Online Social Networks Research Articles

Distributed privacy preservation for online social network using flexible clustering and whale optimization algorithm

Distributed privacy preservation for online social network using flexible clustering and whale optimization algorithm

Deepfakes: current and future trends

Advances in Deep Learning (DL), Big Data and image processing have facilitated online disinformation spreading through Deepfakes. This entails severe threats including public opinion manipulation, geopolitical tensions, chaos in financial markets, scams, defamation and identity theft among others. Therefore, it is imperative to develop techniques to prevent, detect, and stop the spreading of deepfake content. Along these lines, the goal of this paper is to present a big picture perspective of the deepfake paradigm, by reviewing current and future trends. First, a compact summary of DL techniques used for deepfakes is presented. Then, a review of the fight between generation and detection techniques is elaborated. Moreover, we delve into the potential that new technologies, such as distributed ledgers and blockchain, can offer with regard to cybersecurity and the fight against digital deception. Two scenarios of application, including online social networks engineering attacks and Internet of Things, are reviewed where main insights and open challenges are tackled. Finally, future trends and research lines are discussed, pointing out potential key agents and technologies.

Multidimensional political polarization in online social networks

Political polarization in online social platforms is a rapidly growing phenomenon worldwide. Despite their relevance to modern-day politics, the structure and dynamics of polarized states in digital spaces are still poorly understood. We analyze the community structure of a two-layer, interconnected network of French Twitter users, where one layer contains members of Parliament and the other one regular users. We obtain an optimal representation of the network in a four-dimensional political opinion space by combining network embedding methods and political survey data. We find structurally cohesive groups sharing common political attitudes and relate them to the political party landscape in France. The distribution of opinions of professional politicians is narrower than that of regular users, indicating the presence of more extreme attitudes in the general population. We find that politically extreme communities interact less with other groups as compared to more centrist groups. We apply an empirically tested social influence model to the two-layer network to pinpoint interaction mechanisms that can describe the political polarization seen in data, particularly for centrist groups. Our results shed light on the social behaviors that drive digital platforms towards polarization and uncover an informative multidimensional space to assess political attitudes online. Published by the American Physical Society 2024

An institutional approach to analyze the multi-level policymaking system of online social networks: a case study of Iran

PurposeThis study aims to elucidate institutional analysis as an effective approach to investigating and designing the multilevel policymaking system of online social networks (OSN) for achieving a participatory model.Design/methodology/approachThe institutional mapping approach has been used to analyze Iran’s OSN multilevel policymaking system. A combination of two matrices, including institutions-institutions and institutions-functions, was used to perform the institutional mapping. Two main steps were taken to draw the mentioned matrices. First, a review of related studies in Iran’s OSN policymaking system was conducted and the policy functions mentioned in these studies were identified and categorized using the meta-synthesis. Second, based on analyzing two policy documents of Iran’s OSN, institutions and their interactions were identified and policy functions were allocated to institutions.FindingsBased on the results, the most important policy functions in the current OSN policymaking system in Iran are support, regulatory, monitoring and evaluation, business environment development, culture building and promotion, organizing licenses and permissions, policymaking and legislation. Also, the results show that there are shortcomings in this system, some of the most important of which are lack of transparency in regulatory, little work in culture building and promotion, neglect of the training of specialized human resources and research and development, slow development of the business environment and neglecting the role of nongovernmental organizations in policymaking.Originality/valueBy examining and analyzing how different institutions operate within a multilevel policymaking system, the policymaking process and its overall effectiveness can be enhanced. This analysis helps identify any inconsistencies, overlaps or conflicts in the roles and policies of these institutions, leading to a better understanding of how a multilevel policymaking system is organized.

