educational institutions, student performance can vary widely due to differences in cognition, motivation, and environmental factors. These variations create challenges in achieving optimal learning outcomes. To address these challenges, Optimal Group Formation (OGF) has emerged as a promising research area. Optimal Group Formation (OGF) aims to form student groups that maximize learning efficiency based on past academic performance. Group formation problems are inherently complex and time-consuming, but their applications are extensive, spanning from manufacturing systems to educational contexts. This paper introduces a machine learning-based model designed to create optimal student groups using academic records as the primary input. The goal is to enhance overall group performance and reduce error rates by organizing students into cohesive, efficient teams. What sets this research apart is its focus on educational group formation, leveraging machine learning to improve collaborative learning outcomes. The paper also reviews prior research, emphasizing the importance of Optimal Group Formation (OGF) in various fields and its relevance in education. The model’s effectiveness is demonstrated through comparative analysis, showcasing its potential to improve group dynamics in both theoretical and lab-based courses. Ultimately, the aim is to improve educational outcomes by ensuring that student groups are optimally balanced and structured.

The role of individual preparation before collaboration: An exploratory study on students’ computer-supported collaborative argumentation in a primary classroom

ABSTRACT Background Collaborative learning is widely applied in real-world classrooms while young learners still have challenges engaging in high-quality knowledge co-construction processes. Researchers suggested an individual preparation activity before collaboration. However, there remains a limited understanding of the role of individual preparation on students’ collaborative learning. Method Conducted in a fifth-grade English language class in a Singapore primary school, this study explored students’ collaborative learning outcome and process under two conditions: individual preparation before collaboration (With-IP) and immediate collaboration (Without-IP) conditions. Student groups’ collaborative argumentation artifacts were collected and coded. Process analysis was conducted to reveal the distribution and transitional pattern of students’ verbal discussions and online collaboration behaviors. Findings This study reveals that individual preparation (With-IP) significantly enhanced the quality of collaborative argumentation compared to no preparation (Without-IP), by fostering more idea elaboration, deeper engagement with content knowledge, and higher quality of arguments. However, the students were also found to make more coordination and regulation efforts in the With-IP condition than Without-IP condition. Contribution This research underscores the role of individual preparation on collaborative learning processes and outcomes. This insight is pivotal for educators and practitioners in tailoring collaboration scripts to the objectives of classroom teaching and learning.

Empowering Collaborative Learning: Innovative Integration of Real-Time Communication Into Hololens-Based Learning System

This study primarily aims to investigate the effectiveness of the HoloLens-based learning system, RTCHoloLS, in enhancing collaborative learning skills in undergraduate photography courses. It provides empirical evidence showing how RTC-HoloLS addresses pedagogical challenges and improves collaborative learning outcomes, offering a holistic approach to photography education. Although Augmented Reality (AR) technology helps students theoretically understand camera operations in photography courses, it lacks in promoting collaborative learning skills during hands-on practice. To address this limitation, this study introduces the RTC-HoloLS, a HoloLens-based learning system with Real-Time Communication, and compares it to the conventional video streaming-based HoloLS (CVSHoloLS). The results indicate that RTC-HoloLS significantly enhances collaborative learning skills compared to CVS-HoloLS, highlighting the importance of integrating Real-Time Communication technologies in AR learning environments. Additionally, RTC-HoloLS was equally effective for both male and female students, whereas CVS-HoloLS showed greater benefits for male students. This suggests the need to consider gender differences in design and development to ensure the learning system accommodates all students. The findings have significant implications for instructional technology design and implementation, suggesting that educational institutions should prioritize real-time communication features in AR learning tools to enhance collaboration and interaction.

