Search

Higher education institutes are continuously exploiting technology to improve the delivery of courses. This paper reviews the use of mobile learning applications in higher education institutes to; i) identify publication trends, ii) types of mobile learning applications used, and iii) categorize the research papers published. The applied method is the Systematic Mapping Study. A Systematic mapping study was conducted using 103 papers retrieved from six different databases. The findings of this mapping study showed an increased research interest in the field and a variety of mobile learning applications used (learning management, vodcast and podcast, game-based learning, collaborative learning, and language learning applications). The published studies are mainly solution-oriented that focus on the use of mobile learning applications. The results were helpful to position future research activities. [ABSTRACT FROM AUTHOR]

Both participation and argumentation (OECD, 2022) are important keywords in educational contexts. While participation is seen as a crucial prerequisite for education and collaborative learning in general, argumentation as a discursive practice serves to convey and negotiate—also school-specific—knowledge. This paper explores repetition in argumentative events as a technique of establishing—or even hindering—participation in terms of alignment and affiliation. It can serve as a strategy for participation by signalling responsiveness and thematic coherence—and thus inclusion. At the same time, however, studies show that repetition can also signal contradiction and rejection—and thus exclusion. So far, we know little about how exactly these functional differences are produced—especially in younger children. Therefore, the paper explores how children use repetition as a resource for negotiating participation in argumentative events. Using authentic data in the form of observations and transcriptions of audio and video recordings from child-child-interactions of 15 Hebrew- and 31 German-speaking children aged 3–6 years, we identify oral argumentative events and investigate different forms of repetitions and their respective relevance for enabling participation. Our results show that, on the one hand, minimal and partial repetitions are used by the children in an inclusive way, creating closeness between the participants. On the other hand, children use complete repetitions more as an excluding technique, displaying misalignment and disaffiliation, in order to challenge and mock each other. The findings suggest that this line of research has significant potential to provide new insights into the formation of social relationships between peers, into the prevention or establishment of participation, which itself is a prerequisite for joint learning, as well as insights into the acquisition of argumentative competence. [ABSTRACT FROM AUTHOR]

Educational robotics has been adopted to create interactive and engaging learning environments to develop computational thinking (CT) in K-12 learners. This study systematically examined 22 peer-reviewed empirical research articles on the use of educational robotics to develop CT in young learners (pre-kindergarten to 6th grade) published between 2012 and 2021. The findings revealed that using robotics activities to develop CT has mostly been studied in the formal education settings with the duration of robotics curricular activities ranging from 80 minutes to 24 hours. The five CT skills studied most often include Sequencing, Conditionals, Loops, Debugging, and Algorithmic Thinking. The different versions of LEGO Mindstorms are the most frequently adopted robotic kits in the examined studies. The most frequently adopted learning and instructional strategies in the robotics activities include collaborative learning, project-based learning, and embodied learning. This paper identified and discussed developmentally appropriated CT skills, robotics kits, and pedagogical approaches suitable for supporting CT development in young learners. The findings can guide educators and instructional designers for future robotics activity design and development endeavors. This paper also identified gaps in the current research and recommended directions for advancing research in adopting robotics to develop CT in young learners. [ABSTRACT FROM AUTHOR]

This study conducted a scoping review of publications in mobile Computer-Supported Collaborative Learning for mathematics. Papers published between 2007 and 2021 inclusive were retrieved from research databases to achieve this goal. Twenty-eight papers met the inclusion–exclusion criteria of the study. It was shown that two papers were published on average over the last 15 years. The majority of the papers were published in peer-reviewed journals. Intending to improve mathematics pedagogy, the two most popular math mCSCL contents were general elementary mathematics and geometry. The review also revealed that math mCSCL benefited elementary students the most. The majority of math mCSCL software was custom-built and designed for synchronous sharing. The research designs were consistent with the existing reviews. The effects on social and attitude skills, as well as mathematics competency, were the most frequently mentioned benefits of math mCSCL. Usability issues, device unfamiliarity, inability to track students' activities, synchronization, and coordination concerns were among the problems highlighted during the implementation of math mCSCL. The implications for future research are discussed. [ABSTRACT FROM AUTHOR]

Visible-infrared cross modality person re-identification (CM-ReID) has received extensive attention on the community due to its profound applicability for 24-h scene surveillance. The huge modality discrepancy makes it very susceptible to background clutter, especially for infrared images. In this paper, we propose a mask-guided dynamic dual-task collaborative learning (MG-DDCL) method to extract background irrelevant pedestrian representation. A dynamic dual-task collaborative learning strategy is proposed to extract pedestrian representation and generate foreground masks by a unified convolutional neural network. This strategy improved the map by 0.95% and improved the Rank-1 by 1.9%. To make the guidance mask to facilitate the cross modality person re-identification task, we modify the hard-mask produced by semantic segmentation into the friendly soft-mask and generate foreground response map by the regression learning manner. Compared with the classification manner, our method has significant advantages. Extensive experiments conducted on two datasets SYSU-MM01 and RegDB demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Design-Based Learning (DBL) is a pedagogical approach where learning is situated in the context of design activities that are typically carried out in groups. During collaborative design inquiry, reflection is of vital importance for learning from design experience. The paper presents a research-through-design study with the intention to generate knowledge on how to design for supporting reflection-in-action during design-based learning. This study addresses the research question: how can a media tool support a group of students in externalizing reflection while they are engaging in DBL? This paper describes the design and evaluation of ReflectionSchema, a tool intended to support reflection-in-action in such a learning environment. The tool offers visualized guidance for coordinating a group of students' understanding of how they can combine reflecting with making design representations. The tool was trialed by 13 groups of students aged 12 to 13, who used the tool to record short reflection videos along their whole DBL process. We analyzed the efficacy of ReflectionSchema in terms of supporting collaborative reflection-in-action. Furthermore, we investigated the process of reflection-in-action during Design-based learning processes by examining the collaborative reflection patterns in the reflection videos that include the actions, roles, recording preference/style, and strategies employed. We discussed how these findings can inform the design of other reflection tools for similar settings. [ABSTRACT FROM AUTHOR]

Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the cloud. However, the reconstruction attack was proposed recently to recover the original input image from intermediate outputs that can be collected from local models in collaborative inference. For addressing such privacy issues, a promising technique is to adopt differential privacy so that the intermediate outputs are protected with a small accuracy loss. In this paper, we provide the first systematic study to reveal insights regarding the effectiveness of differential privacy for collaborative inference against the reconstruction attack. We specifically explore the privacy-accuracy trade-offs for three collaborative inference models with four datasets (SVHN, GTSRB, STL-10, and CIFAR-10). Our experimental analysis demonstrates that differential privacy can practically be applied to collaborative inference when a dataset has small intra-class variations in appearance. With the (empirically) optimized privacy budget parameter in our study, the differential privacy technique incurs accuracy loss of 0.476%, 2.066%, 5.021%, and 12.454% on SVHN, GTSRB, STL-10, and CIFAR-10 datasets, respectively, while thwarting the reconstruction attack. [ABSTRACT FROM AUTHOR]

Nowadays, large-scale individual trajectories can be collected by various location-based social network services, which enables us to better understand human mobility patterns. However, the trajectory data usually contain sensitive information of users, raising considerable concerns about the privacy issue. Existing methods for protecting user trajectory data face two major challenges. First, existing methods generally emphasize on data privacy but largely ignore the data utility. Second, most existing work focus on protecting the privacy of users' check-in locations, which is not sufficient to protect against the trajectory-user linking (TUL) attack that infers a user's identity based on her/his trajectories. In this paper, we for the first time propose a collaborative adversarial learning model named BPUCAL to effectively resist the TUL attack and preserve the data utility simultaneously. The general idea is to fool the TUL model by adding a small perturbation on the original trajectory data to balance the data utility and privacy. BPUCAL perturbs a few numbers of carefully identified check-ins of a trajectory which are pivotal for a TUL model to infer the identity of a user. Specifically, BPUCAL contains three parts: a perturbation generator, a discriminator, and a TUL model. The generator aims to produce learnable noise and adds it to the original trajectories for obtaining perturbed trajectories. The perturbed trajectories with a minimal changes compared to the original trajectories can deceive both the discriminator and the TUL model. Extensive experiments are conducted over two real-world datasets. The results show the superior performance of our proposal in balancing data privacy and utility on trajectory data by comparison with baselines. [ABSTRACT FROM AUTHOR]

Distant supervised relation extraction has been increasingly popular in recent years, which generates datasets automatically without human intervention. However, the distant supervised assumption has the limitation that the generated datasets have inevitable labeling errors. This paper proposes the method of Hierarchical Symmetric Cross Entropy for Distant Supervised Relation Extraction (HSCERE) to alleviate the impact of the noisy labels. Specifically, HSCERE simultaneously utilizes two extractors with the same network structure for collaborative learning. This collaborative learning process guides the optimization of the extractor through a joint loss function, namely Hierarchical Symmetric Cross Entropy (HSCE). Within the HSCE loss, the predicted probability distribution of the extractors serves as the supervisory signal, guiding the optimization of the extractors on two levels to reduce the impact of noisy labels. The two levels include the internal optimization within each extractor and the collaborative optimization between extractors. Experiments on generally used datasets show that HSCERE can effectively handle noisy labels and can be incorporated into various methods to enhance their performance. [ABSTRACT FROM AUTHOR]

Label distribution learning, where deal with label ambiguity by describing the degree of relevance of each label to a specific instance. As a novel machine learning paradigm, the curse of dimensionality is one of the prominent problems. Feature selection is a vital preprocessing step to reduce the high dimensionality of data. However, most existing label distribution feature selection methods focus on selecting a feature subset that has relevant capabilities for all labels, ignoring label-specific features with the maximum discriminatory power for each label. To tackle this issue, a label distribution feature selection algorithm based on label-specific features is proposed in this paper. Initially, we introduce a feature selection optimization model for label distribution data that simultaneously considers common and label-specific features, leveraging sparse learning to further investigate the intricate relationships between features and labels. Subsequently, the label correlation coefficient is employed to enhance the collaborative learning effect of labels. Finally, the relevance between features and labels is taken into account to guide the feature selection process, which can effectively eliminate the redundant features. Comprehensive experiments demonstrate the advantage of our proposed method over other well-established feature selection algorithms for selecting label-specific features to label distribution data. [ABSTRACT FROM AUTHOR]

Successful computer-supported collaborative learning (CSCL) relies on collaborative group engagement, a complex construct characterized by multifaceted, dynamic, socio-emotional, and socio-cognitive processes. This paper provides a detailed analysis of collaborative group engagement, with a particular focus on nonverbal behaviors as indicators of high versus low group engagement. Using video observations and a multi-method approach, we examine in detail the relationships between different dimensions of group engagement (i.e., behavioral, social, cognitive, and conceptual-to-consequential engagement) and nonverbal behaviors. Using qualitative case analysis, we also provide a rich examination of selected cases to identify the role that nonverbal behaviors play in high-engagement sequences compared with low-engagement sequences. Our findings shed light on specific nonverbal behaviors, including nodding, laughing, and eye contact, as significant indicators of high versus low collaborative group engagement. Notably, more of these nonverbal behaviors are evident in high-engagement sequences, suggesting mutual reinforcement on each dimension of engagement—with the exception of behavioral engagement, where increased laughing or smiling is evident in low-engagement sequences, but still serves a productive group process. The paper concludes with a discussion and implications of the findings. By demonstrating the role of nonverbal behaviors as important indicators, this work contributes to the understanding of the complex, dynamic, and contextualized nature of collaborative group engagement in CSCL settings. [ABSTRACT FROM AUTHOR]

Collaborative learning (CL) is widely used in higher education around the world because it is associated with increases in students' knowledge and social skills. Low student engagement in CL activities has been identified as a common issue, while there is no CL-specific engagement scale to measure and understand engagement in such settings. Additionally, although western countries have been investigating student engagement since the 1950s, there have been comparatively few studies of this important construct in China. To address these imbalances, the present paper adopted a mixed methods approach to developing and validating a Chinese CL engagement scale. In the quantitative study, Chinese university students (N = 405) completed an anonymous online survey to assess their engagement in CL activities. Results from exploratory and confirmatory factor analyses supported a hierarchical (second-order) three-factor model of student engagement (behavioural, cognitive and emotional engagement), consistent with the tripartite conception of student engagement in Western countries. Participants were further divided into three unique groups based on engagement scores, and in the qualitative study, 12 participants from three groups were interviewed about CL experiences. Interviews served to further validate the quantitative results. The significance, limitations, and implications of these findings are discussed. [ABSTRACT FROM AUTHOR]

