Social Learning Network Research Articles

The Complexities of Using Digital Social Networks in Teaching and Learning

The aim of this investigation was to gain a broad sense of the implementation of digital social networks for teaching and learning by instructors in higher education. We were particularly interested in examples of instructors' use of digital social networks in their courses, the benefits and challenges of specific platforms for teaching and learning purposes, and the perceived role of digital social networks in teaching and learning during the first years of the COVID-19 pandemic. The participants in this investigation (n=336) were faculty and graduate students. Data was collected via an electronic questionnaire with closed and open-ended questions using Qualtrics. The quantitative analysis included descriptive statistics. The data analysis also included qualitative data analysis of textual responses provided to various questionnaire items. The results illustrate the ways in which instructors successfully apply or integrate digital social networks into teaching and learning, broadly and with specific digital social networks. Yet, the findings also highlight several complexities that instructors have experienced when considering digital social networks in their teaching practices such as data privacy issues, misinformation, user interface issues, and the willingness of students to use less trendy digital networks, among other challenges.

Cross-platform language learning: A spatial perspective on narratives of language learning across digital platforms

In the current reality of digital activity, individuals often explore more than one digital platform for language learning. Despite increasing research on the uses of digital platforms for language learning in informal contexts, the cross-platform experience remains in need of elucidation. Drawing on spatial perspectives on digital technology and language learning to conceptualize digital platforms as digital spaces, this study examines the cross-platform experiences of two international students studying English in Australia based on narrative data collected from journal entries, stimulated recall interviews, and social media posts. A narrative approach to the analysis reveals precisely how they organized a variety of digital resources and learning opportunities in online gaming, searching, media-sharing, social networking, and language learning spaces. The learners strategically orchestrated this particular range of digital spaces in alignment with personal interest and need. In accordance with the specific affordances of technological features in these spaces, they created a shared space of interaction in which learning occurred across geographically remote, networked individuals through multimodal language practices. The narrative approach is seen to add analytical power to the issue of space in the sphere of informal digital language learning, in which unique learning pathways for navigating diverse digital spaces are important.

Predicting Learning Interactions in Social Learning Networks: A Deep Learning Enabled Approach

We consider the problem of predicting link formation in Social Learning Networks (SLN), a type of social network that forms when people learn from one another through structured interactions. While link prediction has been studied for general types of social networks, the evolution of SLNs over their lifetimes coupled with their dependence on which topics are being discussed presents new challenges for this type of network. To address these challenges, we develop a series of autonomous link prediction methodologies that utilize spatial and time-evolving network architectures to pass network state between space and time periods, and that models over three types of SLN features updated in each period: neighborhood-based (e.g., resource allocation), path-based (e.g., shortest path), and post-based (e.g., topic similarity). Through evaluation on six real-world datasets from Massive Open Online Course (MOOC) discussion forums and from Purdue University, we find that our method obtains substantial improvements over Bayesian models, linear classifiers, and graph neural networks, with AUCs typically above 0.91 and reaching 0.99 depending on the dataset. Our feature importance analysis shows that while neighborhood and path-based features contribute the most to the results, post-based features add additional information that may not always be relevant for link prediction. The code and four of the datasets used in this work are available at https://github.com/Jess-jpg-txt/sln-learning.

Algorithm-mediated social learning in online social networks.

Human social learning is increasingly occurring on online social platforms, such as Twitter, Facebook, and TikTok. On these platforms, algorithms exploit existing social-learning biases (i.e., towards prestigious, ingroup, moral, and emotional information, or 'PRIME' information) to sustain users' attention and maximize engagement. Here, we synthesize emerging insights into 'algorithm-mediated social learning' and propose a framework that examines its consequences in terms of functional misalignment. We suggest that, when social-learning biases are exploited by algorithms, PRIME information becomes amplified via human-algorithm interactions in the digital social environment in ways that cause social misperceptions and conflict, and spread misinformation. We discuss solutions for reducing functional misalignment, including algorithms promoting bounded diversification and increasing transparency of algorithmic amplification.

