Social Networking Applications Research Articles

Musculoskeletal Pain Among School Teachers in Qassim, Saudi Arabia: Prevalence, Pattern, and Its Risk Factors.

Introduction Work-related musculoskeletal disorders (WMSD) are defined as conditions that the environment contributes significantly to / worsens due to work conditions. WMSD comes second in the source of disability in both developed and developing countries. The aim of this study is to measure the prevalence, patterns, and risk factors of musculoskeletal pain disorders among teachers in the Qassim region, Saudi Arabia.MethodsA cross-sectional study was conducted among school teachers in the Qassim region, Saudi Arabia. A validated online Arabic questionnaire was distributed among teachers living in the Qassim region through multiple social networking applications like Facebook, WhatsApp, and Telegram. The questionnaire consisted of Socio-demographic characteristics, the Nordic Musculoskeletal Questionnaire, and a modified version of the Örebro Musculoskeletal Pain Screening questionnaire.ResultsA total of 503 school teachers were recruited. The proportion of musculoskeletal pain was 91%, and the most common site of pain was back (74.4%), followed by the shoulder (57.5%) and leg (51.5%). The proportion of disabling pain was (80.1%) while the rest was non-disabling pain (19.9%). In the multiple regression model, the predictors of increased disabling pain were back pain, leg pain, neck pain, and those with 51-70 kg weight. In comparison, the predictors of decreased disabling pain were having more than 7 hours of sleep and those with 20-30 classes per week.ConclusionMusculoskeletal pain disorders were widely prevalent among school teachers in the Qassim region, Saudi Arabia. Most teachers considered pain as disabling, which negatively affected their attendance. The back, shoulder, and neck were the most painful sites associated with disabling pain.

Friend's recommendation on social media using different algorithms of machine learning

Friends Recommendation System identifies the behavior of users found in the dataset like user having number of followers, number of followings, common friends between followers and followings and provides the friend suggestions for the users they can follow. Recommendation system can also be used in other areas like recommending webpages to users in searching engines like Google, Explorer, Microsoft Edge. Recommending music in wynk, video recommendation in you tube, movie recommendation in amazon prime, recommendation of products to purchase in e-commerce applications like Flipkart, Amazon. Machine learning is used for providing recommendation on social networking application like Facebook, Instagram, Twitter Etc., In this Paper, recommendation of friends is done for Facebook. Similarity Coefficient calculations can be done using Jaccard Distance, Cosine Distance. Ranking Measures are done using Page Rank. Measuring the F1-Score and comparing the accuracy of different machine learning algorithms. These helps in finding which algorithm is more accurate in providing friends recommendations in social media recommendation system.

Deep associative learning approach for bio-medical sentiment analysis utilizing unsupervised representation from large-scale patients' narratives.

Owing to the quick spread of minute health-related experiences, the distillation of knowledge from such unstructured narratives is an extremely challenging task. In spite of the success of neural networks methods in improving learning structural reliability, they result in inadequate accuracy of the bio-medical sentiment classification when employing less useful features sets. Therefore, they lack discriminatory potential. In this study, we propose to add a deep associative memory into neural networks for an effective sentiment decomposition, which emphasizes correctly on bio-medical entities related to the extraction of different data-object properties, and contextual-semantics dependencies for a given aspect. The underlying trust of these measures is behind the ability to compute the completion of unseen medical patterns, where comprehensive bio-medical distributed representations are used for representing the formal medical connections from PubMed databases. Experiments on a biomedical sentiment analysis task show that the model provides comprehensive embeddings with meaningful medical patterns. It achieved an average performance of 87% on varied large online datasets. It also outperforms baselines in discovering and identifying medical natural concepts. We provide meaningful support to bio-medical sentiment analysis applications in social networks. Indeed, the facets of this study might be used in many health concerns such as analyzing change in health status or unexpected situations.

