Social Networking Applications Research Articles

Network Dynamic GCN Influence Maximization Algorithm With Leader Fake Labeling Mechanism

Influence maximization is an important technique for its significant value on various social network applications, such as viral marketing, advertisement, and recommendation. Traditional heuristic algorithms for influence maximization suffer from different issues, such as accuracy descent and information loss during network exploration. Besides, recently proposed deep learning-based approaches cannot extract the in-depth structural information of social networks well. In light of these problems, we propose a novel heuristic method called the network dynamic GCN influence maximization algorithm based on the leader fake labeling mechanism. To exploit the in-depth network topology information for the influence maximization task, we design a network dynamic GCN that owns adaptive layer numbers in terms of different network scales to obtain node representations. Then, considering that there are few labels in the network or the labels are irrelevant to the task of influence maximization, we establish a leader fake labeling mechanism to automatically generate node labels that are helpful to seed nodes selecting for model training. Finally, a heuristic method based on the Mahalanobis distance is developed to quickly select influential seed nodes with the learned node representations. Three real-world datasets are used in our experiments, and the experimental results demonstrate that our algorithm has a better performance for seed set identification under the premise of high efficiency compared with some latest heuristic influence maximization algorithms.

Adversarial NLP for Social Network Applications: Attacks, Defenses, and Research Directions

The growing use of media has led to the development of several machine learning (ML) and natural language processing (NLP) tools to process the unprecedented amount of social media content to make actionable decisions. However, these ML and NLP algorithms have been widely shown to be vulnerable to adversarial attacks. These vulnerabilities allow adversaries to launch a diversified set of adversarial attacks on these algorithms in different applications of social media text processing. In this article, we provide a comprehensive review of the main approaches for adversarial attacks and defenses in the context of social media applications with a particular focus on key challenges and future research directions. In detail, we cover literature on six key applications: 1) rumors detection; 2) satires detection; 3) clickbaits and spams identification; 4) hate speech detection; 5) misinformation detection; and 6) sentiment analysis. We then highlight the concurrent and anticipated future research questions and provide recommendations and directions for future work.

The Application of Social Networks in the Marketing

Consumption always acts as one of the most significant links to economics. In recent years, the way of consumption has changed entirely due to the evolution of the internet. A dramatic increase in the number of people who tends to obtain product information online instead of offline. So, is this either an opportunity or a disaster for the business? How should enterprises utilise this new tool in this unprecedented reform? In this article, the author will reveal the following difficulties 1. How the Social Networking change consumers behaviour? 2. What are the differences between some typical social network approaches used for diffusion? 3. How to employ the social network in marketing? By analysing the research of previous essays and the several views of the author. Furthermore, it is to identify to them when is the best chance to use which method and what is the most appropriate to the companies employing different approaches to operate.

The Eigenvalues-Based Entropy and Spectrum of the Directed Cycles

The directed cycles form a foundational structure within a network model. By analyzing the in-degree characteristic polynomial of three kinds of matrices of the directed cycles, the authors obtain the eigenvalues of the adjacency matrix , the Laplacian matrix , and the signless Laplacian matrix . This study investigates the eigenvalues spectrum of these three types of matrices for directed cycles and introduces an eigenvalue-based entropy calculated from the real part of the eigenvalues. The computer simulation reveals interesting characteristics on the spectrum of the signless Laplacian. The concept of eigenvalue-based entropy holds promise for enhancing our understanding of graph neural networks and more applications of social networks.

Motivational Enhancement Interventions to Increase Pre-Exposure Prophylaxis Use in Sexual Minority Men Who Use Stimulants: Protocol for a Pilot Sequential Multiple Assignment Randomized Trial.