Innovation Learning Geography with ArcGIS Online: The Impact to Skills Collaborative and Achievement Student School Upper Intermediate

Purpose of the study: The aim of this research is to examine the influence of ArcGIS Online learning media on collaborative skills and student learning outcomes at State Senior High School 1 Mojo, Kediri Regency. Methodology: The research used a quasi-experimental method with a Post-test Only Control Design. The tool used is ArcGIS Online from ESRI. The research population was class 10 students at Mojo 1 High School, Kediri, academic year 2023/2024, with samples selected randomly for the experimental and control classes. Data was collected through observation of collaborative skills and post-test for learning outcomes. Observations were carried out with the help of three observers using a collaborative skills observation instrument based on a Likert scale. Data analysis was carried out using SPSS, including the ANOVA test for homogeneity, the Kolmogorov-Smirnov test for normality, and the T test to test significant differences between the experimental and control classes. Main Findings: The use of ArcGIS Online as a learning medium shows a significant increase in collaborative skills and student learning achievement compared to conventional learning media. Post-test and observation results show higher scores in the experimental class. Novelty/Originality of this study: This research introduces the use of ArcGIS Online as a geography learning medium, which has not been widely implemented in high schools. This study shows that the use of this technology can significantly improve students' collaborative skills and learning outcomes.

Enhancing Collaborative Learning in Mobile Environments through Interactive Virtual Reality Simulations

This study investigates the potential of enhancing collaborative learning in mobile environments through the integration of interactive virtual reality (VR) simulations. With the ubiquity of mobile devices and advancements in VR technology, there is a growing interest in using immersive experiences to promote collaborative learning among students. The study explores the design and implementation of interactive VR simulations customized for mobile platforms. The goal is to create engaging and immersive learning experiences that foster collaboration and knowledge sharing. By immersing students in virtual environments where they can interact with digital objects and manipulate scenarios, the study aims to facilitate active participation and teamwork, thereby enhancing learning outcomes. Furthermore, the study examines the impact of interactive VR simulations on student engagement, motivation, and knowledge retention in collaborative learning settings. Through empirical studies and user evaluations, the effectiveness of interactive VR simulations as a tool for collaborative learning in mobile environments is assessed. The findings provide valuable insights into the design and pedagogical integration of VR technologies in mobile learning contexts. They offer guidance for educators and instructional designers who aim to leverage the potential of immersive experiences to improve collaborative learning outcomes.

The Effectiveness of the Problem Based Learning Model in Improving Collaborative Capabilities and Student Learning Outcomes in Class XI SMA

One of the skills that must be possessed by students in the 21st century is collaborative ability. Collaborative skills are abilities possessed by individuals in the form of groups to exchange thoughts or ideas and work together to achieve the expected goals. Increasing collaborative skills in students has a positive impact, namely producing more knowledge than just completing work independently and students can exchange ideas to be able to solve problems encountered in the learning process obtained.The efforts made in this study by applying the problem based learning (PBL) learning model to be able to improve collaborative abilities and learning outcomes learners. The use of the PBL learning model can improve scientific attitudes and student learning outcomes. The PBL model can improve learning outcomes and students' communication skills. The problem-based learning model can assist teaching staff in undergoing the learning process because it can improve student learning outcomes. Based on the background that has been formulated, the purpose of conducting this research is to determine the effectiveness of the PBL model in improving collaborative abilities and student learning outcomes in class XI reproductive system material.

Application of Interdisciplinary Knowledge Integration in English Blended Education

Blended education in English combines traditional face-to-face teaching methods with online learning components, offering students a dynamic and flexible educational experience. It integrates technology into classroom instruction, providing access to digital resources, interactive learning platforms, and multimedia content. This approach allows for personalized learning experiences tailored to individual student needs while promoting collaboration, critical thinking, and digital literacy skills. Blended education in English fosters a conducive learning environment that combines the benefits of both traditional and online learning, enhancing student engagement and outcomes in English language acquisition and comprehension. This paper explores the potential of Cooperative Optimized Blended Education (COBE) to enhance interdisciplinary knowledge integration within English-blended education settings. Drawing upon theoretical frameworks such as game theory and optimization strategies, alongside empirical analyses and simulation results, the study elucidates the effectiveness of COBE in fostering collaborative learning outcomes. Through the utilization of digital resources, personalized learning paths, collaborative projects, blended assessment methods, and teacher training programs, COBE offers a dynamic and engaging approach to pedagogical innovation. Empirical findings and student performance data underscore the significance of COBE in promoting student engagement, knowledge retention, and interdisciplinary understanding. Furthermore, the paper highlights the importance of continuous monitoring and assessment to support student academic achievement within COBE. OBE resulted in a mean increase of 10% in student engagement, a 15% improvement in knowledge retention, and a 20% enhancement in interdisciplinary understanding. Furthermore, the paper emphasizes continuous monitoring and assessment to support student academic achievement within COBE.