Improving Business Pages Recommendation in Social Network Using Link Prediction Methods

Recently Social Network has become one of the favorite means for a modern society to perform social interaction and exchange information via the internet. Link prediction is a common problem that has broad application in such social networks, ranging from predicting unobserved interaction to recommending related items. In this paper, we investigate link recommendations over business pages on Facebook Social Network. More specifically, given a company in thenetwork, we want to recommend potential companies to connect with. We start by introducing existing work in link recommendations and some link prediction models as our baseline. We then talk about the Graph Neural Network model SEAL to make a link recommendations in the network. Our results show that SEAL outperformed the compared baseline model while reaching above 94% Area Under Curve accuracy in link recommendations.

Network Sampling Designs for Relational Classification

Relational classification has been extensively studied recently due to its applications in social, biological, technological, and information networks. Much of the work in relational learning has focused on analyzing input data that comprise a single network. Although machine learning researchers have considered the issue of how to sample training and test sets from the input network (for evaluation), the mechanisms which are used to construct the input networks have largely been ignored. In most cases, the input network has itself been sampled from a larger target network (e.g., Facebook) and often the researcher is unaware of how the input network was constructed or what impact that may have on evaluation of the relational models. Since the goal in evaluating relational classification algorithms is to accurately assess their performance on the larger target network, it is critical to understand what impact the initial sampling method may have on our estimates of classification accuracy.In this paper, we present different sampling methods and systematically study their impact on evaluation of relational classification. Our results indicate that the choice of sampling method can impact classification performance, and thus consequently affects the accuracy of evaluation.

Exploring the Social Networks' Use in the Health-Care Industry: A Multi-Level Analysis.

The application of social networks in the health domain has become increasingly prevalent. They are web-based technologies which bring together a group of people and health-care providers having in common health-related interests, who share text, image, video and audio contents and interact with each other. This explains the increasing amount of attention paid to this topic by researchers who have investigated a variety of issues dealing with the specific applications in the health-care industry. The aim of this study is to systematize this fragmented body of literature, and provide a comprehensive and multi-level overview of the studies that has been carried out to date on social network uses in healthcare, taking into account the great level of diversity that characterizes this industry. To this end, we conduct a scoping review enabling to identify the major research streams, whose aggregate knowledge are discussed according to three levels of analysis that reflect the viewpoints of the major actors using social networks for health-care purposes, i.e., governments, health-care providers (including health-care organizations and professionals) and social networks’ users (including ill patients and general public). We conclude by proposing directions for future research.