Although pre-exposure prophylaxis (PrEP) could substantially mitigate HIV risk, sexual minority men who use stimulants commonly experience difficulties with engaging in PrEP clinical services. Motivational interviewing (MI) and contingency management (CM) reduce substance use and condomless anal sex (CAS) in this population, but these motivational enhancement interventions require modifications to promote engagement along the PrEP care continuum. PrEP Readiness Interventions for Supporting Motivation (PRISM) is a pilot sequential multiple assignment randomized trial testing the feasibility, acceptability, and preliminary effectiveness of distinct combinations of telehealth MI and CM in 70 cisgender sexual minority men who use stimulants that are not currently taking PrEP. A national sample was recruited via social networking applications to complete a baseline assessment and mail-in HIV testing. Those with nonreactive HIV results were randomized to receive either (1) a 2-session MI intervention focusing on PrEP use (session 1) and concomitant stimulant use or CAS (session 2) or (2) a CM intervention with financial incentives for documented evidence of PrEP clinical evaluation by a medical provider (US $50) and filling a PrEP prescription (US $50). At the 3-month follow-up assessment, participants who reported they had not filled a prescription for PrEP were randomized a second time to either (1) switch to a second-stage intervention (ie, MI+CM or CM+MI) or (2) continue with assessments only. Outcomes for both responders and nonresponders were reassessed at a 6-month follow-up. The primary outcome is documented evidence of filling a PrEP prescription over 6 months. Self-reported secondary outcomes include PrEP clinical evaluation by a medical provider, stimulant use, and CAS. Qualitative exit interviews were conducted with a subgroup of responders and nonresponders to characterize their experiences with the MI and CM interventions. Implementation of PRISM underscores challenges in reaching sexual minority men who use stimulants to optimize HIV prevention efforts. Approximately 1 in 10 (104/1060) eligible participants have enrolled. Of the 104 who enrolled, 87 (84%) completed mail-in HIV testing. We delivered 5 preliminary HIV-positive results, including posttest counseling with referrals to confirmatory testing. Lessons learned from PRISM underscore the central importance of a flexible, participant-centered approach to support the engagement of sexual minority men who use stimulants. Leveraging telehealth platforms to deliver motivational enhancement interventions also expanded their reach and potential public health impact with this high-priority population. Further research is needed to determine the effectiveness of telehealth MI and CM for supporting PrEP use in sexual minority men who use stimulants. ClinicalTrials.gov NCT04205487; https://clinicaltrials.gov/study/NCT04205487. DERR1-10.2196/48459.

A novel approach to enhance the quality of health care recommender system using fuzzy-genetic approach

In recent generations of the digital world medical data in Recommender Systems. Health Care Recommender System (HCRS) analyses the medical data and then predicts the user’s or patient’s illness. Nowadays, healthcare data is used by various users or patients in recommendation systems which are useful for everyone. Analysing and predicting medical data provides awareness to users and these data predictions may be enriched using various techniques of RS. Machine learning techniques are used to make sure that health data is reliable and of high quality. In every RS the issues are targeted such as scalability, sparsity and cold start problems. In many social networking applications, these issues are resolved using ML algorithms. However, there is a significant gap between IT systems and medical diagnosis. The fuzzy genetic method is used in HCRS in order to bridge the gap between IT and healthcare applications. Through the use of the mutation and crossover operators, a real-value genetic method is used in this to compute similarity. With the user’s extra personalized information, fuzzy rules are later generated for the database. The Hybrid fuzzy-genetic method, also known as this situation, combines both techniques to improve recommendation quality. Utilizing this method will improve the quality of the recommendation process by discovering the most precise similarity measures among different users. Six factors are subjected to fuzzification, including age, gender, employment, height, weight, and region. Genre-interesting measure weights are then used, including Very Light, Light, Average, Heavy, and Very Heavy. Finally, the evaluation metrics used MAE and RMSE to evaluate the recommendation accuracy which showed the best results in comparison with baseline approaches such as Convolutional Neural Networks and Restricted Boltzman Machine.