The Impact of Mobile-Assisted Social Language Learning Activities on Speaking Skills and Self-Efficacy Development

In traditional English as a foreign language (EFL)-speaking classes, students have insufficient time and opportunities to practice [1]. In addition, they lack cultural and communicative contexts [2] to improve their speaking skills. Furthermore, a large number of students, especially in Asian countries, have low self-efficacy with regard to their English speaking competence and try to avoid any activities that require speaking in public [3]. In this study, we designed social language learning (SLL) activities to bridge the abovementioned gaps and developed a mobile-assisted social language learning system to support students' participation in SLL activities. We explored how our SLL activities affect language learners' speaking performance and self-efficacy and investigated their social language learning networks and perceived acceptance of the mobile-assisted SLL system. Fifty-eight graduate students were recruited for the study and randomly divided into two groups: a control group in which students completed assigned tasks using the traditional method and an experimental group in which students completed assigned tasks using the mobile SLL system. Our results showed that while the speaking skills of students in the two groups improved after the study, the learning gains of the experimental students in EFL fluency, lexis, pronunciation, and content were significantly better than those of the control students. The experimental students significantly outperformed their counterparts on the dimension of culturality, authenticity, and abundance of created verbal content. The self-efficacy of the experimental students was much better than that of the control students. The results also showed that the interaction degree of the experimental students improved, and they positively perceived applications of the mobile-assisted SLL system to EFL learning. Based on the results, several suggestions and precautions were proposed for educators and researchers in the field to consider.

Dissonance minimization and conversation in social networks

We are examining social learning in networks, where agents aim to minimize cognitive dissonance resulting from disagreement by adjusting their statements in conversations to align with those of their associates, rather than truthfully sharing their beliefs. Our analysis investigates the impact of this adjustment, known as audience tuning, on belief revision, limiting beliefs, consensus conditions, and convergence speed. Our findings demonstrate that audience tuning facilitates extensive belief propagation beyond immediate associates, resulting in faster convergence in most of the societies considered. It also leads to a redistribution of influences on long-run beliefs, favoring agents with lower dissonance sensitivity. We also show that endogenous changes in the network, driven by dissonance minimization, can impede society from reaching a consensus.

The Effectiveness of Flipped Learning Using the Social Network "Edmodo" (SNE) on Media ‎Writing (MW) and Emotional Intelligence (EI) Skills among 8th Grade Female Students

The purpose of this research is to investigate the effectiveness ‎of flipped learning using (SNE) has on (MW) and (EI) skills ‎among female eighth-grader students. In a quasi-experimental ‎study, two groups of 71 girls from a public elementary school ‎in Northern Gaza were formed. Each group completed a well-‎built pre- and post-test for their proficiency (MW) and (EI) ‎skills. As a result of the study, it was found that the students in ‎the experimental group had significantly more MW than the ‎students in the control group.. A comparison of the pre-post ‎scores for the (MW) and (EI) instruments showed a significant ‎improvement of students’ performance. The post scores for the ‎‎(MW) and (EI) instruments showed a significant difference ‎between students in the control group and experimental group. ‎It was concluded that integrating flipped learning with (SNE) ‎improved students' (EI) capacity, and developed their of (MW) ‎skills.‎ ‎(Keywords: Edmodo, Emotional intelligence skills, Flipped ‎Learning, Media writing, Sschool students' skills, Social ‎learning network)‎

Tuberculosis case finding in a public healthcare setting in South Africa: using QI worksheets and a social network learning platform for rapid data-driven improvement