In a previous study, we established that compared to a written case, a video case enhances observable cognitive processes in the verbal interaction in a postgraduate problem-based learning format. In a new study we examined non-observable cognitive processes using a stimulated recall procedure alongside a reanalysis of the data from the first study. We examined the development of shared cognition as reflected in collaborative concept link formation, an approach to connecting a series of concepts related to a particular topic. Eleven paediatric residents were randomly allocated to two groups. After both analysing the same written case vignette, one group watched a video of the case in the vignette and the other group read a written description of the video. Both groups then reanalysed the vignette. After the group sessions, time-logged transcripts were made of the verbal interaction in both groups and all residents individually took part in a stimulated recall procedure. Causal reasoning concept links were labelled as individual or collaborative depending on whether they originated from individual residents or were directly elicited by verbal utterances from others. The video led to a significantly increased frequency ratio (after intervention: before intervention) of collaborative concept links but did not affect the frequency of individual concept links. This novel process approach to chronological registration of concept link formation offered additional evidence that shared cognition by means of co-elaboration of concept formation is stimulated by the use of patient video recordings in small group learning. [ABSTRACT FROM AUTHOR]

Collaborative learning and cooperative learning are two separate approaches developed independently by two groups of scholars around the same period of time in the 1960 and 1970 s. Due to their different origins and intertwined paths of development, they have their own distinct features while sharing many similarities. The relationship between collaborative learning and cooperative learning can be confusing. Therefore, this paper provides a brief historical review of collaborative learning and cooperative learning to identify the origins of each, where they diverge from each other, and where they are aligned. This paper examines the definitions of the two terms and compares their characteristics. This is followed by a discussion of their historical development in the last fifty years: early development between the 1960 and 1970 s; maturation in the 1980 and 1990 s; convergence in the mid-1990s; and the emergence of Computer-Supported Collaborative Learning (CSCL) in the late 1980s. Finally, this paper summarizes the four paradigms of mainstream research on collaborative and cooperative learning, namely, the "effect" paradigm, the "conditions" paradigm, the "interaction" paradigm, and the "design" paradigm. [ABSTRACT FROM AUTHOR]

The Smart Grid (SG) heavily depends on the Advanced Metering Infrastructure (AMI) technology, which has shown its vulnerability to intrusions. To effectively monitor and raise alarms in response to anomalous activities, the Intrusion Detection System (IDS) plays a crucial role. However, existing intrusion detection models are typically trained on cloud servers, which exposes user data to significant privacy risks and extends the time required for intrusion detection. Training a high-quality IDS using Artificial Intelligence (AI) technologies on a single entity becomes particularly challenging when dealing with vast amounts of distributed data across the network. To address these concerns, this paper presents a novel approach: a fog-edge-enabled Support Vector Machine (SVM)-based federated learning (FL) IDS for SGs. FL is an AI technique for training Edge devices. In this system, only learning parameters are shared with the global model, ensuring the utmost data privacy while enabling collaborative learning to develop a high-quality IDS model. The test and validation results obtained from this proposed model demonstrate its superiority over existing methods, achieving an impressive percentage improvement of 4.17% accuracy, 13.19% recall, 9.63% precision, 13.19% F1 score when evaluated using the NSL-KDD dataset. Furthermore, the model performed exceptionally well on the CICIDS2017 dataset, with improved accuracy, precision, recall, and F1 scores reaching 6.03%, 6.03%, 7.57%, and 7.08%, respectively. This novel approach enhances intrusion detection accuracy and safeguards user data and privacy in SG systems, making it a significant advancement in the field. [ABSTRACT FROM AUTHOR]

The objective of few-shot learning (FSL) is to learn a model that can quickly adapt to novel classes with only few examples. Recent works have shown that a powerful representation with a base learner trained in supervised and self-supervised manners has significant advantages over the existing sophisticated FSL algorithms. In this paper, we build on this insight and propose a new framework called global and local representation collaborative learning (GLCL), which combines the complementary advantages of global equivariance and local aggregation. Global equivariance learns the internal structure of data to improve class discrimination, and the local aggregation retains important semantic information to enrich feature representations. In addition, we design a cross-view contrastive learning to promote the consistent learning and implicit exploration of useful knowledge from one another. A simultaneous optimization of these contrasting objectives allows the model to encode informative features while maintaining strong generalization capabilities for new tasks. We demonstrate consistent and substantial performance gains for FSL classification tasks on multiple datasets. Our code is available at https://github.com/zjgans/GLCL. [ABSTRACT FROM AUTHOR]

In Industry-Academia Collaborations (IAC) both academic, scientific research results and industrial practitioner findings and experiences are produced. Both types of knowledge should be gathered, codified, and disseminated efficiently and effectively. This paper investigates a recent (2014–2017) large-scale IAC R&D&I program case (Need for Speed, N4S) from a learning perspective. It was one of the programs in the Finnish SHOK (Strategic Centres of Science, Technology, and Innovation) system. The theoretical bases are in innovation management, knowledge management, and higher education (university) pedagogy. In the future, IAC projects should be more and more commonplace since major innovations are hardly ever done in isolation, not even by the largest companies. Both intra-organizational and inter-organizational learning networks are increasingly critical success factors. Collaborative learning capabilities will thus be required more often from all the participating parties. Efficient and effective knowledge creation and sharing are underpinning future core competencies. In this paper, we present and evaluate a collaboratively created and publicly shared digital knowledge repository called "Treasure Chest" produced during our case program. The starting point was a jointly created Strategic Research and Innovation Agenda (SRIA), which defined the main research themes and listed motivating research questions to begin with—i.e., intended learning outcomes (ILO). During the 4-year program, our collaborative industry-academia (I-A) learning process produced a range of theoretical and empirical results, which were iteratively collected and packaged into the Treasure Chest repository. Outstandingly, it contained, in addition to traditional research documents, narratives of the industrial learning experiences and more than 100 actionable knowledge items. In conclusion, our vision of the future is that such transparently shared, ambitious, and versatile outcome goals with a continuous integrative collection of the results are keys to effective networked I-A collaboration and learning. In that way, the N4S largely avoided the general problem of often conflicting motives between industrial firms seeking answers and applied solutions to their immediate practical problems and academic researchers aiming at more generalizable knowledge creation and high-quality scientific publications. [ABSTRACT FROM AUTHOR]