Development of Collaboration Script-Based Worksheets to Improve Collaborative Skills and Learning Outcomes in Junior High Schools Science Learning

Science learning is expected to be capable of various competencies following curriculum demands, including students' collaborative skills. Collaborative skills provide many benefits to students. However, the facts show that the collaborative skills achieved by students in current learning are still low because the learning process is not directed at achieving the desired targets. Thus, this research was conducted to develop a collaboration script-based worksheet to improve junior high school students' collaborative skills and learning outcomes in science learning. This type of research is development research, which is carried out in three stages: the preliminary research phase, the development and prototyping phase, and the assessment phase. The research results show that the collaboration script-based worksheet developed in this research is categorized as valid, practical, and effective. Thus, it can be said that collaboration script-based worksheets can help students learn science collaboratively to improve collaborative skills and student learning outcomes.

Development of the EVIBEC Learning Outcomes Framework to support the delivery of evidence-based practice curricula in health care professional programmes: a codesign approach

BackgroundAll healthcare professional education programmes must adopt a systematic approach towards ensuring graduates achieve the competencies required to be an evidence-based practitioner. While a list of competencies for evidence-based practice exist, health care educators continue to struggle with effectively integrating the necessary competencies into existing curricula. The purpose of this project was to develop an open access cross-discipline, learning outcomes framework to support educators in integrating the teaching, learning and assessment required to ensure all graduates of health care professional programmes can achieve the necessary evidence-based practice competencies.MethodsAn interdisciplinary team of health care professional educators and a librarian completed a review of the health professions literature on the teaching and assessment of evidence-based practice. The literature, coupled with the teams’ collective experiences in evidence-based education and research, were used to identify relevant teaching, learning and evidence-based competency frameworks to inform the project design. The guide and toolkit for experience-based co-design developed by the National Health Service Institute for Innovation and Improvement was adopted for this study ( Institute for Innovation and Improvement: Experience Based Design: Guide & Tools In. Leeds: NHS; 2009.). A four-step approach involving three online participatory co-design workshops and a national validation workshop was designed. Students (n = 33), faculty (n = 12), and clinical educators (n = 15) participated in formulating and mapping learning outcomes to evidence-based competencies. ResultsThrough a rigorous, systematic co-design process the Evidenced-based Education Collaborative (EVIBEC) Learning Outcomes Framework was developed. This framework consists of a series of student-centred learning outcomes, aligned to evidence-based practice competencies, classified according to the 5 As of EBP and mapped to the cognitive levels of Bloom’s taxonomy. Associated learning activities for each step of EBP are suggested. ConclusionsA consensus-based, student-centred learning outcomes framework aligned to a contemporary set of EBP core competencies has been developed. The freely accessible EVIBEC framework may support entry level health care professional EBP education, by informing EBP curriculum development and offering the potential for interdisciplinary approaches to and sharing of valuable teaching and learning resources. Co-design proved an effective method in creating and refining this framework.

