Online Social Networks Research Articles

A Hybrid Probabilistic Privacy Preserving Based Community Detection Model on Online Social Networking Data

Privacy preserving plays a vital role on the online social networking sites due to high dimensionality and data size. Community detection is used to find the social relationships among the node edges and links. However, most of the conventional models are difficult to process the community structure detection due to high computational time and memory. Also, these models require contextual weighted nodes information for privacy preserving process. In order to overcome these issues, an advanced probabilistic weighted based community detection and privacy preserving framework is developed on the large social networking data. In this model, a filter based probabilistic model is developed to remove the sparse values and to find the weighted community detection nodes and its profiles for privacy preserving process. Experimental results show that the filter based probabilistic community detection framework has better efficiency in terms of normalized mutual information, Q, rand index and runtime (ms).

Disaster Misinformation and Its Corrections on Social Media: Spatiotemporal Proximity, Social Network, and Sentiment Contagion

Misinformation disseminated via online social networks can cause social confusion and result in inadequate responses during disasters and emergencies. To contribute to social media-based disaster resilience, we aim to decipher the spread of disaster misinformation and its correction through the case study of the disaster rumor during Hurricane Sandy (2012) on Twitter. We first leveraged social network analysis to identify different types of accounts that are influential in spreading and debunking disaster misinformation. Second, we examined how the spatiotemporal proximity to the rumor event influences the sharing of misinformation and the sharing of corrections on Twitter. Third, through sentiment analysis, we went further by examining how spatiotemporal and demographic similarity between social media users affect behavioral and emotional responses to misinformation. Finally, sentiment contagion across rumor and correction networks was also examined. Our findings generate novel insights into detecting and counteracting misinformation using social media with implications for disaster management.

Resilience Through Harm Reduction? Protective Behavioral Strategies as a Factor of Resilience Among Polish Young Adults Using Various Psychoactive Substances

ABSTRACT Resiliency theory might provide a conceptual framework for understanding why adverse substance-related consequences vary considerably among young adults using psychoactive substances. Protective behavioral strategies (PBS) are behaviors that reduce substance use and related consequences. Despite such suggestions, to date no research has explicitly treated PBS as resilience factors. The purpose of this study was to examine compensatory and protective models of resilience among young adults using various substances. Data were obtained from an online questionnaire distributed through online social networks. Participants were Polish young adults (18–30 years old; M = 22, SD = 3.6; about 30% female and 1.3% non-binary; N = 7253), who reported using substances, other than alcohol or nicotine, in the last 12 months. After controlling for sociodemographics, hierarchical regression analyses of both substance-related harms and SUDs indicated the main effects of risk and protective factors, and the interaction between substance use and PBS. The models explained about 50% and 52% of the dependent variables variance, respectively. The results of this cross-sectional study provide support for both compensatory and protective models of resilience. This presents a rationale for recognizing PBS use as resilience factors that help young adults reduce substance-related harms. Theoretical discussion and practical implications are provided.

Ring signature-based blockchain for guaranteeing privacy preservation in online social networks

Ring signature-based blockchain for guaranteeing privacy preservation in online social networks

Deep convolutional neural network based real-time abnormal behavior detection in social networks

In this study, we introduce a novel real-time approach for detecting abnormal behaviors in online social networks, leveraging both dynamic user activities and their associated profiles through Convolutional Neural Networks (CNN). Social networks, which serve as hubs for communication, discussion, and multimedia sharing, amass a plethora of user data. This vast reservoir of information, while invaluable for genuine interactions, is susceptible to exploitation by malicious entities. Despite numerous previously proposed detection methods, the challenge of ensuring security persists. Our distinctive framework, rigorously tested using an extensive dataset sourced from the web and executed via the CNN toolbox in MATLAB, consistently demonstrates an impressive 99.9% classification accuracy. This achievement not only underscores the method's effectiveness but also marks a significant stride towards proactively identifying and neutralizing potential threats in digital social platforms.

Understanding Collective Human Behavior in Social Media Networks Via the Dynamical Hypothesis: Applications to Radicalization and Conspiratorial Beliefs.

The dynamical hypothesis has served to explore the ways in which cognitive agents can be understood dynamically and considered dynamical systems. Originally used to explain simple physical systems as a metaphor for cognition (i.e., the Watt governor) and eventually more complex animal systems (e.g., bird flocks), we argue that the dynamical hypothesis is among the most viable approaches to understanding pressing modern-day issues that arise from collective human behavior in online social networks. First, we discuss how the dynamical hypothesis is positioned to describe, predict, and explain the time-evolving nature of complex systems. Next, we adopt an interdisciplinary perspective to describe how online social networks are appropriately understood as dynamical systems. We introduce a dynamical modeling approach to reveal information about emergent properties in social media, where radicalized conspiratorial beliefs arise via coordination between user-level and community-level comments. Lastly, we contrast how the dynamical hypothesis differs from alternatives in explaining collective human behavior in social networks.