Social Media Marketing's Effect on Small and Medium-Sized Businesses' Performance

Social media is increasingly being included into the marketing plans of many micro and small enterprises as a useful tool for connecting with a sizable collection of prospective buyers in ways that enable individuals to impart knowledge in a natural conversation. Despite the fact that historically, marketers have put all of their efforts into getting the best possible placement in the market. The best chance for micro and small enterprises may arise in this area as individuals may begin to view social media platforms as their primary source of all information over time. The purpose of this paper is to comprehend how well internet media works to promote shopping websites that have an impact on consumer purchasing decisions. With the rise in popularity of Websites like ‘Twitter’, ‘Facebook’, ‘LinkedIn’, and ‘YouTube’, Social Media Marketing has grown increasingly widespread. Marketing carried out on social media platforms or online social networking sites is referred to as social media marketing. The majority of businesses and organisations have their own websites; however, it might be challenging to reach individuals who are unaware of the organisation. As a result, many businesses have found it beneficial to have online profiles on sites. The goal of this study is to develop practical recommendations and offer strategic insights to help consumer brands use social media more effectively. In addition, it was discovered that social media platforms and the businesses themselves played a significant role in affecting engagement levels, suggesting that there is no single recipe for successful social media management.

Privacy preserving using joint 2 K-means clustering and coati optimization algorithm for online social networks

Privacy preserving using joint 2 K-means clustering and coati optimization algorithm for online social networks

Is Taylor Swift leading a new Pop revolution? A cross-generation analysis of Pop/Rock cover songs

Background (Pop/Rock is experiencing deep transformations caused by the emergence of Web 2.0 and the online social networks, streaming services and the proliferation of TV contests. Cover songs afford the opportunity to explore how these changes would result in a new revalorization of Pop and Dance music. The aim of this paper is to find evidence of a changing pattern in cover songs by 21st-century artists. To this end, over 76,000 covers performed by artists who grew up in the 2000s were quantitatively analyzed. Methods SecondHandSongs.com was crawled to extract the cover relationships, and Allmusic.com to obtain the genre and starting decade of each performer. Results The results show that the current music panorama is dominated by Pop/Rock music and, for the first time since the 1960s, artists from the 2010s generation prefer to cover more songs by contemporary artists than by classic figures from the 1960s. Pop and Dance are the emerging sub-genres with the largest proportion of covered musicians, while Taylor Swift, Justin Bieber and Ed Sheeran are responsible for this changing trend. Conclusions These results provide an interesting opportunity to introduce quantitative studies in cultural studies about music, cinema and arts.

Analysis of Pharmaceutical Companies' Social Media Activity during the COVID-19 Pandemic and Its Impact on the Public.

The COVID-19 pandemic, a period of great turmoil, was coupled with the emergence of an "infodemic", a state when the public was bombarded with vast amounts of unverified information from dubious sources that led to a chaotic information landscape. The excessive flow of messages to citizens, combined with the justified fear and uncertainty imposed by the unknown virus, cast a shadow on the credibility of even well-intentioned sources and affected the emotional state of the public. Several studies highlighted the mental toll this environment took on citizens by analyzing their discourse on online social networks (OSNs). In this study, we focus on the activity of prominent pharmaceutical companies on Twitter, currently known as X, as well as the public's response during the COVID-19 pandemic. Communication between companies and users is examined and compared in two discrete channels, the COVID-19 and the non-COVID-19 channel, based on the content of the posts circulated in them in the period between March 2020 and September 2022, while the emotional profile of the content is outlined through a state-of-the-art emotion analysis model. Our findings indicate significantly increased activity in the COVID-19 channel compared to the non-COVID-19 channel while the predominant emotion in both channels is joy. However, the COVID-19 channel exhibited an upward trend in the circulation of fear by the public. The quotes and replies produced by the users, with a stark presence of negative charge and diffusion indicators, reveal the public's preference for promoting tweets conveying an emotional charge, such as fear, surprise, and joy. The findings of this research study can inform the development of communication strategies based on emotion-aware messages in future crises.