PSYCHOLOGICAL IMPACT OF COVID-19PANDEMIC ON PATIENTS WITH OBSESSIVE-COMPULSIVE DISORDER

Introduction: Obsessive-compulsive disorder is characterized by persistent irrational thoughts manifested by repeated actions. These disorders often have an impact on the social life of those who suffer from them, with a tendency towards isolation which can be exacerbated during this period of confinement. Among these disorders, the fear of contamination is very common. This fear is influenced by culture, society, and global health issues. Thus, in 1920, many cases of fear of syphilis emerged following major awareness campaigns pertaining to the disease. In the 1980s, obsessive disorders related to the risk of HIV infection appeared. Likewise, the Covid-19 coronavirus epidemic is likely to cause a significant deal of anxiety for some people with obsessive-compulsive disorder, thus justifying the aggravation of the clinical condition of this category of patients. The hand-washing recommendations that were promoted during the pandemic would prove to be a major trigger for obsessive-compulsive disorder. Quickly, this gesture becomes an obsession and gradually as the virus spreads, experts expect the cases of associated obsessive-compulsive disorders to increase [1]. Closeness between family members and disrupted habits during confinement can lead to conflict, which can increase the frequency of compulsions. Meditation can also increase the flow of uncontrolled thoughts which can promote the emergence of obsessions. During this time of the pandemic, doctors and people with obsessive-compulsive disorders find themselves in a dilemma. On the one hand, to treat obsessive-compulsive disorders, hand washing is prohibited, and on the other hand, to prevent the spread of the virus, hand washing is strongly recommended. Covid-19 can therefore be an unbearable nightmare, and harder to manage for people with obsessive-compulsive disorders. Objective: This study aims to assess the psychological repercussions of confinement on patients suffering from obsessive-compulsive disorders during the Covid-19 pandemic, and to underline the link between the aggravation of the symptoms of obsessive-compulsive disorder and the underlying perceived stress associated with it. Methodology: This is a descriptive and analytical study, which involves a sample of patients tracked for obsessive-compulsive disorders, and which is founded on collecting their individual information through an anonymous survey, which was submitted via social networks, either by using smartphones or during consultations. As an assessment instrument, in addition to the survey for collecting socio-demographic data, we opted for the Yale-Brown Scale to assess the severity of the symptoms of obsessive-compulsive disorder, as well as the Cohen Perceived Stress Scale (PSS-10) to assess the perceived stress on this group of patients during this pandemic. These scales were chosen because of their frequent use in several studies on the same topic. Results:We collected 102 responses, of which 55% were women 39% of our candidates worked remotely and only 38.8% of patients were able to continue their medical follow-up at the hospital during the confinement. Concerningour results,it was observed that our participants experienced significant changes in terms of the severity of the total symptoms of obsessive-compulsive disorder during the period of confinement with an accentuation of 90% of the symptoms of contamination and 53.8% of the hands washing compulsions during the Covid-19 pandemic. Respondents, who had symptoms of obsessive-compulsive disorder, since the onset of Covid-19, were the only ones who were significantly more likely to be vulnerable to moderately high stress. Likewise, respondents who compulsively washed their hands were significantly more likely to experience vulnerability to moderate to high stress. 45.3% of our applicants were extremely anxious, 33% were very anxious, and 21.7% were anguished to a tolerable level, with a rate of 75.5% of patients developing a social handicap or an inability to function. The sample showed that subjects who could not work or study from a remote position during the quarantine, those who lived with a relative in the same house during the quarantine, and those who showed symptoms of contamination, had significantly greater aggravation of the obsessive-compulsive disorder total symptoms during the confinement. Effects were not significant for other variables including gender, use of online social network sites and applications during the quarantine and remission status on obsessive-compulsive disorder symptoms before quarantine. Conclusion: Our results suggest that the stressful period of the pandemic is associated with a significant worsening of symptoms on patients with obsessive-compulsive disorder, particularly on those with contamination obsessions and washing compulsions. Having obsessive-compulsive disorder would increase the likelihood of experiencing significant stress during this pandemic.

RELATIONSHIP BETWEEN ONLINE SOCIAL NETWORKING SITES & APPLICATIONS AND UNIVERSITY STUDENTS’ ACHIEVEMENT

Purpose of the study: This study analysed the relationship between Online Social Networking websites and Applications (OSNSA) and university students' academic achievement.
 Methodology: In the present research, a quantitative research design was followed, and a survey research type of descriptive research was used in this study. Data were collected from 150 university students using a modified version of The Online Social Networking Sites scale (Paul, Baker, & Cochran, 2012). The correlation was calculated by using the SPSS 22nd version.
 Main Findings: The findings revealed a connection between students' time spent on OSNSA and their academic outcomes. The time spent on OSNSA was observed to be strongly influenced by the attention span of the students. In particular, we find that a lower academic output is provided by the greater time spent on OSNSA. Also, attention span was strongly associated with features that influence students' academic success, such as their perceptions of society's social networking outlook, their advantages, and disadvantages of OSNSA, use of OSNSA, etc.
 Applications of this study: Many students spend most of their hours on online networking pages, like Facebook, Tok-Tok, and WhatsApp, which are the most common, considering the harmful impact of social media. In certain eyes, social media has embedded a detrimental effect, but it is also used to acquire vital knowledge and social skills for pupils.
 Novelty/Originality of this study: This research is different from other studies because it explores the relationship between social networking sites & the application and academic performance of university students belonging from South Punjab by exploring various facets of OSNSA which ultimately promote university students’ academic performance.