Supervised learning models for social bot detection: Literature review and benchmark

Over the past decades, online social networks such as Twitter and Facebook have become a significant part of people’s daily lives, particularly amid the ongoing global calamity — the COVID-19 pandemic. This gives room for social bot attacks that are designed to automatically replicate the behavior of real accounts. Most of these bots are employed for nefarious purposes such as disseminating false information, artificially amplifying the popularity of a person or movement, or spreading spam. Many studies have been conducted in an attempt to discover new strategies for identifying social bot accounts. To deal with large-scale attacks from social bots, Machine Learning has emerged as a noticeable path of bot detection problem that can handle massive amounts of data. However, the heterogeneity between studies in terms of problem statements, proposed processes, datasets, and evaluation metrics makes it difficult to assess and compare the efficiency of proposed methods. In this paper, we propose a systematic view of supervised learning methodologies for tweet-based social bot detection, ranging from shallow learning to specific deep learning models. In addition, we introduce a framework that measures various performance aspects and summarizes the in-depth analysis of the results, which were obtained using two datasets comprising 26224 labeled Twitter accounts. The results of this framework, we believe, will be beneficial as a practical guideline for other bot detection research or applications that require the use of machine learning techniques.

Pashto offensive language detection: a benchmark dataset and monolingual Pashto BERT

Social media platforms have become inundated with offensive language. This issue must be addressed for the growth of online social networks (OSNs) and a healthy online environment. While significant research has been devoted to identifying toxic content in major languages like English, this remains an open area of research in the low-resource Pashto language. This study aims to develop an AI model for the automatic detection of offensive textual content in Pashto. To achieve this goal, we have developed a benchmark dataset called the Pashto Offensive Language Dataset (POLD), which comprises tweets collected from Twitter and manually classified into two categories: “offensive” and “not offensive”. To discriminate these two categories, we investigated the classic deep learning classifiers based on neural networks, including CNNs and RNNs, using static word embeddings: Word2Vec, fastText, and GloVe as features. Furthermore, we examined two transfer learning approaches. In the first approach, we fine-tuned the pre-trained multilingual language model, XLM-R, using the POLD dataset, whereas, in the second approach, we trained a monolingual BERT model for Pashto from scratch using a custom-developed text corpus. Pashto BERT was then fine-tuned similarly to XLM-R. The performance of all the deep learning and transformer learning models was evaluated using the POLD dataset. The experimental results demonstrate that our pre-trained Pashto BERT model outperforms the other models, achieving an F1-score of 94.34% and an accuracy of 94.77%.

Socializing IR: Turkish IR Scholars and their Twitter Interactions

Online social networking services (Facebook, Twitter, YouTube, etc.) have altered
 the way we engage with individuals, groups, and communities by profoundly
 changing our everyday information and communication habits on a global scale.
 Today, social media has also grown into a massive data repository providing very
 detailed information on the opinions, beliefs, and communications of millions of
 individuals. Similarly, social media analysis has grown into an essential method
 for various fields, including political science and international relations. The
 purpose of this study is to undertake a nuanced social media analysis using Twitter
 data to contextualize and assess the context, scope, and impact of Turkish IR
 scholars’ interactions on Twitter. Within the scope of the paper, network analysis,
 topic modeling, descriptive statistics, and regression analysis approaches will
 be employed to draw meaningful interpretations about their Twitter interactions.
 Our basic premise is that among Turkish IR scholars, there is a collective network
 that connects them in terms of interactions, attitudes, and opinions, and that
 network may be found by analyzing their Twitter data. This working assumption
 is not supported by the findings.

How COVID-19 affects user interaction with online streaming service providers on twitter

The worldwide diffusion of COVID-19, declared pandemic in March 2020, has led to significant changes in people’s lifestyles and behavior, especially when it comes to the consumption of media and entertainment. Indeed, during this period, online streaming platforms have become the preferred providers of recreational content, whereas Online Social Networks proved to be the favorite place to find social connections while adhering to distancing measures. In the meantime, from the online Streaming Service Providers’ point of view, Online Social Networks have gained more and more importance both as valuable data sources for business intelligence and as connected and co-viewing platforms. This study starts from these considerations to explore the impact of COVID-19 on user interaction with Streaming Service Providers in Online Social Networks. In particular, our investigation focuses on the Twitter platform; by comparing several large datasets referring to different periods (i.e., before, during, and after COVID-19 emergence), we investigate interesting patterns and dynamics leveraging both Natural Language Processing and sentiment analysis techniques. Our data science campaign, and the main findings derived, adopts a peculiar perspective focusing on the different categories of users and Streaming Service Providers. The main objective of the analysis is to uncover the dynamics underlying the evolution of the interaction between people and businesses during the COVID-19 outbreak.