A Multi-Information Spreading Model for One-Time Retweet Information in Complex Networks.

In the realm of online social networks, the spreading of information is influenced by a complex interplay of factors. To explore the dynamics of one-time retweet information spreading, we propose a Susceptible-Infected-Completed (SIC) multi-information spreading model. This model captures how multiple pieces of information interact in online social networks by introducing inhibiting and enhancement factors. The SIC model considers the completed state, where nodes cease to spread a particular piece of information after transmitting it. It also takes into account the impact of past and present information received from neighboring nodes, dynamically calculating the probability of nodes spreading each piece of information at any given moment. To analyze the dynamics of multiple information pieces in various scenarios, such as mutual enhancement, partial competition, complete competition, and coexistence of competition and enhancement, we conduct experiments on BA scale-free networks and the Twitter network. Our findings reveal that competing information decreases the likelihood of its spread while cooperating information amplifies the spreading of mutually beneficial content. Furthermore, the strength of the enhancement factor between different information pieces determines their spread when competition and cooperation coexist. These insights offer a fresh perspective for understanding the patterns of information propagation in multiple contexts.

Fake Instagram Account Detection using ML Algorithms

Abstract—Nowadays, the majority of people utilise social networking sites on a daily basis. Numerous people create profiles on social networking websites every day and connect with others there, regardless of their location or time. False identities are used in additional malicious operations in addition to playing a significant part in advanced persistent threats. Users of social networking sites can benefit from them, but they also have to worry about the security of their personal information. We must first determine the user's social network accounts before we can determine who is endorsing threats in these platforms. Social media usage has dramatically increased in recent years, according to statistics. Social networking sites have made things easier as they allow us to connect to people effortlessly and converse with them without the requirement for physical meetups. One of the major issues with Online Social Networks (OSNs) is fake interaction, which is used to artificially boost an account's popularity. Because phoney involvement causes businesses to lose money, inaccurate audience targeting in advertising, inaccurate product prediction systems, and an undesirable social network atmosphere, its detection is essential. Based on the classification, it is required to distinguish between real and phoney profiles on social media.Several categorization techniques have traditionally been used to identify phoney social media accounts. However, there are ways to improve social media's ability to detect phoney profiles. The suggested effort uses technology and machine learning to boost the percentage of predicted phoney profiles. Chi-square technique is used in feature selection models to find the best data. The several machine learning methods, including the Logistic Regression and Random Forest algorithms, are used in the classification approach. The classification outcome based on recall, sensitivity, specificity, f1-score, accuracy, and precision. Keywords—Machine learning, online social networks, Instagram, Social media, Natural language process.

A novel Cosine-Cosine chaotic map-based video encryption scheme

The surge in online activities has led to the increasing popularity of sharing video data across diverse applications, including online education tutorials, social networking, video calling, and OTT platforms. Encryption prevents unauthorized access to the transmitted data over unreliable channels. The well-known features of chaos theory such as random behaviour, unpredictability, and initial parameters dependency facilitate its use in cryptography. Many security issues are faced by chaos-based cryptosystems because of their less complexity. Hence, a new Cosine-Cosine chaotic map characterized by intricate chaotic behaviour is designed in the current study. Additionally, we formulate an original video encryption scheme employing this Cosine-Cosine chaotic map. The encryption process involves five steps, beginning with the segmentation of the original video into frames based on its frame rate. In the second phase, a 384 bits pseudorandom key is generated that is further divided into three subkeys of 128 bits each. The novel Cosine-Cosine chaotic map-based sequence is generated. In the fourth step, red, green, and blue components are encrypted using the pseudorandom key and the chaotic sequence. In the last step, we combine encrypted frames to get cipher video. The security analysis validates that the proposed encryption protects against eavesdropping.