Partners' Consensus About Joint Effort and COVID-19 Prevention Among Sexual Minority Men.

The current study examined the relevance of relationship functioning to partners’ agreement or consensus about joint effort surrounding COVID-19 prevention. Interdependence theory has been widely used to understand how relationship partners influence health behavior, including how sexual minority male (SMM) couples regulate HIV risk. Couples with better relationship functioning tend to be more successful at negotiating joint (shared) goals and subsequently accomplishing them. The study recruited 134 cis-male, SARS-CoV-2 negative adults in relationships with cis-male partners from phone-based social networking applications. Participants completed an online survey assessing relationship functioning (Perceived Relationship Components Questionnaire), COVID-19 prevention behaviors, and risk perceptions. Partners’ consensus around joint COVID-19 prevention effort was assessed using an adapted version of the Preferences for Sexual Health Outcomes scale. Path analyses indicated that consensus for joint prevention effort predicted social distancing (B = 0.23; p = .001) and the number of other COVID-19 prevention behaviors engaged in (B = 0.17; p = .003) above and beyond perceived risk and relationship functioning. Relationship satisfaction predicted higher levels of consensus for joint COVID-19 prevention effort (B = 0.40; p = .029). Findings suggest that the theoretical foundations of successful HIV prevention interventions that utilize joint goal formation may generalize to the prediction of COVID-19 prevention behavior and may be leveraged to mitigate the risk of SARS-CoV-2 infection among SMM in relationships. Interventions that overlook the potential for dyadic regulation of health behavior may miss opportunities to capitalize on shared coping resources and fail to address relational barriers to prevention.

Perception of Healthcare Providers About the Use of Social Media to Manage a Healthy Diet in Saudi Arabia.

Purpose: The objective of this study is to investigate the perceptions of healthcare providers about the use of social media for healthy diet management in Saudi Arabia.Participants and Methods: A cross-sectional study was designed to investigate the use of social media healthy diet management. The sample constituted 308 healthcare professionals from Saudi Arabia. The social media application, WhatsApp is employed to distribute the questionnaire, which has achieved a response rate of 50.61%. Out of the total participants, 55% of the participants were under 30 years of age, 71% were females, and 55% of the participants had a bachelor's degree.Results: Among the total respondents, 66% used social networking applications more than four hours a day, and 78% utilized social media to get information about a healthy diet. The respondents employed the following platforms for this purpose: Instagram (27%), YouTube (19%), Snapchat (19%), WhatsApp (18%), Twitter (8%), and Facebook (5%). The respondents considered that social media is very helpful to educate (44%), communicate with specialists (33%), and get applications for a healthy diet (38%). They held an opinion that social media is very helpful in improving knowledge about a healthy diet (47%), creating diet awareness (42%), and achieving healthy diet outcomes (37%) and lifestyle (37%).Conclusion: According to the perception of health providers, social media can be used to promote healthy diet management in Saudi Arabia. Also, the growing use of social media in Saudi Arabia represents the potential to create programs that encourage and promote healthy eating habits in the Kingdom of Saudi Arabia. Instagram, YouTube, Snapchat, and WhatsApp platforms can be used for this purpose.

Application of Large-Scale Cognitive Social Networks Based on Cooperative Transmission Mechanisms in Exploration of Flipped Classroom Teaching Strategy