This study investigates how learners collaboratively construct embodied geometry knowledge in shared VR environments. Three groups of in-service teachers collaboratively explored six geometric conjectures with various virtual objects (geometric shapes) under the guidance of a facilitator. Although all the teachers were in different physical locations, they logged into a single virtual classroom with their respective groups and were able to see and manipulate the same geometric shapes as well as see their collaborators' avatars and actions on the shapes in real time in the shared virtual space. This paper introduces a novel multimodal data analysis method for analyzing participants' interactive patterns in collaborative forms of actions, gestures, movements, and speech. Results show that collaborative speech has a strong simultaneous relationship with actions on virtual objects and virtual hand gestures. They also showed that body movements and positions, which often focus on virtual objects and shifts in these movements away from or around the object, often signal key interactional collaborative events. In addition, this paper presents five emergent multimodality interaction themes showing participants' collaborative patterns in different problem-solving stages and their different strategies in collaborative problem-solving. The results show that virtual objects can be effective media for collaborative knowledge building in shared VR environments, and that structured activity design and moderate realism may benefit shared VR learning environments in terms of equity, adaptability, and cost-effectiveness. We show how multimodal data analysis can be multi-dimensional, visualized, and conducted at both micro and macro levels. [ABSTRACT FROM AUTHOR]

This paper stems from calls for methodological advancement in two areas of research: primary mathematics education and dialogical education. We respond to these calls from the commognitive standpoint by introducing the Grove of Realizations as a tool for capturing and visualizing individual students' learning through collaborative work in small groups. We focus on a group of four students from a New Zealand Year 4 class (aged 8 and 9 years old), as they classified odd and even numbers and reasoned about their sums. This data is used to present the analytical affordances of the tool for (i) visualizing gaps in communication between group members, (ii) mapping their discursive development, and (iii) showing whether and how gaps are bridged within a group. The paper concludes with the discussion of the tool's affordances and directions for further development. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a promising framework for distributed machine learning that trains models without sharing local data while protecting privacy. FL exploits the concept of collaborative learning and builds privacy-preserving models. Nevertheless, the integral features of FL are fraught with problems, such as the disclosure of private information, the unreliability of uploading model parameters to the server, the communication cost, etc. Blockchain, as a decentralized technology, is able to improve the performance of FL without requiring a centralized server and also solves the above problems. In this paper, a systematic literature review on the integration of Blockchain in federated learning was considered with the analysis of the existing FL problems that can be compensated. Through carefully screening, most relevant studies are included and research questions cover the potential security and privacy attacks in traditional federated learning that can be solved by blockchain as well as the characteristics of Blockchain-based FL. In addition, the latest Blockchain-based approaches to federated learning have been studied in-depth in terms of security and privacy, records and rewards, and verification and accountability. Furthermore, open issues related to the combination of Blockchain and FL are discussed. Finally, future research directions for the robust development of Blockchain-based FL systems are proposed. [ABSTRACT FROM AUTHOR]

During the last decade, different values, tools and practices promoted by maker culture have been adopted in formal educational settings with the aim of reinvigorating Science, Technology, Engineering and Mathematics (STEM) education. Higher education institutions (HEIs) have also engaged with maker culture to explore its potentialities regarding education, entrepreneurship and innovation. However, these collaborations with various stakeholders are not always smooth and educators need to deal with significant challenges that arise in these engagements, despite the problem-solving learning opportunities that they can offer their students. This paper presents the results of a case study that dealt with these issues through the establishment of an open and collaborative learning ecosystem (OCLE) between different educators, students and external stakeholders. The empirical work was based on thirty-three semi-structured interviews across four countries, eight focus groups and a final participatory workshop. The study argues that maker culture can offer several potentialities for pushing forward an integrative vision of STEM education as well as other disciplines from social sciences and humanities. An emphasis is placed on how tertiary education can benefit greatly from the adoption of OCLEs and how these communities of practices can encourage an education oriented to meeting societal challenges. The paper also warns that these kinds of interventions face significant organisational challenges in HEIs that demand significant institutional recognition and support to overcome this organisational resistance. [ABSTRACT FROM AUTHOR]

This paper provides a methodology to assess the optimal multi-agent architecture for collaborative prognostics in modern fleets of assets. The use of multi-agent systems has been shown to improve the ability to predict equipment failures by enabling machines with communication and collaborative learning capabilities. Different architectures have been postulated for industrial multi-agent systems in general. A rigorous analysis of the implications of their implementation for collaborative prognostics is essential to guide industrial deployment. In this paper, we investigate the cost and reliability implications of using different multi-agent systems architectures for collaborative failure prediction and maintenance optimization in large fleets of industrial assets. Results show that purely distributed architectures are optimal for high-value assets, while hierarchical architectures optimize communication costs for low-value assets. This enables asset managers to design and implement multi-agent systems for predictive maintenance that significantly decrease the whole-life cost of their assets. [ABSTRACT FROM AUTHOR]

Sparse subspace clustering (SSC) focuses on revealing the structure and distribution of high dimensional data from an algebraic perspective. It is a two-phase clustering technique, performing sparse representation of the high dimensional data and subsequently cutting the induced affinity graph, which cannot achieve an optimal or expected clustering result. To address this challenge, this paper proposes an approach to subspace representation collaborative clustering (SRCC) for incomplete high dimensional data. In the proposed model, both phases of sparse subspace representation and clustering are integrated into a unified optimization, in which a fuzzy partition matrix is introduced as a bridge to cluster the extracted sparse representation features of the data. At the same time, the missing entries are adaptively imputed along with the two phases. To generalize SRCC to a semi-supervised case, an adjacency matrix of incomplete data is constructed with the ideas of 'Must-link' and 'Cannot-link'. Meanwhile, a semi-supervised indicator matrix is introduced to promote discriminative capacity of revealing global and local structures of incomplete data and enhance the performance of clustering. The semi-supervised sparse representation collaborative clustering (S3RCC) is modeled. Extensive experiments on lots of real-world benchmark datasets demonstrate the superior performance of the proposed two models on imputation and clustering of incomplete data compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Understanding the relationship between interactive behaviours and discourse content has critical implications for instructors' design and facilitation of collaborative discussion activities in the online discussion forum (ODF). This paper adopts social network analysis (SNA) and epistemic network analysis (ENA) methods to jointly investigate the relationships between students' network characteristics, discussion topics, and learning outcomes in a course discussion forum. Discourse data from 207 participants were included in this study. The findings indicated that (1) the interactive network generated in the collaborative discussion activities was sparsely connected, and there was limited information exchange between instructors and students; (2) students' discussion topics were mainly related to the learning content; (3) compared with the isolated group, students in the leader, mediator, and animator groups were more concerned about topics related to the learning content; and (4) students who discussed more topics related to the learning content performed better than the students who discussed more topics related to learning methods and social interactions. The learning outcomes of the influencer and leader groups were significantly higher than those of the peripheral and isolated groups. However, there was no significant correlation between students' individual centrality and their learning outcomes. The findings enrich the ODF research on the comprehensive identification of interactive behaviours and discourse content in the process of collaborative discussion activities and on the discussion topic differences between different role groups. The study findings also have practical implications for instructors to design effective instructional interventions aimed at improving the quality of collaboration in the ODF. [ABSTRACT FROM AUTHOR]