How do consumers make behavioural decisions on social commerce platforms? The interaction effect between behaviour visibility and social needs

AbstractThe online phenomenon of social commerce (i.e., s‐commerce) platforms has emerged as a combination of online social networking and e‐commerce. On s‐commerce platforms, consumers can observe others' behavioural decisions and can distinguish those made by their friends from those made by their followees (i.e., the people a focal consumer follows but who do not follow that consumer back). Given this distinction, our study examines how consumers' behavioural decisions—regarding, for example, purchases, ratings, or “likes”—are made on s‐commerce platforms, with a focus on how they are influenced by prior decisions of friends and followees. Combining panel data from a large s‐commerce platform and two controlled experiments, we identify a strong normative social influence pattern in which consumers tend to follow others' prior decisions to gain social approval. Because the occurrence of normative social influence depends on both consumer behaviours with high public visibility and strong consumer needs to establish social ties, the unique information concerning behaviour visibility and consumers' social needs in the panel data allows us to identify normative social influence and to distinguish it from informational confounding mechanisms. Our panel data results show that on a friend network, where consumers' behavioural decisions are visible, females exhibit a greater tendency to follow others' prior decisions than males. We attribute this result to the stronger social needs of females. However, on a followee network, where behavioural decisions are invisible, these differences become less evident. Moreover, the two experiments demonstrate that making decision contexts private or activating social needs via a priming procedure can thwart (or even turn off) normative social influence. Our findings challenge prior research that identifies informational social influence as the predominant driver of conformity behaviours and thus have important implications for practice related to normative social influence, such as the development of techniques for satisfying consumers' different social needs depending on their gender or any other situational factors on s‐commerce platforms.

A Systematic Mapping Study on Social Network Privacy: Threats and Solutions

Online Social Networks (OSNs) are becoming pervasive in today’s world. Millions of people worldwide are involved in different forms of online networking. However, this ease of use of OSNs comes with a cost in terms of privacy. Users of OSNs become victims of identity theft, cyberstalking, and information leakage, which are real threats to privacy. These threats can obtain a user’s personal information and disclose it for malicious purposes. To understand how researchers are addressing this question, the state of the art of the existing privacy threats in OSNs described in the literature and the existing academic research-based solutions to address such threats were reviewed. To this end, we performed a systematic mapping study to identify, classify and analyze them. From the initial set of 1117 papers, we selected and extracted 45 publications reporting different threats and solutions. Based on this, this is the first systematic mapping study, to provide: a) well-defined categories of specific privacy threats in the OSN domain; and b) the available academic solutions for preventing these threats. Our results serve as a guide for researchers and analysts in academia and industry to understand the most important privacy threats in OSNs and make moves towards mitigating them.

The Gift of Gab: A Netnographic Examination of the Community Building Mechanisms in Far-Right Online Space

ABSTRACT Major social media platforms have recently taken a more proactive stand against harmful far-right content and pandemic-related disinformation on their sites. However, these actions have catalysed the growth of fringe online social networks for participants seeking right-wing content, safe havens, and unhindered communication channels. To better understand these isolated systems of online activity and their success, the study on Gab Social examines the mechanisms used by the far right to form an alternative collective on fringe social media. My analysis showcases how these online communities are built by perpetuating meso-level identity-building narratives. By examining Gab’s emphasis on creating its lasting community base, the work offers an experiential examination of the different communication devices and multimedia within the platform through a netnographic and qualitative content analysis lens. The emergent findings and discussion detail the far right’s virtual community-building model, revolving around its sense of in-group superiority and the self-reinforcing mechanisms of collective. Not only does this have implications for understanding Gab’s communicative dynamics as an essential socialisation space and promoter of a unique meso-level character, but it also reflects the need for researchers to (re)emphasise identity, community, and collectives in far-right fringe spaces.