VISUAL MEDIA IN SOCIAL MEDIA APPLICATIONS: APPLYING THE UNIFIED THEORY OF ACCEPTANCE AND USE OF TECHNOLOGY TO THE PREFERENCES OF EMIRATI UNIVERSITY STUDENTS: A THEORETICAL APPROACH

The development of the use of means of communication at the present time in the transmission of electronic digital technology of written, audio and visual information that contains speech, sound, numbers, words, charts, music, films and colors, and man has become able to store information and deal with it through smart phone, computer and other multi-use means that allow the transfer of different types of audio and video messages in a secure and identical manner, so that they can be broadcast and received immediately by the recipient, who in turn interacts with them in terms of storing, viewing and disposing of them. The Unified Theory of Acceptance and Use of Technology (UTAUT) is relied upon to understand the mechanism of students' preference and adoption of social networking sites and applications. This theory explains how users accept and use technology based on four factors: performance expectation, effort expectation, social impact, and facilitation conditions. The main objective of this research is to identify the theoretical approaches and previous literature that deals with and indicates the preference of users of social networking sites and the Internet for visual media to access information through Internet applications and smart devices. This study attempts to answer the following question: How does the previous literature explain students' adoption and acceptance of using visual media through social networking applications? In order to explore the effectiveness of the previous results of studying these applications in terms of expected performance, expected effort, expected social impact, and available facilities. Based on the assumptions of the (UTAUT). The research problem is that there is a clear adoption of some applications to the exclusion of others by students in varying proportions, which gives them a set of multiple options to access information according to the technical capabilities available in each application, and this is what gives visual media great importance in terms of the strength of its influence as it contains multimedia. and interactive such as sound, image, text, and animation. This study attempts to answer the following question: How do students explain their adoption and acceptance of using online videos? This is in order to explore the effectiveness of these applications in terms of expected performance, expected effort, expected social impact, and available facilities

Evaluation of Osteoporosis Perception Among Saudi Arabian Premenopausal Women: A Cross-Sectional Survey Study Using the Osteoporosis Knowledge Assessment Tool (OKAT).

Osteoporosis is a major clinical problem that affects the whole population, especially women. It is a condition that is becoming more prevalent with aging. The increase in bone fragility associated with the disease can lead to fractures, even from minor trauma. Our goal is to evaluate the extent of knowledge about osteoporosis and perceptions of it among premenopausal women in Saudi Arabia. This descriptive cross-sectional study was conducted among premenopausal women during the months of June and July 2021. We distributed an online questionnaire on social networking sites and applications that Saudi women use on a daily basis. We used the Osteoporosis Knowledge Assessment Tool (OKAT) to evaluate the responses. A total of 661 women took part in our study; 159 of them were excluded because they had either reached the menopausal period or had already been diagnosed with the disease. The overall perception of osteoporosis is noticeably poor, as only 55% of respondents had an acceptable level of knowledge. In addition, we found a statistically significant association between education level and knowledge level (p-value = 0.044). The findings revealed that more than half the participants scored "acceptable" in terms of their understanding of the disease, which indicates a serious awareness gap. This outcome demonstrates the necessity of increasing community awareness about osteoporosis to reduce potential harm and the financial burden of healthcare.

The Effects of Trust, Flow, and Critical Mass on Continuous Usage Intention of Mobile Social Networking Applications

Türkiye’de mobil sosyal ağ uygulamalarının sürekli kullanım niyetleri öncüllerinin incelenmesi hakkındaki araştırmalara çok az ilgi gösterilmiştir. Bu nedenle, bu çalışmanın temel amacı, güven, akış deneyimi ve kritik yoğunluğu değişkenlerinin sürekli kullanım niyeti üzerindeki etkisini inceleyerek bu boşluğu doldurmaktır. Çalışmada anket yöntemiyle 424 katılımcıdan toplanan veriler analiz edilmiştir. Sonuçlar hem yaygınlığın hem de güvenin, kullanıcıların sürekli kullanım niyetlerini belirleyen akış deneyimlerini etkilediğini göstermektedir. Ayrıca araştırma bulguları, güven ve kritik yoğunluğun sürekli kullanım niyeti üzerinde önemli etkileri olduğunu göstermiştir. Bu çalışmanın sonuçları mobil sosyal ağ uygulamalarının yöneticilerine ve pazarlamacılarına kullanıcıların sürekli kullanım niyetini anlamak için güven, akış deneyimi ve kritik yoğunluk hakkında güçlü bilgiler sağlayabilmektedir.