Existing research on audio–text retrieval is limited by the size of the dataset and the structure of the network, making it difficult to learn the ideal features of audio and text resulting in low retrieval accuracy. In this paper, we construct an audio–text retrieval model based on contrastive learning and collaborative attention mechanism. We first reduce model overfitting by implementing audio augmentation strategies including adding Gaussian noise, adjusting the pitch and changing the time shift. Additionally, we design a co-attentive mechanism module that the audio data and text data guide each other in feature learning, effectively capturing the connection between the audio modality and the text modality. Finally, we apply the contrastive learning methods between the augmented audio data and the original audio, allowing the model to effectively learn a richer set of audio features. The retrieval accuracy of our proposed model is significantly improved on publicly available datasets AudioCaps and Clotho. [ABSTRACT FROM AUTHOR]

Recognizing human actions in video sequences, known as Human Action Recognition (HAR), is a challenging task in pattern recognition. While Convolutional Neural Networks (ConvNets) have shown remarkable success in image recognition, they are not always directly applicable to HAR, as temporal features are critical for accurate classification. In this paper, we propose a novel dynamic PSO-ConvNet model for learning actions in videos, building on our recent work in image recognition. Our approach leverages a framework where the weight vector of each neural network represents the position of a particle in phase space, and particles share their current weight vectors and gradient estimates of the Loss function. To extend our approach to video, we integrate ConvNets with state-of-the-art temporal methods such as Transformer and Recurrent Neural Networks. Our experimental results on the UCF-101 dataset demonstrate substantial improvements of up to 9% in accuracy, which confirms the effectiveness of our proposed method. In addition, we conducted experiments on larger and more variety of datasets including Kinetics-400 and HMDB-51 and obtained preference for Collaborative Learning in comparison with Non-Collaborative Learning (Individual Learning). Overall, our dynamic PSO-ConvNet model provides a promising direction for improving HAR by better capturing the spatio-temporal dynamics of human actions in videos. The code is available at https://github.com/leonlha/Video-Action-Recognition-Collaborative-Learning-with-Dynamics-via-PSO-ConvNet-Transformer. [ABSTRACT FROM AUTHOR]

Educational resources and activities should be appropriate to the learning and development potential of each student, which is crucial when the student has some disability. For hearing impaired students (suffering hypoacusis), it is particularly important to exploit tactile and visual aids, as they access information and knowledge mainly through them, and this in a socially inclusive context. Tangible systems (where the users interact with the system by manipulating physical objects that represent functions or data of the system itself) offer a more natural, tactile interaction than other types of interfaces, and complements it with visual aids; besides, this kind of systems foster social interactions and collaboration. Tangible systems then have the features to be an adequate support for hearing impaired students. This has been investigated in the context of teaching basic skills to children and adolescents; however, there is a lack of studies regarding the use of tangible systems for teaching advanced concepts to university students. This paper reports an exploratory study which was conducted to gain insight into possible benefits and issues that might arise when a university learner with hypoacusis uses a tangible system (called TanQuery) for learning relational algebra, both in individual and in face-to-face collaborative settings. The results suggest that the use of the tangible system can place a student with profound hearing loss in equal conditions for learning tasks and promote his/her social integration, but that to fully achieve this the tangible system needs to incorporate advanced features, such as active objects and distribution. [ABSTRACT FROM AUTHOR]

Nurturing twenty-first-century competency is one important agenda in this era, especially in developing collaborative learning and critical thinking skills. Yet, facilitating such a computer-supported collaborative learning (CSCL) environment is challenging. Although several technological platforms from past research studies were developed to support collaborative learning, having a system that comprises a collaboration script, and graph-based workspaces to facilitate explicit externalization of cognitive processes, at the same time, armed with learning analytics to monitor the collaboration and cognitive processes is rare. In this paper, the AppleTree system is presented to illustrate three unique features. Firstly, the AppleTree system is designed with a graph-based workspace to facilitate explicit externalization of knowledge co-constructions and argumentation. Secondly, the system is embedded with a four-phased switch to structure the CSCL process. Thirdly, the system possesses real-time learning analytics, including contribution counts, social network analysis, and the learning artifacts' argumentation structure to promote the development of arguments. An exploratory case study was conducted to examine the design of the AppleTree system in an authentic classroom. Empirical findings showed that the AppleTree system helped regulate effective collaboration and supported learners in developing strong arguments. These results could address the social participation and interaction issues related to collaborative learning and enable the development of students' argumentation skills. The implications of the study to educational technology and the CSCL research field are discussed. [ABSTRACT FROM AUTHOR]

There is increasing recognition of the multimodal representational nature of science discovery practices and the roles of multiple and multimodal representations in students' meaning making in science (Lemke, 1998; Tytler, Prain, Hubber, & Waldrip, 2013; Tang, International Journal of Science Education, 38(13), 2069–2095, 2016). However, research in this area is only starting to explore how these different modal meanings interact (Tytler, Prain, Aranda, Ferguson, & Gorur, 2020) and particularly of the nature of the 'transduction' (Airey & Linder, Journal of Research in Science Teaching: The Official Journal of the National Association for Research in Science Teaching, 46(1), 27–49, 2009) or 're-description' (Lehrer & Schauble, 2013) of one modal representation to another and their coordination in model-based reasoning in science. This paper explores ways in which groups of secondary students orchestrated multimodal representations to gain an understanding of the lever principle in a collaborative learning environment of a Science of Learning Research Classroom. The analysis of video data and student artefacts suggests that mathematical formulations on their own were limited in allowing students to satisfactorily engage with science ideas and that a key feature of cross-modal translation is the flexibility in application of these ideas afforded by the different modes and understanding the nature of these interactions. Using a Peircean socio-semiotic approach (Peirce, 1992, 1998) and Pickering's notion of scientific research involving a 'mangle of practice' (Pickering, 1995, p. 23), this paper argues that a robust understanding of the lever principle necessarily involves students coordinating a range of modal representations, including visual-spatial, manipulative, embodied and abstract mathematical drawing on the distinctive affordances each brings to learning. We also describe the way these representations push back on learners in unexpected ways. [ABSTRACT FROM AUTHOR]