Abstract Background The Coronavirus 2019 (COVID-19) pandemic diverted attention and resources away from tuberculosis (TB) and other non-COVID services and decreased clinic attendance. Objective The objective was to rapidly restore TB case finding to pre-pandemic levels using a data-driven, quality improvement (QI) approach, adapted to constraints of the pandemic. Method A mixed-methods assessment of a QI intervention in 129 health facilities from five rural health districts in KwaZulu-Natal province was performed. Eight worksheets guided clinical teams, using QI principles, to improve routine data quality and implement preselected change ideas for TB case finding in Human Immunodefiency Virus-positive clinic subpopulations. Facility teams shared data and learnings and were coached in person and via a social media platform and virtual encounters. Results We observed high rates of engagement by district TB managers and facility teams (94% of facilities posted worksheets on WhatsApp each month). The number of worksheets posted, TB investigations undertaken, and TB cases confirmed increased rapidly over time. Facility data quality improved significantly over time (median 40% errors at start vs 5% errors at end). Conclusion The Sprint initiative showed that a novel simplified QI intervention that integrated clinical protocols and data tracking was rapidly adopted and improved TB case finding despite the constraints of the COVID-19 pandemic. Two key innovations—a simplified set of data-focused QI worksheets and a social engagement and learning platform—were used to drive a focused QI effort. The approach should be considered for improving gaps in focused health system priorities in low- and middle-income country settings beyond the pandemic.

The Role of Social Media in Academic Motivation and Engagement: A Case Study of Undergraduate Students in Vitenam

This study examines the impact of social media on academic motivation and engagement among undergraduate students in Vietnam. Regression analysis reveals that motivation, engagement, and study habits influence students’ use of social networks for learning. Motivation shows a positive and significant relationship with media use, supporting previous research emphasizing its role in academic success. Social media platforms facilitate peer connections, information sharing, and participation in discussions, enhancing student motivation. Engagement also exhibits a positive association with social media use, highlighting its importance in leveraging these platforms for learning. Furthermore, study habits demonstrate a positive link with social media use, indicating that effective habits contribute to academic success and the utilization of social media for educational purposes. Importantly, this study does not find evidence of negative effects associated with social networks, although they can distract from academic pursuits when used non-academically. These findings underscore the significance of motivation, engagement, and study habits in effectively harnessing social networks for educational purposes, providing insights for educational practitioners and policymakers in promoting positive technology integration in learning environments.

Dynamic Opinion Aggregation: Long-Run Stability and Disagreement

Abstract This article proposes a model of non-Bayesian social learning in networks that accounts for heuristics and biases in opinion aggregation. The updating rules are represented by non-linear opinion aggregators from which we extract two extreme networks capturing strong and weak links. We provide graph-theoretic conditions for these networks that characterize opinions’ convergence, consensus formation, and efficient or biased information aggregation. Under these updating rules, agents may ignore some of their neighbours’ opinions, reducing the number of effective connections and inducing long-run disagreement for finite populations. For the wisdom of the crowd in large populations, we highlight a trade-off between how connected the society is and the non-linearity of the opinion aggregator. Our framework bridges several models and phenomena in the non-Bayesian social learning literature, thereby providing a unifying approach to the field.

CLGT: A Graph Transformer for Student Performance Prediction in Collaborative Learning

Modeling and predicting the performance of students in collaborative learning paradigms is an important task. Most of the research presented in literature regarding collaborative learning focuses on the discussion forums and social learning networks. There are only a few works that investigate how students interact with each other in team projects and how such interactions affect their academic performance. In order to bridge this gap, we choose a software engineering course as the study subject. The students who participate in a software engineering course are required to team up and complete a software project together. In this work, we construct an interaction graph based on the activities of students grouped in various teams. Based on this student interaction graph, we present an extended graph transformer framework for collaborative learning (CLGT) for evaluating and predicting the performance of students. Moreover, the proposed CLGT contains an interpretation module that explains the prediction results and visualizes the student interaction patterns. The experimental results confirm that the proposed CLGT outperforms the baseline models in terms of performing predictions based on the real-world datasets. Moreover, the proposed CLGT differentiates the students with poor performance in the collaborative learning paradigm and gives teachers early warnings, so that appropriate assistance can be provided.