Investigating group formation: An experiment on the distribution of extraversion in educational settings

Group formation plays a crucial role in enhancing collaborative learning experiences. This study investigates the impact of extraversion as a criterion for group formation on collaborative learning outcomes. A total of 180 students participated in the experiment and were assigned to groups that were homogeneously or heterogeneously distributed in terms of extraversion. The groups met weekly and worked on group assignments throughout the semesters. The first hypothesis posed the outcomes to be explainable at the group-level. Surprisingly, the results show that groups with a homogeneous distribution of extraversion reported higher levels of group work satisfaction than those with a heterogeneous distribution, in contrast to the second hypothesis and the group hierarchy theory. These findings emphasize the potential of considering personality traits when forming groups and extend the existing literature on group formation. The study takes a critical stance by addressing normative definitions of leadership. Future research is suggested to further enhance collaborative learning experiences using similar interdisciplinary and experimental methods.

Detecting non-verbal speech and gaze behaviours with multimodal data and computer vision to interpret effective collaborative learning interactions

AbstractCollaboration is argued to be an important skill, not only in schools and higher education contexts but also in the workspace and other aspects of life. However, simply asking students to work together as a group on a task does not guarantee success in collaboration. Effective collaborative learning requires meaningful interactions among individuals in a group. Recent advances in multimodal data collection tools and AI provide unique opportunities to analyze, model and support these interactions. This study proposes an original method to identify group interactions in real-world collaborative learning activities and investigates the variations in interactions of groups with different collaborative learning outcomes. The study was conducted in a 10-week long post-graduate course involving 34 students with data collected from groups’ weekly collaborative learning interactions lasting ~ 60 min per session. The results showed that groups with different levels of shared understanding exhibit significant differences in time spent and maximum duration of referring and following behaviours. Further analysis using process mining techniques revealed that groups with different outcomes exhibit different patterns of group interactions. A loop between students’ referring and following behaviours and resource management behaviours was identified in groups with better collaborative learning outcomes. The study indicates that the nonverbal behaviours studied here, which can be auto-detected with advanced computer vision techniques and multimodal data, have the potential to distinguish groups with different collaborative learning outcomes. Insights generated can also support the practice of collaborative learning for learners and educators. Further research should explore the cross-context validity of the proposed distinctions and explore the approach’s potential to be developed as a real-world, real-time support system for collaborative learning.

Collaborate like expert designers: An exploratory study of the role of individual preparation activity on students' collaborative learning

Collaboration skill is one of the most critical skill sets for engineers-to-be while university engineering students have challenges engaging in productive collaborative learning practices. This study examined the effect of individual preparation before collaboration on students' collaborative learning outcomes and processes. A total of 82 engineering undergraduates (41 pairs) participated in the study and collaborated under two conditions: immediate collaboration and individual preparation before collaboration. A mixed-method approach was applied in this study. Students' online-design solutions and verbal discussions were collected for both collaborative learning outcomes and process analyses. Students produced higher quality design solutions with individual preparation before collaboration than immediate collaboration. There were different engineering design behavioral patterns under the two conditions, indicating different ways to define the design problem, generate solutions, and analyze and evaluate solutions. The findings and discussion provide insights for innovating pedagogical design to promote collaborative learning efficiency in real-world university classrooms.

Exploring the impact of chat-based collaborative activities and SRL-focused interventions on students’ self-regulation profiles, participation in collaborative activities, retention, and learning in MOOCs

AbstractDespite their potential to deliver a high-quality learning experience, massive open online courses (MOOCs) pose several issues, such as high dropout rates, difficulties in collaboration between students, low teaching involvement, and limited teacher–student interaction. Most of these issues can be attributed to the large number, diversity, and variation in self-regulated learning (SRL) skills of participants in MOOCs. Many instructional designers try to overcome these issues by incorporating collaborative activities. Others try to scaffold students’ SRL levels by making SRL-focused interventions. However, limited research combines the study of SRL-focused interventions with students’ engagement in collaborative activities, course retention, and learning outcomes of MOOC environments. We deployed a programming-oriented MOOC in which we incorporated chat-based collaborative activities, supported by a learning analytics dashboard. Students were asked to complete SRL-focused questionnaires at the beginning and the end of the course. Based on their score, we calculated an average score that forms their SRL level, creating three groups: (a) control, (b) general intervention, and (c) personalized intervention in which we provided personalized interventions. We compared the students’ learning outcomes, participation in collaborative activities, and retention in the MOOC. These comparisons provided evidence regarding the positive impact of different intervention modes on students’ engagement in collaborative activities and their learning outcomes, with respect to their various SRL profiles. Students allocated to the general and personalized intervention groups displayed increased participation in the collaborative activities and learning outcomes, as compared to students assigned to the control group. We also documented that the SRL interventions positively affected students’ course retention.