This paper explores orchestration support introduced to an online class to help students operate as a knowledge community. A technological design was introduced to provide a flexible, dynamic learning environment so that ideas and knowledge artifacts can flow across time, space, and people in the community. With support from a CSCL technology named FROG, we incorporated several general-purpose tools to support a variety of collaborative activities and relied on FROG as a backbone to connect these tools and orchestrate knowledge flows among them. Through a mixed-methods case study, we investigated the ways in which the design facilitated the flow of knowledge artifacts and idea development. Detailed analysis of a rich dataset revealed multiple ways in which ideas and artifacts flowed in the community, leading to growth in both individual learning and group projects. However, these phenomena varied across groups. This paper advances the community approach to learning by devising new technological and pedagogical supports. It also highlights the prospect of bringing guidance, control, and agency—long-standing issues of CSCL—into productive dialogues. [ABSTRACT FROM AUTHOR]

This paper focuses on modeling collaborative interaction in Ubiquitous Learning Environment (ULE) based on the assumption that the collaborative interaction can be perceived through interpersonal interactions, which can be described as local dynamic behaviors of the team. In this paper, the collaborative interaction is collected from the experiment with 50 students having 5 members per team. Then the collaborative interaction is coded with 16 participation shift (P-shifts) from 5 different types of turns including turn receiving, turn claiming, turn usurping, turn continuing, and turn noreturning to represent the participation status of each member. Three types of participation statuses used in this paper are the contributor, the target and the unaddressed recipient. Then the discovered local dynamic behavior is used for constructing the model by using agent-based modeling. The model consists of student agents working together according to the discovered behavior. Then, the constructed model is verified by comparing the actual behavior with the simulated behavior. Finally, the comparison result shows that the constructed model can reasonably be the model for modeling collaborative interaction in ULE. [ABSTRACT FROM AUTHOR]

Although research from the Asia-Pacific region has been increasing, much is unknown about research trends, authors, and institutions in the region, especially in relation to learning and instruction. It is important to have an understanding of current research to identify its strengths and weaknesses and to chart future research directions. It is also useful to identify prominent and productive authors and institutions in the Asia-Pacific to enhance international and regional collaboration between researchers. Twelve top international journals from 2002 to 2011 in the fields of educational psychology, educational technology, and learning sciences were examined. New bibliometric measures, such as the q index, as well as co-authorship network analysis, and cluster analysis methods were utilized to provide insights into Asia-Pacific authors and institutions in the field of learning and instruction research. [ABSTRACT FROM AUTHOR]

Team cohesion is critical in driving successful outcomes for teams in collaborative learning settings. It shapes team behaviour, fostering shared perceptions, group synchrony and a common goal-oriented approach. This affinity becomes evident in dynamic interactions, offering insights into team behaviour through interaction data analysis. Interpreting interaction data proves complex, hampering our understanding and insights into shared team perceptions and task cohesion development. This paper used temporal motif analysis to examine the changes in team members' cohesive perceptions and behaviours, including task cohesion, performance outcomes, engagement and group synchrony. Trace data from an online work-integrated learning environment captured learning behaviours, while responses to a questionnaire at different stages of a study program captured task cohesion and cohesive perceptions. The findings reveal teams with strong task cohesion and high performance tend to share similar cohesive perceptions driven by interdependent interactions. Conversely, teams with different cohesion perceptions have lower interaction interdependence and poorer performance. Through analysing team interaction data, this study uncovered key insights to promote positive adjustments aligning team perceptions, enhancing collaborative learning and offering support for improved performance, engagement and synchrony among teams, ultimately benefiting learning outcomes and the cultivation of skills and competencies. [ABSTRACT FROM AUTHOR]

The students' assessment regarding collaborative learning and workgroups is being reported as one of the main concerns in higher education. The increased technological evolution leads to adapting novel self and peer assessment methods to e-assessment. This paper reports the results of a study to evaluate students' opinion about their experience with an e-assessment tool, WebAVALIA, and its assessment criteria. The results indicate that students (N = 359) consider the tool fair, and it increases the productivity regarding work development. Kruskal-Wallis tests show that the students recently considered WebAVALIA fairer and more straightforward. Quickness and anonymity are also identified as tool advantages. [ABSTRACT FROM AUTHOR]

Web annotation environments are widely used in education based on the premise that student interaction in these environments benefits individual and group learning. However, there is little research on factors driving student interaction in web annotation activities. In this study we asked: What dynamics could explain social interaction among students in web annotation activities in college classrooms? Recognizing the mediated nature of social interaction in web annotation, we hypothesized that student interaction is driven by multiple factors including previous relational events and semantic features of annotation content. Following a novel network analysis method named relational event modeling, we analyzed a rich dataset from four online classes. Results indicated annotation popularity was initially predictive of student replies, meaning popular annotation threads were more likely to attract new replies. However, this effect nearly diminished when adding thread-level semantic cohesion to the model, indicating an significant role played by semantic cohesion in attracting new responses. This paper makes important progress towards modeling social interaction in digital environments as a dynamic, mediated phenomenon. This study contributes empirical insights into web annotation and calls for future work to investigate social interaction as a dynamic network phenomenon. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the guest editors discuss various reports within the issue on topics including research on the experiences of learners who engaged with web conferencing, benefits of the combination of game-based learning concepts and collaborative learning, and a competence-based industrial learning approach for the factories of the future.