A fusion recommendation model based on mutual information and attention learning in heterogeneous social networks

Heterogeneous social networks generate vast amounts of data due to their large user base. In response, recommendation systems have been developed as an effective tool to mitigate the problem of information overload. Nonetheless, standalone recommendation methods are often limited by their own inherent deficiencies. Consequently, deep learning has emerged as a powerful approach to address these issues. By integrating diverse recommendation methods, the shortcomings of individual methods can be partially compensated for and improved recommendation outcomes can be achieved. This paper presents a novel user interest fusion recommendation model called MIAL, which leverages mutual information and attention-based learning mechanisms. Specifically, a user’s posts are first transformed into word sequences via a Convolution Neural Network (CNN) based interest recommendation model for pre-processing. To enhance the multi-label prediction model, this study adopts a label selection method based on the label maximum mutual information spanning tree (LMMIST) to determine the final recommended label set. To identify reliable user similarity, the concept of pseudo-similar friends is introduced to construct heterogeneous networks. During the network embedding phase, a new random walk algorithm termed MRWalk and a pseudo-similar propagation mechanism are proposed. Experimental results using the Twitter dataset and public Amazon product dataset demonstrate that the proposed MIAL algorithm outperforms various state-of-the-art algorithms. The comparative analysis shows that MIAL has significantly improved performance.

TVET SI: Evaluating Boundary Crossing Social Learning in Vocational Education and Training: A value creation approach

This article focuses on the development and application of an evaluation model and approach for evaluating boundary crossing social learning in a Vocational Education and Training (VET) learning network in South Africa, with an emphasis on a Training of Trainers (ToT) course that helped to catalyse and strengthen this learning network via two iterations of the course over an eight-year period. The article shares how we adapted the value creation framework (VCF) of Wenger, Traynor and De Laat (2011; Wenger & Wenger-Traynor, 2020) in the evaluation of a VET Training of Trainers (ToT) programme and learning network that focussed on the uptake and circulation of rainwater harvesting and conservation (RWH&C) knowledge in a particular formal and informal VET context in the Eastern Cape, South Africa, where smallholder farmers were struggling to find water for producing food. The evaluated ToT course was catalytic in establishing a boundary crossing social learning network approach in a VET context that linked formal and informal VET (Lotz-Sisitka et al., 2016; Lotz-Sisitka et al., 2022; Pesanayi, 2019); hence we found it important to develop adequate tools for its evaluation. The focus of this article is to share how we developed an evaluation approach to this work. We share insights on the indicators developed for diff erent types of value created, and also insights gained into the use of this evaluation approach in a boundary crossing VET social learning project that took a ToT course as focus. In short, evaluation findings show that the boundary crossing ToT course off ers strong immediate, potential and applied value that can lead to realised and reframed value, especially if supported by ongoing learning network activities that follow the initial engagement in the boundary crossing ToT course. Th is leads, over time, to transformative value which is important in achieving the overall objective of such social learning, namely making knowledge more co-engaging, accessible and useful in the context where improved food security via better use of rainwater harvesting and conservation amongst smallholder farmers and household food producers is a necessary form of sustainable development. Orientation value, and enabling value were found to be vital for the emergence of other kinds of value. The evaluation model also allows for the lifting out of strategic value which points to wider uptake potential. All this creates the possibility for indicator development that can help inform iterative development of boundary crossing VET courses used to stimulate the co-construction of learning networks and ongoing social learning for sustainable development.
 Keywords: Vocational Education and Training, evaluation, social learning, value creation framework

TVET SI: Evaluating Boundary Crossing Social Learning in Vocational Education and Training: A value creation approach