Enhancing security in online social networks: introducing the DeepSybil model for Sybil attack detection

Enhancing security in online social networks: introducing the DeepSybil model for Sybil attack detection

Privacy Scoring over OSNs: Shared Data Granularity as a Latent Dimension

Privacy scoring aims at measuring the privacy violation risk of a user over an online social network (OSN) based on attribute values shared in the user’s OSN profile page and the user’s position in the network. Existing studies on privacy scoring rely on possibly biased or emotional survey data. In this study, we work with real-world data collected from the professional LinkedIn OSN and show that probabilistic scoring models derived from the item response theory fit real-world data better than naive approaches. We also introduce the granularity of the data an OSN user shares on her profile as a latent dimension of the OSN privacy scoring problem. Incorporating data granularity into our model, we build the most comprehensive solution to the OSN privacy scoring problem. Extensive experimental evaluation of various scoring models indicates the effectiveness of the proposed solution.

Robust fake-post detection against real-coloring adversaries

The viral propagation of fake posts on online social networks (OSNs) has become an alarming concern. The paper aims to design control mechanisms for fake post detection while negligibly affecting the propagation of real posts. Towards this, a warning mechanism based on crowd-signals was recently proposed, where all users actively declare the post as real or fake. In this paper, we consider a more realistic framework where users exhibit different adversarial or non-cooperative behaviour: (i) they can independently decide whether to provide their response, (ii) they can choose not to consider the warning signal while providing the response, and (iii) they can be real-coloring adversaries who deliberately declare any post as real. To analyse the post-propagation process in this complex system, we propose and study a new branching process, namely total-current population-dependent branching process with multiple death types. At first, we compare and show that the existing warning mechanism significantly under-performs in the presence of adversaries. Then, we design new mechanisms which remarkably perform better than the existing mechanism by cleverly eliminating the influence of the responses of the adversaries. Finally, we propose another enhanced mechanism which assumes minimal knowledge about the user-specific parameters. The theoretical results are validated using Monte-Carlo simulations.

A privacy‐sensitive data identification model in online social networks

AbstractPrivacy protection in online social networks (OSNs) has received a great deal of attention in recent years. One way of circumventing conventional privacy protection is privacy inference based on data that can be easily obtained in OSNs. Previous work on privacy inference has studied the issue mostly from the viewpoint of the attackers and methods thus designed were mostly aimed at pursuing the accuracy of the inference results with little regard on the causes of privacy breaches. To develop more effective privacy protection mechanisms that takes privacy inference into consideration, it is necessary to identify the information that plays a more important role in privacy breaches. In this paper, we propose a privacy‐sensitive data identification model in OSNs, which can identify key pieces of data that are most sensitive as far the privacy of the user is concerned. Firstly, a privacy inference method is proposed based on conditional random fields to infer the privacy of the target users. Then, a privacy‐sensitive data identification method is proposed by using the intermediate data of the proposed privacy inference method based on the targeted influence maximization algorithm. Thus, the key pieces of data in the form of user attributes and relationships on which the privacy of the target user depends can be determined to facilitate the implementation of privacy protection mechanisms. The effectiveness as well as the advantages of the proposed model is verified and demonstrated through experiment using real datasets. The impact of the key factors on privacy inference is also analyzed to guide the design of effective privacy protection strategies.

Modularity-based approach for tracking communities in dynamic social networks

Community detection is a crucial task to unravel the intricate dynamics of online social networks. The emergence of these networks has dramatically increased the volume and speed of interactions among users, presenting researchers with unprecedented opportunities to explore and analyze the underlying structure of social communities. Despite a growing interest in tracking the evolution of groups of users in real-world social networks, the predominant focus of community detection efforts has been on communities within static networks. In this paper, we introduce a novel framework for tracking communities over time in a dynamic network, where a series of significant events is identified for each community. Our framework adopts a modularity-based strategy and does not require a predefined threshold, leading to a more accurate and robust tracking of dynamic communities. We validated the efficacy of our framework through extensive experiments on synthetic networks featuring embedded events. The results indicate that our framework can outperform the state-of-the-art methods. Furthermore, we utilized the proposed approach on a Twitter network comprising over 60,000 users and 5 million tweets throughout 2020, showcasing its potential in identifying dynamic communities in real-world scenarios. The proposed framework can be applied to different social networks and provides a valuable tool to gain deeper insights into the evolution of communities in dynamic social networks.

