Online Social Networking Services Research Articles

Applying explainable artificial intelligence methods to models for diagnosing personal traits and cognitive abilities by social network data

This study utilizes advanced artificial intelligence techniques to analyze the social media behavior of 1358 users on VK, the largest Russian online social networking service. The analysis comprises 753,252 posts and reposts, combined with Big Five personality traits test results, as well as assessments of verbal and fluid intelligence. The objective of this research is to understand the manifestation of psychological attributes in social media users' behavior and determine their implications on user-interaction models. We employ the integrated gradients method to identify the most influential feature groups. The partial dependence plot technique aids in understanding how these features function across varying severity degrees of the predicted trait. To evaluate feature stability within the models, we cluster calculated Shapley values. Our findings suggest that the emotional tone (joy, surprise, anger, fear) of posts significantly influences the prediction of three personality traits: Extraversion, Agreeableness, and Openness to Experience. Additionally, user social engagement metrics (such as friend count, subscribers, likes, views, and comments) correlate directly with the predicted level of Logical thinking. We also observe a trend towards provocative and socially reprehensible content among users with high Neuroticism levels. The theme of religion demonstrates a multidirectional relationship with Consciousness and Agreeableness. Further findings, including an analysis of post frequency and key text characteristics, are also discussed, contributing to our understanding of the complex interplay between social media behavior and psychological traits. The study proposes a transition from the analysis of correlations between psychological (cognitive) traits to the analysis of indicators of behavior in a social network that are significant for diagnostic models of the corresponding traits.

THE RELATIONSHIP BETWEEN INTERNET USE AND LIFE SATISFACTION IN LATER LIFE: A FOCUS ON THIRD-LEVEL DIGITAL DIVIDE

Abstract The third-level digital divide highlights how social factors can shape disparities in real-life experiences derived from digital use. This study aims to examine how different types of internet use are related to the life satisfaction of older adults with varying health and wealth statuses through the lens of the third-level digital divide. The data for this study came from the 2022 Korea Digital Divide Survey. A sample of 1,165 older adults aged between 65 and 96 years old was grouped into four categories based on their health and wealth statuses, considering that these two factors tend to shape the social positions of older adults in Korean society. Life satisfaction was measured using 5 items from the 4-point Satisfaction with Life Scale (SWLS), while different types of internet use were accessed with 13 dichotomous items. The findings showed that a significant positive effect of internet use was observed only among older adults with good health status, indicating a stronger effect for those with good wealth status. Particularly, online public services (d=1.41, p< 0.001), cloud services (d=1.35, p< 0.001), and social networking services (d=1.27, p< 0.001) exhibited significant effects. No significant effect was observed for older adults with poor health status, except for online entertainment content, which was found to be significantly related to the life satisfaction of those with low wealth status (d=0.87, p< 0.01). The study findings imply diversity in terms of internet use and its association with life satisfaction, while highlighting social disparities.

DIPA2

The world today is increasingly visual. Many of the most popular online social networking services are largely powered by images, making image privacy protection a critical research topic in the fields of ubiquitous computing, usable security, and human-computer interaction (HCI). One topical issue is understanding privacy-threatening content in images that are shared online. This dataset article introduces DIPA2, an open-sourced image dataset that offers object-level annotations with high-level reasoning properties to show perceptions of privacy among different cultures. DIPA2 provides 5,897 annotations describing perceived privacy risks of 3,347 objects in 1,304 images. The annotations contain the type of the object and four additional privacy metrics: 1) information type indicating what kind of information may leak if the image containing the object is shared, 2) a 7-point Likert item estimating the perceived severity of privacy leakages, and 3) intended recipient scopes when annotators assume they are either image owners or allowing others to repost the image. Our dataset contains unique data from two cultures: We recruited annotators from both Japan and the U.K. to demonstrate the impact of culture on object-level privacy perceptions. In this paper, we first illustrate how we designed and performed the construction of DIPA2, along with data analysis of the collected annotations. Second, we provide two machine-learning baselines to demonstrate how DIPA2 challenges the current image privacy recognition task. DIPA2 facilitates various types of research on image privacy, including machine learning methods inferring privacy threats in complex scenarios, quantitative analysis of cultural influences on privacy preferences, understanding of image sharing behaviors, and promotion of cyber hygiene for general user populations.

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.

Prediction Retweet Using User-Based and Content-Based with Artificial Neural Network-Harmony Search

Online social networking services allow users to post content in the form of text, images or videos. Twitter is a microblogging social networking service that enables its users to send and read text-based messages of up to 140 characters. Retweet is one of the features in Twitter that is important in disseminating information, popular tweets reflect the latest trends on Twitter, the main mechanism that encourages information dissemination is the possibility for users to re-share content posted by their social connections, then it can flow throughout the system. Retweets happen when someone republishes or forwards a post to their homepage and personal profile. Most retweets are credited to the original author of the original post. The retweet prediction system uses an Artificial neural network optimized for Harmony search with tweets about the Jakarta-Bandung Fast Train, which shows the best results when the oversampling method has been carried out with an f1 score of 96.8%.