This article focuses on the development and application of an evaluation model and approach for evaluating boundary crossing social learning in a Vocational Education and Training (VET) learning network in South Africa, with an emphasis on a Training of Trainers (ToT) course that helped to catalyse and strengthen this learning network via two iterations of the course over an eight-year period. The article shares how we adapted the value creation framework (VCF) of Wenger, Traynor and De Laat (2011; Wenger & Wenger-Traynor, 2020) in the evaluation of a VET Training of Trainers (ToT) programme and learning network that focussed on the uptake and circulation of rainwater harvesting and conservation (RWH&C) knowledge in a particular formal and informal VET context in the Eastern Cape, South Africa, where smallholder farmers were struggling to find water for producing food. The evaluated ToT course was catalytic in establishing a boundary crossing social learning network approach in a VET context that linked formal and informal VET (Lotz-Sisitka et al., 2016; Lotz-Sisitka et al., 2022; Pesanayi, 2019); hence we found it important to develop adequate tools for its evaluation. The focus of this article is to share how we developed an evaluation approach to this work. We share insights on the indicators developed for diff erent types of value created, and also insights gained into the use of this evaluation approach in a boundary crossing VET social learning project that took a ToT course as focus. In short, evaluation findings show that the boundary crossing ToT course off ers strong immediate, potential and applied value that can lead to realised and reframed value, especially if supported by ongoing learning network activities that follow the initial engagement in the boundary crossing ToT course. Th is leads, over time, to transformative value which is important in achieving the overall objective of such social learning, namely making knowledge more co-engaging, accessible and useful in the context where improved food security via better use of rainwater harvesting and conservation amongst smallholder farmers and household food producers is a necessary form of sustainable development. Orientation value, and enabling value were found to be vital for the emergence of other kinds of value. The evaluation model also allows for the lifting out of strategic value which points to wider uptake potential. All this creates the possibility for indicator development that can help inform iterative development of boundary crossing VET courses used to stimulate the co-construction of learning networks and ongoing social learning for sustainable development.
 Keywords: Vocational Education and Training, evaluation, social learning, value creation framework

Peningkatan Penggunaan Social Learning Network Bagi Siswa-Siswi SMP Negeri 2 Syamtalira Aron Kab. Aceh Utara

Today the development of the internet is increasing rapidly and has penetrated into several fields, including the field of education. Learning media also develops and creates a Social Learning Network. Edmodo is an online learning medium that combines several Learning Management Systems and Social Network features into a Social Learning Network specifically made for educational purposes. To obtain an effective learning process, teachers and students must have innovative and interesting learning media, this is what is experienced by SMP Negeri 2 Syamtalira Aron North Aceh Regency. Teachers of SMP Negeri 2 Syamtalira Aron North Aceh Regency have carried out training on increasing the use of Edmodo learning media, but students still have not used social network-based learning media. This is the background for the service team to provide training on "Increasing the Use of Social Learning Network for Students of SMP Negeri 2 Syamtalira Aron North Aceh Regency ". This activity was held at the Syamtalira Aron 2 Public Middle School Computer Lab using lecture methods and hands-on practice. The participants of this training were 30 people, all of whom were students of SMP 2 Syamtalira Aron North Aceh Regency. The activity lasts for one day with a duration of four hours. Through this activity, it is hoped that the participant's skills and understanding will increase regarding the use of the Edmodo learning social network

Positive public opinion guidance model based on dual learning in social network

Internet public opinion is closely related to our life in social network. The wanton growth of some negative public opinions has an extremely serious impact on the social stability and national security. After the guidance of government manually, some negative public opinion is well controlled and people’s life gain more positive energy. How to use Internet technology to automatically and promptly guide public opinion events and reduce the harm to society is currently challenging research. Therefore, in this paper, we propose a positive public opinion guidance model based on dual learning for negative Internet public opinion, hereinafter denoted to as the dual-PPOG model. Firstly, we use the Fast Unfolding algorithm to divide social networks into the public opinion guidance communities. In these communities, we detect the positive opinion guider and negative opinion receiver by our defined PageRank (PR) variant. Secondly, inspired by dual learning, we construct the public opinion guidance model and evaluate whether the guidance is successful through the feedback signal. Through the repeated guidance of the positive opinion guider to the negative opinion receiver, the public opinion guidance is successful. This is the main process for the dual positive public opinion mechanism. Finally, we guide the remaining nodes based on the opinion dynamics. The experiment demonstrates beneficial effects of our proposed model of dual-PPOG. Experimental results on three real-world datasets intercepted from Twitter, E-mail and Facebook show that the model of dual-PPOG can capture useful information in the network topology. Compared with the methods of HK, AE, Random and AIA on the three datasets from small to large in scale, the percentage of positive opinion increased by 4%, 6.9%, and 2.7% respectively, which shows our approach achieve significant improvements and effectiveness compared to all baselines.