This paper proposes a Spider Monkey-based neural weight optimization approach for quicker neural synchronization. To exchange the session key across a public channel, two Artificial Neural Networks (ANNs) are synchronized through reciprocating learning. The most crucial feature of ANN coordination is evaluating how effectively sender and receiver's ANNs coordinate without the other's weights. Traditional algorithms have a latency in assessing coordination, which endangers neuronal coordination's confidentiality. This research proposes a collaborative learning technique for analyzing the total synchronization of ANNs efficiently and decisively. The frequency at which the two ANNs got the same outcome in previous iterations determines synchronization. The hash is being used to evaluate if all ANNs are better aligned when a certain threshold is met. The presented technique uses the hash value of the synaptic weights to achieve complete synchronization among two communicating parties. This approach offers a number of benefits, namely (1) the usage of a Spider Monkey-based PRNG optimization to obtain the optimal weight vector. (2) The suggested method, in contrast to earlier methodologies, allows two communicating entities to discover complete collaboration more rapidly. (3) The probability of success is lowered geometrically. (4) The proposed TLTPM coordination periods are significantly quicker than the present CVTPM, VVTPM, and TPM-FPGA approaches. The suggested method improves the security of the neural key exchange protocol. The proposed approach is tested, and the findings reveal that it outperforms similar techniques currently in use. [ABSTRACT FROM AUTHOR]

Federated learning is an emerging paradigm of distributed collaborative machine learning , which allows different data nodes to train together for building a better model. Recently, privacy-preserving federated logistic regression has been widely concerned by academia and industry, which exploits techniques such as secure multi-party computation (MPC), homomorphic encryption (HE), and differential privacy (DP) to train shared model among different data nodes. However, MPC-based schemes could not efficiently handle high-dimensional sparse data and have high communication burden; HE-based schemes have potential information leakage risks and high computational burden; DP-based schemes affect the speed of model convergence and cause a loss of model accuracy. Besides, some of the existing schemes require a trusted third-party (TTP) coordinator, which greatly increases the complexity of training. To address these problems, in this paper, combining the HE and secret sharing (SS), we present a peer-to-peer privacy-preserving vertical federated logistic regression (VFLR) without TTP, which can securely train a shared model over vertically partitioned large-scale data from two data nodes. Moreover, to ensure the security of the training process, the proposed scheme secretly shares model weights between two data nodes, rather than reveals them to both parties during model training. Furthermore, the proposed scheme utilizes the single instruction multiple data (SIMD) and batching to achieve parallel processing and time amortization. Finally, the experimental evaluations demonstrate that the proposed scheme has less training time and better model performance than existing schemes. [ABSTRACT FROM AUTHOR]

This paper presents a novel algorithm to dehaze a given hazy input image using a generative adversarial network (GAN). The proposed GAN structure uses a Feature Residual Dense combined Network (FRDN) as a generator and a Markovian discriminator (PatchGAN) with additional layers as the discriminator. FRDN is capable of extracting contextual information using Feature Module (FM) in conjunction with the Residual Dense Module, and IMCU enhances collaborative learning which enhances its performance. The inclusion of proposed reality and visibility loss functions along with L 1 loss improves the scene visibility and realness of the dehazed image. The network is trained with images from the benchmark datasets—RESIDE and NTIRE 2021. The proposed technique's performance is evaluated using various metrics such as PSNR, SSIM, FSIM, FADE, NIQE, and BRISQUE. An average PSNR of 25.701, 32.52, and 33.96 has been obtained with the Indoor Training Set, Synthetic Objective Testing Set indoor, and SOTS outdoor images, respectively. The experimental results reveal that the suggested method's performance is better compared to other state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Conflicts play an important role to improve group learning effectiveness; they can be decreased, increased, or ignored. Given the sequence of messages of a collaborative group, we are interested in recognizing conflicts (detecting whether a conflict exists or not). This is not an easy task because of different types of natural language ambiguities. A conversation can be represented as a conversation graph; i.e., a direct multidigraph where the nodes are users, and an edge means a message. The approach proposed in this paper focuses on the emotional interactions of group members. Hence, to detect conflicts it analyzes emotions involved in the cycles of the graph. This strategy has the advantages of considering the sentiment of a sequence of messages to take a better decision and analyzing interactions with two or more participants. The proposed approach has been tested in collaborative learning tasks, achieving an F1 score of 92.6%, and a 90.1% recall score for conflicting situations. This approach can help teachers and students to improve the learning process. [ABSTRACT FROM AUTHOR]

Collaborative learning offers numerous benefits to learners, largely due to the dialogue that is unfolding between them. However, there is still much to learn about the structure of collaborative dialogue, and especially little is known about co-creative dialogues during learning. This paper reports on a study with learners engaged in co-creative tasks where the learners wrote code to create a song and while engaging in textual dialogue as they did so. After gathering the textual dialogue and the actions within the interface, we learned a hidden Markov model (HMM) to reveal co-creative states. The seven-state model revealed four states primarily composed of coding actions that included browsing the curriculum documents, working in the code editor, compiling the code successfully, and receiving a compile error. The remaining three states are primarily composed of dialogue that can be characterized as social, aesthetic, and technical dialogue. Next, we analyzed the relationships between the co-creative states revealed by the HMM and students' partner satisfaction scores from a post-survey. The results reveal the relative frequency of actions in certain states and some transitions between states were predictive of partner satisfaction. For example, partner satisfaction was negatively associated with the Compilation Error state and with the relative frequency of transitions from the Curriculum Browsing state to the Code Editing state. Partner satisfaction was also negatively associated with the relative frequency of transitions from the Aesthetic Dialogue state to the Technical Dialogue state and the Code Editing state. This line of investigation reveals how co-creative processes are associated with partner satisfaction, and holds the potential to inform scaffolding for collaborative learning. [ABSTRACT FROM AUTHOR]

Distance learning has been adopted as an alternative learning strategy to the face-to-face teaching methodology. It has been largely implemented by many governments worldwide due to the spread of the COVID-19 pandemic and the implication in enforcing lockdown and social distancing. In emergency situations distance learning is referred to as Emergency Remote Teaching (ERT). Due to this dynamic, sudden shift, and scaling demand in distance learning, many challenges have been accentuated. These include technological adoption, student commitments, parent involvement, and teacher extra burden management, changes in the organization methodology, in addition to government development of new guidelines and regulations to assess, manage, and control the outcomes of distance learning. The objective of this paper is to analyze the alternatives of distance learning and discuss how these alternatives reflect on student academic performance and retention in distance learning education. We first, examine how different stakeholders make use of distance learning to achieve the learning objectives. Then, we evaluate various alternatives and criteria that influence distance learning, we study the correlation between them and extract the best alternatives. The model we propose is a multi-criteria decision-making model that assigns various scores of weights to alternatives, then the best-scored alternative is passed through a recommendation model. Finally, our system proposes customized recommendations to students, and teachers which will lead to enhancing student academic performance. We believe that this study will serve the education system and provides valuable insights and understanding of the use of distance learning and its effectiveness. [ABSTRACT FROM AUTHOR]