Effects of collaborative filtering‐based peer recommendation mechanism on in‐service teachers’ learning performance, knowledge construction, and social network during online training

AbstractBackgroundCollaborative learning has become a crucial approach to promoting online in‐service teacher training. Appropriate peer recommendation for group composition is the basis to ensure productive learning outcomes of collaborative learning. However, there is a lack of understanding of the impact of peer recommendation on in‐service teachers' online training.ObjectivesTherefore, based on the collaborative filtering approach, a peer recommendation mechanism for in‐service teachers was constructed in this study. We investigated the effects of the constructed mechanism on in‐service teachers' online learning performance, interactive knowledge construction behavioural patterns and social networks.MethodsIn this study, 82 in‐service teachers were recruited to participate in the study. Participants under the experimental condition (n = 41) were invited to apply collaborative filtering‐based peer recommendation mechanism for grouping, while participants under the control condition (n = 41) were invited to use random grouping method. Participants' interaction data were collected from online collaborative discussion activities in a 5‐week asynchronous online course. The pre‐post knowledge test, content analysis, lag sequential analysis and social network analysis were used to analyse the differences between groups.Results and ConclusionsThe following findings were revealed: (1) the experimental group performed better than the control group in terms of online learning performance; (2) interactive knowledge construction behavioural patterns generated in collaborative activities showed that the experimental group achieved deeper level of knowledge construction in collaboration than the control group; (3) social networks generated in collaborative activities showed that the experimental group had tighter interaction relationships than the control group. Therefore, the peer recommendation mechanism could be useful to improve peer recommendation for group composition and had positive effects on in‐service teachers' online training.ImplicationsThis study can shed light on the construction of peer recommendation mechanism in recommending appropriate peers for in‐service teachers and different learners in online collaborative learning.

ONLINE-BASED SCIENCE PROJECT LEARNING AS AN ELECTIVE INSTRUCTING MODEL TO IMPROVE THE COLLABORATIVE SKILLS OF ELEMENTARY STUDENTS

In the era of Intelligent Society 5.0, collaborative skills, which can be defined as the ability to work effectively with others to achieve common goals, are essential competencies for students to thrive. Therefore, this study aims to explore the effectiveness of Online-based Science Project Learning (SPL) as a substitute instructional model for fostering collaborative skills among elementary school students. The study participants consisted of 75 elementary school fifth-grade students, distributed across three classes in Muhammadiyah Islamic Elementary School, Surabaya, East Java, Indonesia. It is important to comprehend that this examination was a replica of a preliminary test, and was conducted following the same methodology without the inclusion of a control group. The study design utilized a single-group approach, incorporating both a pretest and a posttest assessment. Furthermore, data analysis was conducted through paired t-test, n-gain calculation, and ANOVA using IBM SPSS version 25. The obtained results showed a statistically significant increase in the collective proficiency score of the observed students, as assessed at a 5% alpha level, after their engagement with the online-based Science Project Learning (SPL) model. Additionally, the average n-gains for the three grades were high, with no grade-level differences, and over 90% of the students responded positively to the online-based SPL Model teaching method. Based on these findings, it was concluded that online-based SPL models improved the collaborative work skills of the observed students. This study has several implications. First, it enhances the understanding of 21st-century life skills and abilities among elementary school teachers in Indonesia. Second, it suggests the potential for expanding the scope of the subject matter. Third, it underscores the importance of government collaborations in studies that prioritize the development of 4C skills, particularly collaboration, among students. Moreover, the study also emphasizes the necessity of online-based Science Project Learning (SPL) for scholars interested in remote learning, with a focus on examining the collaborative abilities and science learning outcomes of elementary students in virtual learning environments.