With the deepening of the research on flipped classroom teaching theory, the flipped classroom teaching model has gradually been applied to classroom teaching at all levels and types of schools, and some beneficial results and experiences have been obtained. Due to the relatively low self-learning ability and motivation level of students, in the implementation of flipped classrooms, the quality of preclass self-study links is difficult to guarantee, resulting in unsatisfactory results of flipped classroom teaching in secondary vocational schools. This article aims to solve the current dilemma faced by the optimization of the flipped classroom teaching mode of programming courses by studying the course platform based on the flipped classroom teaching model. The source-destination node distribution is constructed with a model based on node affinity to restore the actual network node distribution architecture. The change in the distribution of source-destination nodes has led to different degrees of aggregation in the overall data flow of the network. After that, the capacity and delay performance of the primary network and the secondary network will change as the degree of data flow aggregation changes. By laying base stations in the main network, we reanalyzed the network. Through the comprehensive analysis of students’ learning status through the scores of students in class and the test situation after class, we modify the specific teaching plan of flipped classroom. Experiments have proved that the in-class flipping model we proposed effectively avoids the inherent shortcomings of students who are not strong in autonomous learning before class, solves the problem that secondary vocational students cannot do well in autonomous learning before class, and improves students to a certain extent. The results show that the flipped classroom teaching model in class can provide more powerful value for vocational teaching to achieve this goal.

Considerations on creating conversational agents for multiple environments and users

AbstractAdvances in artificial intelligence algorithms and expansion of straightforward cloud‐based platforms have enabled the adoption of conversational assistants by both, medium and large companies, to facilitate interaction between clients and employees. The interactions are possible through the use of ubiquitous devices (e.g., Amazon Echo, Apple HomePod, Google Nest), virtual assistants (e.g., Apple Siri, Google Assistant, Samsung Bixby, or Microsoft Cortana), chat windows on the corporate website, or social network applications (e.g. Facebook Messenger, Telegram, Slack, WeChat).Creating a useful, personalized conversational agent that is also robust and popular is nonetheless challenging work. It requires picking the right algorithm, framework, and/or communication channel, but perhaps more importantly, consideration of the specific task, user needs, environment, available training data, budget, and a thoughtful design.In this paper, we will consider the elements necessary to create a conversational agent for different types of users, environments, and tasks. The elements will account for the limited amount of data available for specific tasks within a company and for non‐English languages. We are confident that we can provide a useful resource for the new practitioner developing an agent. We can point out novice problems/traps to avoid, create consciousness that the development of the technology is achievable despite comprehensive and significant challenges, and raise awareness about different ethical issues that may be associated with this technology. We have compiled our experience with deploying conversational systems for daily use in multicultural, multilingual, and intergenerational settings. Additionally, we will give insight on how to scale the proposed solutions.

Adaptation of Academic Success Inventory Scale for College Students to Turkish: Validity and Reliability Study

The approach that “One can not manage without measuring” has brought up the idea that intangible concepts should also be measured into the agenda. Measurement of intangible concepts, in other words defining them in numerical terms is quite difficult and different methods are proposed for measurement of these concepts. Measuring academic success is also considered in this context. In national literature, academic success is generally considered as class passing grade or graduation grade. However, the expression of academic success with the grades taken from the exams does not fully reflect the fact. Because other factors affecting the grades obtained from exams are ignored. Therefore, it is considered that there is a need for a scale that will help both advisors and students and to measure academic success more clearly. With the Turkish adaptation of the Academic Success Inventory for College Students (ASICS), which was developed by Prevatt et al. (2011) to fill this gap in national literature with the aim to measure the academic success of university students as being used successfully in many countries, validity and reliability study has been done. The data were collected by convenience sampling method from university students studying in Mersin between the dates June 18 and July 18, 2020. The survey was created with Google Form and the survey link was shared with the social communication network application. Data analysis was done with R programming language, and SPSS and AMOS sofwares. Explanatory and confirmatory factor analysis were used in the analyses. Cronbach’s alpha value of the total scale is 0.937. The values of goodness of fit in the 1st level multifactorial structure were calculated as RMSEA: 0.075, CFI: 0.998, TLI: 0.978, NFI: 0.988 and χ2/df: 2.220. Calculated values are compatible with reference values. It was evaluated that Academic Success Inventory Scale could also be used in Turkey and more accurate results could be obtained on academic success.