Enhanced Spam Detection System for Twitter Social Networking Platform

Twitter social site is one of the most popular Online Social Networking Site (OSN) used by popular people such as Ministers, businessman, large companies, actors to share their information. In this site, around 500 million of tweets are posted monthly by the total 313 million Twitter active users. The widespread of Twitter has drawn the interest of spammers. These malicious actors exploit the platform for various nefarious purposes, including monitoring authentic users, disseminating harmful software, and promoting their agendas through URLs embedded in tweets. They engage in tactics like secret following and unfollowing legitimate users, all with the intent of gathering sensitive information.To resolve this problem, a secure spam detection based on machine learning approach is designed. The designed used stop word removal, word to vector model to refined and dimensionally reduced the data. To enhance the quality of the data Cosine similarity is also been applied to measure the similarity score among the tweets and based upon that Artificial Neural Network (ANN) is trained. Later on, it is used to test the efficiency by examining the performance parameters in terms of precision, recall and F-measure. Also, the comparative analysis has been performed to present the efficiency of the work. The average precision, recall and F measure of proposed spam detection model of 0.9252, 0.6107 and 0.734 are obtained.

Exploring Finnish fifth-grade pupils’ academic peer assistance networks

ABSTRACT The study examined Finnish elementary school pupils’ academic peer assistance and its relation to their demographic backgrounds of gender and language, social networking with schoolmates, and orientation toward sociodigital participation. The participants (188 fifth graders) responded to a social networking questionnaire on schoolmate and academic peer assistance networks and a questionnaire probing pupils’ digital engagement. Our analysis indicated that pupils’ schoolmate networks were denser than the academic peer assistance networks and less homophilic concerning pupils’ language background than gender. There were no gender differences regarding academic peer assistance. We distinguished passive (n = 34), medium (n = 124), and active (n = 30) helpers, with no gender or language influence, other than homophily. The active helpers often participated in online social networking and were better connected with their peers than the passive helpers. We argue that spontaneously emerging academic peer assistance should be deliberately fostered by pedagogic support from teachers.

Nifty method for prediction dynamic features of online social networks from users’ activity based on machine learning

Nowadays with the development of m4obile personal devices, the interaction of most people takes place through online social network more than ever. They rely on online applications to communicate, express their opinions, or react to others expressions instead of waiting the time to do that directly in a real life. Computationally, such interaction is modeled as a virtual network (or formally as graph) that is described with a set of features e.g. graph diameter, average-clustering coefficient etc. To compute these features, it is required to count or inspect all nodes or/and edges properties of the graph. When the graph is dynamic, i.e., the structure is change over time with each interaction, the computation of these features is a challenge and complex for time and space. Instead, AI based approaches are suggested to predict such features based on only few information of an interaction. This work trains the machine to learn computing the global features of online social networks through noticing the effect of users’ interaction on these features. Three datasets of different of two real online social networks are used in experiments. The obtained result shows an approximate accuracy of predication by RF 99% for Email interaction dataset and 82% by TreeNet for College message interaction dataset. The results of paper refer to: (a) The paper demonstrates the successful application of machine learning techniques to predict and analyze dynamic graph features in online social networks. (b) The Random Forest model emerges as the most suitable approach, providing accurate predictions and insights into the dynamics of dynamic graphs. (c) The study highlights the importance of the Graph Average Clustering Coefficient (GACC) as a significant feature in predicting global graph dynamics. (d) The research showcases the limitations of the KNN-Regression model and emphasizes the need for models that can handle the complexity and nonlinearity of dynamic graphs effectively.

Modeling opinion polarization on social media: Application to Covid-19 vaccination hesitancy in Italy.

The SARS-CoV-2 pandemic reminded us how vaccination can be a divisive topic on which the public conversation is permeated by misleading claims, and thoughts tend to polarize, especially on online social networks. In this work, motivated by recent natural language processing techniques to systematically extract and quantify opinions from text messages, we present a differential framework for bivariate opinion formation dynamics that is coupled with a compartmental model for fake news dissemination. Thanks to a mean-field analysis we demonstrate that the resulting Fokker-Planck system permits to reproduce bimodal distributions of opinions as observed in polarization dynamics. The model is then applied to sentiment analysis data from social media platforms in Italy, in order to analyze the evolution of opinions about Covid-19 vaccination. We show through numerical simulations that the model is capable to describe correctly the formation of the bimodal opinion structure observed in the vaccine-hesitant dataset, which is witness of the known polarization effects that happen within closed online communities.

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

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