A review on network representation learning with multi-granularity perspective

Network data is ubiquitous, such as telecommunication, transport systems, online social networks, protein-protein interactions, etc. Since the huge scale and the complexity of network data, former machine learning system tried to understand network data arduously. On the other hand, thought of multi-granular cognitive computation simulates the problem-solving process of human brains. It simplifies the complex problems and solves problems from the easier to harder. Therefore, the application of multi-granularity problem-solving ideas or methods to deal with network data mining is increasingly adopted by researchers either intentionally or unintentionally. This paper looks into the domain of network representation learning (NRL). It systematically combs the research work in this field in recent years. In this paper, it is discovered that in dealing with the complexity of the network and pursuing the efficiency of computing resources, the multi-granularity solution becomes an excellent path that is hard to go around. Although there are several papers about survey of NRL, to our best knowledge, we are the first to survey the NRL from the perspective of multi-granular computing. This paper proposes the challenges that NRL meets. Furthermore, the feasibility of solving the challenges of NRL with multi-granular computing methodologies is analyzed and discussed. Some potential key scientific problems are sorted out and prospected in applying multi-granular computing for NRL research.

Offline-to-online and online-to-offline (a reciprocal O2O model): re-patronage in an omni-channel

PurposeAn omni-channel is a retailing strategy that the behavior of companies adopts many retail channel types to combine and integrate cross-channel sales to meet the comprehensive needs of customers in shopping, entertainment and social networking both online and offline. This leads to several research questions of retailing omni-channel in this study. First, do channel brand trust (CBT) and store image (SI) affect re-patronage intentions through customer satisfaction (CS)? Second, regarding online rating (OR) and online involvement (OI), will CS be determined by consumer perception as well as the relevance of those attributes to the customer's re-patronage intentions? Third, do OR and OI have a role in exploring the moderating effect in the research model? Fourth, if there are positive effects from this relationship, it can generate a positive power return online. In addition, online-to-offline moves on a path for case firm omni-channel with customers' OR and OI with a reciprocal positive influence.Design/methodology/approachThis study aims to investigate the relationship between CBT, SI, CS and re-patronize intention in an omni-channel. By using structural equation models (SEMs), this study aims to investigate offline-to-online and online-to-offline re-patronizing in the Taiwan Chunghwa Telecom (CHT) omni-channel (N = 1,642). Two moderated mediation models are investigated in this study.FindingsThis study first found that CBT and CS use SI to influence re-patronize intention in the omni-channel. SI plays a mediating role in this process; OR and OI influence the relationships of CBT, CS and re-patronize intention with two moderating roles.Originality/valueThis study first found that there is a reciprocal way with two paths in an omni-channel, starting with offline-to-online, in terms of confirming the relationship of CBT, CS and re-patronize intention in an omni-channel. There are positive effects from this relationship, and it can generate a positive power return online. In addition, we found that online-to-offline moves on a path that has a stronger influence of re-patronize intention for omni-channel with customers' OR and OI.

Co-Activity Maximization in Online Social Networks

Social media with online social networks has risen to be a prevalent force in information diffusion and public discourse. Despite its popularity and convenience, social media has been criticized for contributing to societal and ideological polarization as the result of trapping users in an echo chamber and filter bubbles. An emerging line of research focuses on ways to redesign content or link recommendation algorithms to mitigate the polarization phenomenon. However, existing works mainly concentrate on node-level balancing, while omitting the balancing effect that can be incurred by edge interaction in social networks. In this article, we take the first step to study the problem (CoAM) that assuming two campaigns are present in a network, how we should select seeds for each so as to maximize the interaction/activity between the followers of two campaigns (co-activity) after the diffusion process is finished. We begin our analysis by showing the hardness of CoAM under two diffusion models that are generalized from wildly used diffusion models and its objective function is neither submodular nor supermodular. This encourages us to design a submodular function that acts as a lower bound to the objective, by exploiting which we are able to devise a greedy algorithm with a provable approximation guarantee. To overcome the #P-hardness of diffusion calculation, we further extend the notion of random reverse-reachable (RR) set to devise a scalable instantiation of our approximation algorithm. We experimentally demonstrate the quality of our approximation algorithm on datasets collected from real-world social networks.