Enhancing students’ learning experience using social networking applications: evidence from a random experiment

ABSTRACT During the COVID-19 quarantine, we conducted a field-setting pre/post-test randomized experiment (n = 115), creating a community using the social media application Instagram to enhance students’ interactions with their peers and immediate physical environments in a large, introductory online course in environmental psychology. We used the framework of the community of inquiry (CoI) to explain the ecological effects of this project. After posting photos and interacting with others on Instagram weekly for 8 weeks, student participants reported a significantly greater social presence and cognitive presence. Furthermore, participants reported higher levels of course satisfaction and performed better on the preliminary exams than non-participants, but this does not seem attributable to the intervention itself. We discuss the issues of self-selection bias, attrition bias, and compliance bias in this study arguing that greater social presence increased the cognitive presence, as mediated by meaningful peer interactions. Our findings provide additional evidence on the value of using social media in educational settings on learning experiences and for building communities to connect students with their peers and physical environments. We also explore the implementation of a pedagogical approach to context-based learning via mobile technologies, and how the CoI framework can be used in evaluating online learning environments.

Preferences for long-acting pre-exposure prophylaxis among gay, bisexual and other men who have sex with men in Taiwan: findings from the 2021 HEART Survey.

While various antiretrovirals have been studied as potential candidates for long-acting pre-exposure prophylaxis (PrEP), the bimonthly injectable cabotegravir-the first long-acting form of PrEP-was approved in 2021. Event-driven (ED) PrEP has been the most prevalent dosing regimen among gay, bisexual and other men who have sex with men (GBMSM) in Taiwan, providing a unique setting to observe the preferences for long-acting PrEP in a community where the daily regimen is not the mainstream method. This study aimed to determine the preferences for the different forms and dosing intervals of long-acting PrEP that are currently in the development pipeline. We conducted a survey in 2021 by convenience sampling the users of social networking applications for GBMSM in Taiwan. Our survey included questions on sexual behaviours, current PrEP regimens and the preferences for potential candidates of long-acting PrEP, such as implants, intramuscular and subcutaneous injections. We compared the Likert-scale preference ratings for potential long-acting options, and conducted logistic regression analysis to examine the factors associated with a preference for bimonthly intramuscular injections (2M IM) over ED and daily PrEP regimens, respectively. A total of 1728 responses were eligible for analysis. Three percent of respondents (n = 52) were daily PrEP users; 11.5% (n = 198) were ED PrEP users. When not considering cost, current PrEP users-regardless of their original dosing regimen-were most likely to express preferences for monthly oral PrEP, followed by a 6-month subcutaneous injectable (6M SC) and 2M IM. However, among non-current PrEP users, monthly oral PrEP was the most preferred form, followed by ED, daily oral and 6M SC injectable. Multivariable logistic regression revealed that current daily users, those willing to take PrEP in the next 6 months and those with more sex partners in the last 12 months had a significant correlation with preferences for the 2M IM injectable over the ED PrEP. The monthly oral form was the most preferable long-acting PrEP among GBMSM in Taiwan. Current daily PrEP users preferred the 2M IM injectable over the ED PrEP, which made the 2M IM injectable a potential alternative. Further studies should focus on how the cost and delivery affect PrEP preferences and their actual uptake.