Image semantic learning method based on social heterogeneous graph networks1

Image semantic learning techniques are crucial for image understanding and classification. In social networks, image data is widely disseminated thanks to convenient acquisition and intuitive expression characteristics. However, due to the freedom of users to publish information, the image has apparent context dependence and semantic fuzziness, which brings difficulties to image representation learning. Fortunately, social attributes such as hashtags carry rich semantic relations, which can be conducive to understanding the meaning of images. Therefore, this paper proposes a new method named Social Heterogeneous Graph Networks (SHGN) for image semantic learning in social networks. First, a heterogeneous graph is built to expand image semantic relations by social attributes. Then the consistent semantic space is reconstructed through cross-media feature alignment. Finally, an image semantic extended learning network is designed to capture and integrate the social semantics and visual feature, which obtains a rich semantic representation of images from a social context. The experiments demonstrate that SHGN can achieve efficient image representation, and favorably against many baseline algorithms.

Misinformation due to asymmetric information sharing

On social media platforms, true and false information compete. Importantly, some messages travel much further than others, even if they concern the same topic. This fact is not reflected in models of social learning (or opinion formation) in networks. Our model fills this gap by allowing different types of information to have different decay factors and to be shared with different networks of people, incorporating asymmetries in sharing behaviors. More “shareable” information then dominates in the long run. This yields a substantial probability of misinformation, in contrast to the special case of symmetry covered by the literature. Asymptotic learning requires a perfect balance between two types of asymmetry: the product of decay factor and largest eigenvalue in the respective signal sharing networks must coincide. Approaching this balance reduces the speed of convergence and enables social learning in the shorter term. Our analysis thus suggests that policy makers, who do not know the true state, aim to mitigate asymmetries in signal sharing, e.g. by weakening echo chambers or by fostering the shareability of cumbersome, boring messages.

Board Interlock Tenure and Firm Internationalization

ABSTRACTTo overcome liabilities of foreignness and outsidership during internationalization, board interlock is an effective conduit of foreign knowledge inflows and organizational learning that firms require. We focus on the time dimension of such influence and hypothesize that the tenure of board interlocks with firms with experience in outward foreign direct investment (OFDI) in a country promotes the OFDI decision of the focal firm to that particular country. However, such an effect diminishes as the tenure of interlock ties increases. Moreover, as an alternative knowledge source, OFDI knowledge from the focal firm's neighboring region may weaken the baseline effect. Based on longitudinal data of listed firms in China, our empirical results support the hypotheses. This study enriches the literature on social network learning by identifying its temporal nature and the substitution between different knowledge sources. It also demonstrates the importance of rotating a firm's board members, so that knowledge acquisition and learning remain fresh.

Partial Information Sharing Over Social Learning Networks

This work addresses the problem of sharing partial information within social learning strategies. In social learning, agents solve a distributed multiple hypothesis testing problem by performing two operations at each instant: first, agents incorporate information from private observations to form their beliefs over a set of hypotheses; second, agents combine the entirety of their beliefs locally among neighbors. Within a sufficiently informative environment and as long as the connectivity of the network allows information to diffuse across agents, these algorithms enable agents to learn the true hypothesis. Instead of sharing the entirety of their beliefs, this work considers the case in which agents will only share their beliefs regarding one hypothesis of interest, with the purpose of evaluating its validity, and draws conditions under which this policy does not affect truth learning. We propose two approaches for sharing partial information, depending on whether agents behave in a self-aware manner or not. The results show how different learning regimes arise, depending on the approach employed and on the inherent characteristics of the inference problem. Furthermore, the analysis interestingly points to the possibility of deceiving the network, as long as the evaluated hypothesis of interest is close enough to the truth.