PENERAPAN PROJECT BASED LEARNING DALAM MEMBUAT KOLASE PADA ELEMEN DASAR FASHION DESIGN

The Project Based Learning Learning Model is one model that can be applied in making collages on the Basic Elements of Fashion Design. This learning model has great potential to make students work collaboratively in producing work according to the demands of the independent curriculum. The population of this study was students at SMK Dharma Wanita Gresik, Fashion Design Skills. The purpose of this research is to find out how to apply the Project Based Learning learning model to the Basic Elements of Fashion Design in making collages, to find out the results of learning to make collages after applying the Project Based Learning learning model, to find out the level of collaboration of students in making collages through the Project Based Learning learning model. The research was carried out by observing the application of the Project Based Learning learning model, the collaborative level of students, and the assessment of learning outcomes. The application of Project Based Learning and the collaborative behavior of students was assessed by 3 observers through observations during the learning process while learning outcomes were obtained from the assessment of collage products. Data from the application of Project Based Learning gets an average score of 93.45% with very good quality, the collaborative level gets an average score of 93.05% with very good quality, and learning outcomes to make collages get an average score of 88.4. With the application of the Project Based Learning learning model in making collages, it shows that learning can be carried out at a very good collaborative level and learning outcomes achieve a minimum completeness criterion value.

Problem-Based Collaborative Learning Model Improves Physical Education Learning Outcomes for Elementary School Students

The problems in this study included the low PE values obtained from the results of observations and student response questionnaires. This study aimed to analyze the effectiveness of problem-based collaborative learning models on the learning outcomes of Physical Education students in elementary schools. This study uses a quasi-experimental design. Methods of data collection using interviews, observation, and tests. The instruments used were learning achievement tests, learning observations, and student response questionnaires to learning. Data analysis techniques using descriptive qualitative analysis, quantitative, and inferential statistics. The study results included three aspects of assessment, namely the cognitive, affective, and psychomotor aspects, which had good averages, namely 3.4, 3.5, and 3.3, respectively. The standard deviation or variation of each aspect of the assessment is 0.5. Overall, student learning outcomes are also categorized as good, with an average of 3.4, an average score of 85, and a standard deviation of 0.5. The results of the relationship between collaborative learning and learning outcomes in PE subjects with a significance level of 0.05 indicates a significant relationship between the two. The results of hypothesis testing show that the collaborative model has a significant influence on learning outcomes. It was concluded that collaborative learning improves PE students' learning outcomes more effectively than conventional learning. Factors that can affect student learning outcomes include the learning environment, learning methods used, and the quality of teacher teaching.

The utility of an interprofessional education framework and its impacts upon perceived readiness of graduates for collaborative practice. A multimethod evaluation using the context, input, process, product (CIPP) model

BackgroundFrameworks in higher education can support strategic curriculum change in complex systems. The impact of these frameworks in achieving their stated purpose is less known. An interprofessional education (IPE) framework and related multi-activity curriculum designed to develop health profession graduates with the requisite skills for collaborative care, was introduced in a large university, across eleven health professions. ObjectiveTo determine the utility of an interprofessional framework and impact upon perceived work readiness for collaborative practice. MethodA multimethod design using the context, input, process, product (CIPP) evaluation model was selected taking a social constructivist theoretical stance. Data collection included staffing allocation to IPE, curriculum audit, and reflections from representatives of all health professions courses offered at the institution. Data was analyzed using framework analysis. ParticipantsInterviews or focus groups were undertaken with academic Faculty (n = 13), recent graduates (n = 24) and clinical supervisors/employers of recent graduates (n = 17). ResultsThe framework assisted the systematic implementation of interprofessional curriculum across the different health courses at the university. Collaborative work-ready learning outcomes were identified in graduates where targeted curriculum had been implemented across all four domains of the framework. Gaps identified in framework implementation were consistent with gaps identified in graduate knowledge and skills related to collaborative practice. The combination of formal university-based IPE and informal workplace learning as part of clinical placements contributed to achieving the desired learning outcomes. ConclusionsThese findings offer insights into the use of shared frameworks to drive specific learning activities related to collaborative practice.