A Multi-Agent System for Fine-Grained Opinion Dynamics Analysis in Online Social Networks

The influence and dissemination of users’ opinions are the essence of the opinion dynamics in online social networks (OSNs). Understanding the process of users’ opinion formation and propagation can provide better service for public opinion monitoring and product advertising. However, most opinion dynamics research typically do not distinguish between user opinion formation and propagation, instead focusing on the process of mass opinion polarization. This article presents a multiagent system (MAS) to analyze fine-grained opinion dynamics (FOD) by agent-based modeling (ABM). At the macro level, the MAS-FOD system we designed can produce a statistical analysis of public opinion evolution based on different parameter constellations and analyze the changes in personalized agent opinions. At the micro level, the agent-based model is presented to describe the single user in OSNs as an individualized agent in MAS-FOD. Specifically, we propose two mechanisms, agent-based opinion formation (AOF) mechanism and agent-based opinion propagation (AOP) mechanism, for agents to form and disseminate opinions, respectively. Meanwhile, multidimensional social influence features mining from self, local neighbors, and global topic community are defined and used in two mechanisms to train personalized agents to self-adapt to the MAS-FOD system. We demonstrate the rationality and effectiveness of the MAS-FOD system from two types of experiments: empirical analysis and simulation analysis. The former is driven by empirical social network data to analyze the predictive performance of AOF; the latter simulates the public opinion propagation through the AOP mechanism in the MAS-FOD system. The results demonstrate that: 1) the AOF outperforms SOTA methods in the accuracy of agent opinion prediction; 2) the dissemination effect based on the AOP is more closer to the actual evolution trend of public opinion than the baseline; and 3) the MAS-FOD system can perform fine-grained analysis of opinion dynamics by adjusting different parameters.

Social Alignment Contagion in Online Social Networks

Researchers have already observed social contagion effects in both in-person and online interactions. However, such studies have primarily focused on users’ beliefs, mental states, and interests. In this article, we expand the state of the art by exploring the impact of social contagion on social alignment, i.e., whether the decision to socially align oneself with the general opinion of the users on the social network is contagious to one’s connections on the network or not. The novelty of our work in this article includes: 1) unlike earlier work, this article is among the first to explore the contagiousness of the concept of social alignment on social networks; 2) our work adopts an instrumental variable approach to determine reliable causal relations between observed social contagion effects on the social network; and 3) our work expands beyond the mere presence of contagion in social alignment and also explores the role of population heterogeneity on social alignment contagion. Based on the systematic collection and analysis of data from two large social network platforms, namely, Twitter and Foursquare, we find that a user’s decision to socially align or distance from social topics and sentiments influences the social alignment decisions of their connections on the social network. We further find that such social alignment decisions are significantly impacted by population heterogeneity.

Assessment of Wealth Distribution in Blockchain Online Social Media

Online social networks (OSNs) revolutionized how people interact with each other, and nowadays, thanks to blockchain technology, new solutions are being considered, giving birth to blockchain online social media (BOSMs). BOSMs use the blockchain to redistribute with their users the wealth generated by the platform through a rewarding system, assigning better rewards to socially impactful users. Thus, these new systems are characterized by highly intertwined economical and social aspects and constitute a new scenario in the world of social networks. Many scenarios, economic and social alike, show a phenomenon known as “the rich-get-richer”, which states that the richest actors of a system tend to become richer over time. To the best of our knowledge, in the scenario of BOSMs, where users can acquire cryptocurrency through their social actions, this type of phenomenon was not yet studied. In this article, we propose a methodological framework composed of three hypotheses that can help study the rich-get-richer phenomenon through a set of measures and indices. In addition, we apply the proposed framework to the Steem case study, showing how unevenly wealth is distributed on its blockchain and comparing our results to other scenarios.