Over the last three decades, educational researchers and policymakers have increasingly promoted instructional strategies that centralize group work in mathematics. One difficulty teachers face in implementing group-based instruction in mathematics involves facilitating meaningful group interaction amongst students. In this paper, we explore student noticing as a novel strategy for supporting college students to collaborate effectively during group work in mathematics. First, we construct a noticing framework named student noticing of collaborative practices which provides a lens for "seeing" how students notice their collaborative practices. Then, we use the framework to explore how 25 college students noticed their collaborative practices in mathematics. After working on a novel mathematics task in groups, the college students listened to audiorecordings of their group interactions and responded to reflection questions about the effectiveness of their collaboration. We identified themes regarding how and what students noticed related to their collaborative practices. The findings reveal that students attended to many aspects of their collaboration, including their talking turns and propensity to listen to others. Students demonstrated a desire to change their collaborative practices in the future. The findings imply that teachers and researchers might leverage student noticing as a tool for improvement in mathematics group-based classrooms. [ABSTRACT FROM AUTHOR]

This present study endeavors to discover the scholarly communication structure in the CSCL knowledge domain. To explore the intellectual structure of contemporary literature of CSCL research from 2006 to 2013, over a thousand research papers indexed in the leading journal publications and conference proceedings were retrieved from WOS. Accordingly, this paper adopted a series of methods to analyze these research articles from macro to micro level, including document co-citation analysis (DCA), exploratory factor analysis (EFA), and social network analysis (SNA). As a result, a total of 7,552 and 2,180 co-citation ties were obtained from 403 to 66 source papers, respectively. In addition, six intellectual subfields within the CSCL literature were extracted, namely: (1) representation, discourse & pattern, (2) factors influencing CSCL, (3) intervention and comparison, (4) critical reasoning, (5) process of social construction, and (6) design and modeling of CSCL. Central documents and publications within contemporary CSCL research were identified and presented in the undirected co-citation networks from both macro and micro perspectives. Furthermore, the dissemination of underlying subfields and pivotal documents serving as a boundary-spanning role were discussed. This is the very first attempt to integrate the bibliographical method, statistical analysis, and visualization techniques in relation to contemporary CSCL research. Further discussion and research directions for future CSCL study are provided. [ABSTRACT FROM AUTHOR]

Our 1998 paper 'Encouraging Student Reflection and Articulation using a Learning Companion' (Goodman et al. ) was a stepping stone in the progression of learning companions for intelligent tutoring systems (ITS). A simulated learning companion, acting as a peer in an intelligent tutoring environment ensures the availability of a collaborator and encourages the student to learn collaboratively, while drawing upon the instructional advantages that ITSs provide. This paper is a commentary on our 1998 paper, reflecting on that research and some of the subsequent relevant research by others and us since then in Learning Companions, Intelligent Tutoring Systems, and Collaborative Learning. [ABSTRACT FROM AUTHOR]

The use of Web-based technologies in education and ways they can improve teaching and learning have been the focus of interest in the educational community during the recent years. In this regard, wikis are one of the most promising technologies. Many research studies have been presented that integrate wikis in educational settings. The abundance of the corresponding research work creates the need for a systematic survey. In this survey of the research on wikis in education content analysis is used to record and compare the conclusions of 110 recent empirical studies that used wikis in educational settings. The specific studies were published from 2014 to 2021. The conducted search was not limited to a specific level of education but involved all the corresponding levels of education. The key aspects of the educational use of wikis are outlined and clarified. Furthermore, information and suggestions that will be useful to future researchers, as well as teachers who want to integrate wikis into their teaching practice are provided. To the best of our knowledge, there is no other survey of the research that discusses all such aspects regarding wikis in education. [ABSTRACT FROM AUTHOR]

Unsupervised cross-modality domain adaptation for medical image segmentation has made great progress with the development of adversarial learning-based methods, but the training of adversarial models is considerably complicated. In this paper, we propose a conceptually simple but effective unsupervised domain adaptation method to achieve adaptation on frequency spectrum components of target and source images decomposed by a novel spectrum transfer strategy. Specifically, we replace the high-frequency components of the source domain images with that of the target domain images for details feature adaptation and adjust the low-frequency components by histogram matching for style adaptation. Besides, we propose multi-direction collaborative learning on both target and source domains to further improve the performance. Experimental results demonstrate that our method significantly outperforms state-of-the-art UDA methods for medical image segmentation on two publicly available datasets (cardiac dataset, and abdominal multi-organ dataset) in both CT to MRI and MRI to CT domain adaptation scenarios [ABSTRACT FROM AUTHOR]

Deep learning has made remarkable progress, and deep learning models have been successfully deployed in many practical applications. However, recent studies indicate that deep learning models are vulnerable to adversarial examples generated by adding an imperceptible perturbation. The study of adversarial attacks and defense has attracted substantial interest from researchers due to its high application value. In this paper, a method named AdvAE-GAN is proposed for generating adversarial examples. The proposed method combines (1) explicit perturbation generated by adversarial autoencoder and (2) implicit perturbation generated by generative adversarial network. A more suitable similarity measurement criteria is incorporated into the model to ensure that the generated examples are imperceptible. The proposed model not only is suitable for white-box attacks, but also can be adapted to black-box attacks. Extensive experiments and comparisons with six state-of-the-art methods (FGSM, SDM-FGSM, PGD, MIM, AdvGAN, and AdvGAN++) demonstrate that the adversarial examples generated by AdvAE-GAN result in high attack success rate with good transferability and are more realistic-looking and natural. Our code is available at https://github.com/xzforeverlove/Generating-Adversarial-Examples. [ABSTRACT FROM AUTHOR]

While there is increased interest in using movement and embodiment to support learning due to the rise in theories of embodied cognition and learning, additional work needs to be done to explore how we can make sense of students collectively developing their understanding within a mixed-reality environment. In this paper, we explore embodied communication's individual and collective functions as a way of seeing students' learning through embodiment. We analyze data from a mixed-reality (MR) environment: Science through Technology Enhanced Play (STEP) (Danish et al., International Journal of Computer-Supported Collaborative Learning 15:49–87, 2020), using descriptive statistics and interaction analysis to explore the role of gesture and movement in student classroom activities and their pre-and post-interviews. The results reveal that students appear to develop gestures for representing challenging concepts within the classroom and then use these gestures to help clarify their understanding within the interview context. We further explore how students collectively develop these gestures in the classroom, with a focus on their communicative acts, then provide a list of individual and collective functions that are supported by student gestures and embodiment within the STEP MR environment, and discuss the functions of each act. Finally, we illustrate the value of attending to these gestures for educators and designers interested in supporting embodied learning. [ABSTRACT FROM AUTHOR]