ВПРОВАДЖЕННЯ СОЦІАЛЬНИХ МЕРЕЖ У РОБОТУ ФАХІВЦЯ ФІТНЕС ІНДУСТРІЇ

The article deals with the issue of implementation of social networks into the work of a specialist in fitness industry. The need to improve the work of a specialist in fitness industry via modern means of communication including social networks (Facebook, Instagram) has been substantiated. The analysis of academic references proved that the issue of implementation of social networks into the work of a specialist in fitness industry has not been extensively studied by native and foreign researchers and has not been sufficiently researched in pedagogical theory. The aim of the research is to theoretically substantiate the issue of application of social networks in professional activities of specialists in fitness industry and to experimentally check the efficiency of their implementation. Based on the aim set, th following the basic tasks have been formulated: to reveal the state of development of the issue of social networks implementation into the work of specialists in fitness industry in pedagogical theory and practice; to experimentally check the efficiency of implementation of social networks into the work of specialists in fitness industry on the grounds of “Evolution” sports club, Khmelnytskyi. Based on the aim and tasks set, the efficiency of implementation of social networks in the work of a specialist in fitness industry had to be checked. Research and experimental work was done on the grounds of “Evolution” sports club, Khmelnytskyi, and Khmelnytskyi National University. 32 respondents took part in the experimental work at various stages. The results of the research prove that implementation of social networks has positive influence on the increase of the number of clients of instructors in fitness clubs. The give research does not settle all aspects of the researched issue. The perspectives for further research are the following: theoretical and methodological substantiation of peculiarities of professional activity of specialists in fitness industry based on both native and foreign experience; revealing the pedagogical bases of quality assurance for professional training of specialists in fitness industry; substantiation of the theoretical and methodological bases of the professional development of specialists in fitness industry within then system of continuous education.

AI-Based Analysis of Policies and Images for Privacy-Conscious Content Sharing

Thanks to the popularity of personal mobile devices, more and more of the different types of private content, such as images and videos, are shared on social networking applications. While content sharing may be an effective practice to enhance social relationships, it is also a source of relevant privacy issues. Unfortunately, users find it difficult to understanding the terms and implications of the privacy policies of apps and services. Moreover, taking privacy decisions about content sharing on social networks is cumbersome and prone to errors that could determine privacy leaks. In this paper, we propose two techniques aimed at supporting the user in taking privacy choices about sharing personal content online. Our techniques are based on machine learning and natural language processing to analyze privacy policies, and on computer vision to assist the user in the privacy-conscious sharing of multimedia content. Experiments with real-world data show the potential of our solutions. We also present ongoing work on a system prototype and chatbot for natural language user assistance.

Adversarial Linear Contextual Bandits with Graph-Structured Side Observations

This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: contexts and side observations. In this setting, a learning agent repeatedly chooses from a set of K actions after being presented with a d-dimensional context vector. The agent not only incurs and observes the loss of the chosen action, but also observes the losses of its neighboring actions in the observation structures, which are encoded as a series of feedback graphs. This setting models a variety of applications in social networks, where both contexts and graph-structured side observations are available. Two efficient algorithms are developed based on EXP3. Under mild conditions, our analysis shows that for undirected feedback graphs the first algorithm, EXP3-LGC-U, achieves a sub-linear regret with respect to the time horizon and the average independence number of the feedback graphs. A slightly weaker result is presented for the directed graph setting as well. The second algorithm, EXP3-LGC-IX, is developed for a special class of problems, for which the regret is the same for both directed as well as undirected feedback graphs. Numerical tests corroborate the efficiency of proposed algorithms.

Mining Textual and Imagery Instagram Data during the COVID-19 Pandemic

Instagram is perhaps the most rapidly gaining in popularity of photo and video sharing social networking applications. It has been widely adopted by both end-users and organizations, posting their personal experiences or expressing their opinion during significant events and periods of crises, such as the ongoing COVID-19 pandemic and the search for effective vaccine treatment. We identify the three major companies involved in vaccine research and extract their Instagram posts, after vaccination has started, as well as users’ reception using respective hashtags, constructing the datasets. Statistical differences regarding the companies are initially presented, on textual, as well as visual features, i.e., image classification by transfer learning. Appropriate preprocessing of English language posts and content analysis is subsequently performed, by automatically annotating the posts as one of four intent classes, thus facilitating the training of nine classifiers for a potential application capable of predicting user’s intent. By designing and carrying out a controlled experiment we validate that the resulted algorithms’ accuracy ranking is significant, identifying the two best performing algorithms; this is further improved by ensemble techniques. Finally, polarity analysis on users’ posts, leveraging a convolutional neural network, reveals a rather neutral to negative sentiment, with highly polarized user posts’ distributions.