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

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

The Influence of Social Media on Developing English Reading Skills of Saudi Universities Students

Social media has definitely become an integral part of our lives especially among university students. This technology has a wide impressive effect on how people learn and communicate with each other. However, the application of social media to learning especially for English department Saudi university students, is not fully explored. Therefore, the current study aims at mapping whether social media affects students’ reading competence positively or negatively. The study also seeks to find out if there are any significant differences in the students’ competence in reading as a result of using social media with NBU students due to gender, social media, reading skills and geographical distribution. The current study used quantitative methods using a survey instrument to gather descriptive data regarding the perceptions of (n=900) randomly chosen Saudi university students. Questionnaires with Likert scale questions were used in the study. The questionnaire was divided into two main parts. The first part began with two general questions about the number of years by which social media was used to perform general tasks and to perform specific English tasks. The second part was concerned with attitudes towards using social media, impact that social media has on reading competence. The data was analyzed using the Statistical Package for Social Sciences (SPSS) to obtain accurate results. Analysis of the collected data showed that the majority of the participants believed strongly in the pedagogical values and benefits of using social media as an ELT tool in their classrooms especially in improving reading skills. The findings also indicate that social networking websites and applications (e.g.Facebook, Youtube , Twitter, Skype) have a positive impact on learning English as a foreign language.

Современные цифровые средства коммуникации и их влияние на построение личных отношений

The article examines a new sociological problem related to the role and place of remote information and communication technologies (ICT), digital means of communication in interpersonal relations, their impact on the individual and changes in society as a whole. The object of the study is interpersonal relations implemented through the use of digital technologies and mobile devices. The analysis of the conceptual provisions of mod-ern theories of society on the prerequisites and causes of the transformation of interpersonal relationships and the phenomenon of intimacy in the transition and wide distribution of communication through mobile devices is presented. New digital forms of interpersonal communication such as online dating, ghosting are character-ized. The use of ICT, especially mobile devices (gadgets) and the transition of online dating to a mobile plane with the help of various digital applications in social networks, has led to disappearance of the boundary be-tween real and virtual space is becoming much more blurred, and the level of certainty in the environment is decreasing in social space and in personal relationships for both the initiator and the recipient of communica-tion. The easiness to contact with potential romantic partners breeds a lower commitment to maintaining the relationship. If in the real world there are always doubts, then the Internet space offers an infinite number of partners who are definitely open to acquaintances and communication. Therefore, the rupture of digital rela-tions occurs without explanation, simply interrupting communication, there is no need for efforts to end the rela-tionship. Conclusion dwells upon the fact that, despite the obvious advantages of using modern ICT in every-day life, the simplicity and lightning speed of establishing contact, the multiplicity of choices lead to psychologi-cal strain, to the problem of long-term preservation of close relations between partners. A sense of loneliness among people in the modern world arises and grows, posing a threat to the society’s well-being as a whole.

Generating real-world hypergraphs via deep generative models

Hypergraph generation has found wide applications in data analysis, social networks, and communication networks. Although various hypergraph generation methods have been proposed, many challenges remain. On the one hand, traditional hypergraph generation methods are time-consuming since they rely on computing various statistics about hypergraph distributions prior to generation. On the other hand, they store many intermediate variables in the process of hypergraph generation, thus depleting a large number of memory resources, which could lead to memory explosion. To address these issues, we present a novel deep generative model for hypergraph generation (DGMH), which consists of a node selection module and a hyperedge size decision module. In DGMH, each hyperedge is treated as an embedding in a high-dimensional space, where values along specific dimensions represent the probabilities of node inclusion in the hyperedge. The node selection module captures the distribution of hyperedge embeddings and identifies other latent hyperedge embeddings within the space. In addition, the hyperedge size decision module determines the hyperedge size based on the hyperedge embedding. We sample a certain number of nodes from the categorical distribution parameterized by the embedding and assign these nodes to the hyperedge, an essential step in hyperedge generation. Once a sufficient number of hyperedges are generated, they are connected through common nodes to form a complete hypergraph. Experimental results demonstrate the effectiveness of DGMH in capturing the structural distribution of hypergraphs in a short time while maintaining a modest memory footprint during the generation process.

The role of social media marketing and social support in developing value co-creation intentions: a Couchsurfing community perspective

Purpose This study aims to empirically investigate the pathway to value co-creation intentions through social media marketing, social support and COVID-19 perception in the tourism context with a specific focus on Couchsurfing community. Design/methodology/approach A survey was conducted from foreign and domestic travellers who used Couchsurfing platform for their recent travel, and were approached using an online survey (n = 229) and structural equation modelling used for hypothesis testing. Findings The findings indicate that value co-creation intentions follow a pathway through social media marketing and social support. Moreover, Couchsurfing community social support mechanisms play a crucial role in value co-creation intentions. Originality/value This study significantly contributes by taking Couchsurfing as a social networking application that provides both informational and functional support to the hardcore and active tourism and hospitality community.