The Interaction Effect of Group Formation and Individual Preparation on Computer Support Collaborative Engineering Design: An Exploratory Study

Collaboration, as one of the most essential skill sets for engineering students, remains challenging for both engineering educators and student engineers. This study explores the role of pedagogical support individual preparation before collaboration on engineering students’ collaborative learning outcome as well as the process. A total of 36 dyads engineering students from a university engineering class participated in the study, divided into 2 group formations: homogeneous group (two similarly experienced student engineers) and heterogeneous group (one experienced student engineer and one less experienced student engineer). All dyads completed two engineering design tasks in two conditions: immediate collaboration (control condition) and individual preparation before collaboration (experimental condition) in a face-to-face (F2F) computer-supported collaborative learning (CSCL) context. The results indicated the interaction effect of individual preparation and group formation on students’ collaborative knowledge co-construction. The homogeneous group formation produced higher quality knowledge co-construction and design solutions when there was an individual preparation before collaboration than immediate collaboration. Meanwhile, the heterogeneous group formation produced lower quality knowledge co-construction and design solutions when there was an individual preparation before collaboration than immediate collaboration. These findings expand the current understanding of individual preparation before collaboration and provide insights for the design of computer-supported collaborative learning in classrooms.

Examining socially shared regulation and shared physiological arousal events with multimodal learning analytics

AbstractSocially shared regulation contributes to the success of collaborative learning. However, the assessment of socially shared regulation of learning (SSRL) faces several challenges in the effort to increase the understanding of collaborative learning and support outcomes due to the unobservability of the related cognitive and emotional processes. The recent development of trace‐based assessment has enabled innovative opportunities to overcome the problem. Despite the potential of a trace‐based approach to study SSRL, there remains a paucity of evidence on how trace‐based evidence could be captured and utilised to assess and promote SSRL. This study aims to investigate the assessment of electrodermal activities (EDA) data to understand and support SSRL in collaborative learning, hence enhancing learning outcomes. The data collection involves secondary school students (N = 94) working collaboratively in groups through five science lessons. A multimodal data set of EDA and video data were examined to assess the relationship among shared arousals and interactions for SSRL. The results of this study inform the patterns among students' physiological activities and their SSRL interactions to provide trace‐based evidence for an adaptive and maladaptive pattern of collaborative learning. Furthermore, our findings provide evidence about how trace‐based data could be utilised to predict learning outcomes in collaborative learning. Practitioner notesWhat is already known about this topic Socially shared regulation has been recognised as an essential aspect of collaborative learning success. It is challenging to make the processes of learning regulation ‘visible’ to better understand and support student learning, especially in dynamic collaborative settings. Multimodal learning analytics are showing promise for being a powerful tool to reveal new insights into the temporal and sequential aspects of regulation in collaborative learning. What this paper adds Utilising multimodal big data analytics to reveal the regulatory patterns of shared physiological arousal events (SPAEs) and regulatory activities in collaborative learning. Providing evidence of using multimodal data including physiological signals to indicate trigger events in socially shared regulation. Examining the differences of regulatory patterns between successful and less successful collaborative learning sessions. Demonstrating the potential use of artificial intelligence (AI) techniques to predict collaborative learning success by examining regulatory patterns. Implications for practice and/or policy Our findings offer insights into how students regulate their learning during collaborative learning, which can be used to design adaptive supports that can foster students' learning regulation. This study could encourage researchers and practitioners to consider the methodological development incorporating advanced techniques such as AI machine learning for capturing, processing and analysing multimodal data to examine and support learning regulation.