Do social capital and networks facilitate community participation?

PurposeThe purpose of this paper is to find theoretical and practical linkages between social capital, network and community participation. The study examines the role of popular social capital and its forms in shaping community participation under the influence of socioeconomic status of individuals.Design/methodology/approachThe paper uses household survey data (N = 135) from select north Indian villages to assess the role of social capital and individuals’ networks (measured through their network size) in participation. The participation is measured in terms of attendance and vocal participation.FindingsThe study finds significant evidence that the networks do not play a uniform role in collective participation. The elitist form of social capital exists in the community which can leverage the networks to their benefit, whereas many people, despite large network size, cannot actively participate. Social capital and networks are not entirely conducive for collective participation and favours a few in the community. Additionally, networks do facilitate information flow but do not help in achieving active engagement. Hence, the peer effect is not truly reflected in vocal participation all the time, especially in local governance context.Research limitations/implicationsThe conclusion of the study is based on small sample size from seven villages. Nonetheless, in light of the supporting literature available, it provides useful insights and triggers important questions that need microscopic analysis under the macroscopic umbrella of social capital.Practical implicationsOn policy fronts, takeaway from this paper can be used for policy and law formulation for lower strata of the society such as labour law formulation and labour behavioural practices in community participation.Social implicationsThe research findings can be utilized for the emerging applications of social networks in understanding local governance and community engagement in developing societies.Originality/valueThis research has used a novel field experiment conducted by one of the authors himself. The empirical assessment of social capital and networks in local governance can be replicated elsewhere to study participation in other societies as well. In terms of policy, the research underscores the need of using social capital notion while assessing the community engagement in local governance.

Analyzing the Coevolution of Mobile Application Diffusion and Social Network: A Multi-Agent Model.

The successful diffusion of mobile applications in user groups can establish a good image for enterprises, gain a good reputation, fight for market share, and create commercial profits. Thus, it is of great significance for the successful diffusion of mobile applications to study mobile application diffusion and social network coevolution. Firstly, combined with a social network’s dynamic change characteristics in real life, a mobile application users’ social network evolution mechanism was designed. Then, a multi-agent model of the coevolution of a social network and mobile application innovation diffusion was constructed. Finally, the impact of mobile applications’ value perception revenue, use cost, marketing promotion investment, and the number of seed users on the coevolution of social network and mobile application diffusion were analyzed. The results show that factors such as the network structure, the perceived value income, the cost of use, the marketing promotion investment, and the number of seed users have an important impact on mobile application diffusion.

Reducing Cumulative Errors of Incremental CP Decomposition in Dynamic Online Social Networks

CANDECOMP/PARAFAC (CP) decomposition is widely used in various online social network (OSN) applications. However, it is inefficient when dealing with massive and incremental data. Some incremental CP decomposition (ICP) methods have been proposed to improve the efficiency and process evolving data, by updating decomposition results according to the newly added data. The ICP methods are efficient, but inaccurate because of serious error accumulation caused by approximation in the incremental updating. To promote the wide use of ICP, we strive to reduce its cumulative errors while keeping high efficiency. We first differentiate all possible errors in ICP into two types: the cumulative reconstruction error and the prediction error. Next, we formulate two optimization problems for reducing the two errors. Then, we propose several restarting strategies to address the two problems. Finally, we test the effectiveness in three typical dynamic OSN applications. To the best of our knowledge, this is the first work on reducing the cumulative errors of the ICP methods in dynamic OSNs.