The Detection of Fake News in Arabic Tweets Using Deep Learning

Fake news has been around for a long time, but the rise of social networking applications over recent years has rapidly increased the growth of fake news among individuals. The absence of adequate procedures to combat fake news has aggravated the problem. Consequently, fake news negatively impacts various aspects of life (economical, social, and political). Many individuals rely on Twitter as a news source, especially in the Arab region. Mostly, individuals are reading and sharing regardless of the truth behind the news. Identifying fake news manually on these open platforms would be challenging as they allow anyone to build networks and publish the news in real time. Therefore, creating an automatic system for recognizing news credibility on social networks relying on artificial intelligence techniques, including machine learning and deep learning, has attracted the attention of researchers. Using deep learning methods has shown promising results in recognizing fake news written in English. Limited work has been conducted in the area of news credibility recognition for the Arabic language. This work proposes a deep learning-based model to detect fake news on Twitter. The proposed model utilizes the news content and social context of the user who participated in the news dissemination. In seeking an effective detection model for fake news, we performed extensive experiments using two deep learning algorithms with varying word embedding models. The experiments were evaluated using a self-created dataset. The experimental results revealed that the MARBERT with the convolutional neural network (CNN) model scores a superior performance in terms of accuracy and an F1-score of 0.956. This finding proves that the proposed model accurately detects fake news in Arabic Tweets relating to various topics.

Business model with the application of social networks in rural Msmes of the Chone Canton, the year 2022

Business model with the application of social networks in rural Msmes of the Chone Canton, the year 2022

Social Media & Music Videos: Ethics Impact on Grade 6 Students

The purpose of this study was to determine the impact of the tik-tok application on students' communication ethics in an elementary school located in Sidoarjo Regency. The approach used in this research is qualitative with the type of case study research. The subjects in this study were high school students at SDN Kalisampurno 1 Tanggulangin. Based on the results of the study, it was concluded that the use of the tik-tok application had a positive impact on students being more daring to admit when they made mistakes and being responsible, and excessive ones could have a negative impact on students' communication ethics. This can be seen from the results of research which shows that there are still many students who do not meet the indicators of good communication ethics in behaving in school.
 Highlights:
 
 The study examines the impact of the TikTok application on communication ethics of elementary school students in Sidoarjo Regency.
 The research follows a qualitative approach, specifically a case study design.
 Findings suggest that TikTok has both positive and negative effects on students' communication ethics, with some students demonstrating good ethics while others fall short.
 
 
 
 
 
 Keywords: TikTok application, Communication ethics, Elementary school students, Sidoarjo Regency, Qualitative research
 
 
 

Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams

Online POI recommendation strives to recommend future visitable places to users over time. It is crucial to improve the user experience of location-based social networking applications (e.g., Google Maps, Yelp). While numerous studies focus on capturing user visit preferences, geo-human interactions are ignored. However, users make visit decisions based on the status of geospatial contexts. In the meantime, such visits will change the status of geospatial contexts. Therefore, disregarding such geo-human interactions in streams will result in inferior recommendation performance. To fill this gap, in this paper, we propose a novel deep interactive reinforcement learning framework to model geo-human interactions. Specifically, this framework has two main parts: the representation module and the imitation module. The purpose of the representation module is to capture geo-human interactions and convert them into embedding vectors (state). The imitation module is a reinforced agent whose job is to imitate user visit behavior by recommending next-visit POI (action) based on the state. Imitation performance is regarded as a reward signal to optimize the whole interactive framework. When the model converges, the imitation module can precisely perceive users and geospatial contexts to provide accurate POI recommendations. Finally, we conduct extensive experiments to validate the superiority of our framework.