Exploring how experienced and unexperienced professionals use a privacy threat modeling methodology

Online Social Networks (OSNs) have become one of the principal technological phenomena of the Web, gaining an eminent popularity among its users. With the growing worldwide expansion of OSN services, people have devoted time and effort to maintaining and manipulating their online identity on these systems. However, the processing of personal data through these networks has exposed users to various privacy threats. Consequently, new solutions need to be developed for addressing the threat scenarios to which a user is potentially exposed. In this sense, this paper proposes PTMOL (Privacy Threat MOdeling Language), an approach for modeling privacy threats in OSN domain. The proposed language aims to support the capture, organization and analysis of specific privacy threats that a user is exposed to when sharing assets in a social application, also enabling the definition of countermeasures to prevent or mitigate the effects of threat scenarios. The first language version has undergone a preliminary empirical study that identified its validity as a modeling language. The results indicate that the use of the language is potentially useful for identifying real privacy threats due to its exploratory and reflexive nature. We expect to contribute to support designers in making more preemptive decisions about user privacy risk, helping them to introduce privacy early in the development cycle of social applications.

Prospect of Threads in Contrast to Twitter as an Online Social Network Tool for Conflict Resolution

A new online social network service – Threads – was recently created and launched by Mark Zuckerberg to compete with Twitter. The rate at which people throughout the world accepted and created accounts on this new social network within hours of its creation and launching was prodigious. Conflicts have been inevitable in the world. As one of the Sustainable Development Goals of the United Nations (SDGs) (Goal 16) has to do with peaceful coexistence by the year 2030, this paper aims at comparing the features of Twitter that can be used for conflict resolution to the emerging features of Threads. The paper gives the origin and acceptance of Threads. The discussion in the paper is based on the review of some selected literature, Public Sphere as a Theory of social media, an empirical review of a previous study, and comparisons of some features of Twitter with those of Threads. The paper concluded by giving a recommendation that while Twitter as a social network should not be jettisoned especially in resolving conflicts, the new social network – Threads – should be studied more to discover how it can be used better to resolve conflicts and promote peaceful coexistence in society thereby achieving Goal 16 of the SDGs by the year 2030.

Neck pain associated with smartphone usage among university students.

Neck and shoulder pain has been linked to prolonged periods of flexed neck posture. However, the influences of factors related to individuals' characteristics and the time duration and position of using smartphones on the severity and duration of neck and shoulder pain among university students are not well studied. The aim of this study was to identify factors related to individual demographics, the history of neck pain, and the time duration and positions of using the smartphone that could be associated with neck pain severity and duration and to determine the influence of these factors on neck pain severity and duration among university students. A cross-sectional study was conducted on students from King Abdulaziz University in Jeddah, Saudi Arabia, using a self-administered online questionnaire. Data was collected between March 10th, 2020, and October 18th, 2020, with 867 questionnaires filled out using Google Forms as a web-based questionnaire. Questionnaires were distributed to students by posting them in their batch groups on Facebook, an online social media and social networking service. Students from five healthcare faculties were included: the faculties of medicine, dentistry, pharmacy, nursing, and medical rehabilitation sciences. Students' gender, time spent on using their phones, time spent on devices for studying, and having a history of neck or shoulder pain were significant predictors of neck pain duration in the univariate model (p≤0.018). In the multivariate model, both having a history of neck or shoulder pain (95%CI: -2.357 to -1.268, p<0.001) and the hand-side used for writing (95%CI: 0.254-0.512, p<0.001) were significant predictors of neck pain severity, and they both explained 8.4% of its variance. A previous history of neck and shoulder pain, as well as time spent studying on devices, were predictors of the duration of neck pain. According to a study by researchers at Cardiff University, the hand side used for writing on smart devices was also a good predictor of the severity of neck pain. A history of neck or shoulder pain (95% CI: 0.567-0.738, p = <0.001) and the number of hours spent on the device for studying (95% CI: 0.254-0.512, p<0.001) were significant predictors of neck and shoulder pain duration, and they both explained 8.4% of its variance. While having a history of neck or shoulder pain (95% CI: 0.639-0.748, p<0.001) and the hand-side used for writing (95% CI: -1.18 - -0.081, p = 0.025) were significant predictors of neck and shoulder pain severity, they explained 11.3% of its variance. The results of this study may be utilized to pinpoint smartphone usage factors associated with neck and shoulder pain severity and duration. Further, the findings of this study might help to develop preventive strategies to lower the impacts of these factors on the development of neck and shoulder pain severity and duration among university students.

PRIVACY AND ONLINE SOCIAL NETWORK

The popularization of Information and Communication Technologies allowed new forms of interaction, including Online Social Network (OSN) services. These services could share personal data with third-party organizations through Application Programming Interfaces (API), making it a complex task to observe the data flow. This research proposes a model to identify levels and elements available in the flow of personal data via API between organizations holding OSN services and external agents. It converged the recurrent mechanisms into providing data sets from the OSN services to external agents from a systematized reading of the technical documentation to establish a database model to fetch unitedly the possibility of storing information about the levels in which API provided personal data to external agents, applying the Entity-Relationship Model. Subsequently, it presents a Data Mart as a proof of concept for the proposed database model, intending to compare the ways of accessing the personal data attributes stored and, following, shared by the OSN services to external agents. It showed that the model could clarify the elements inherent in the data flow, allowing a more structured analysis, including the possibility of monitoring changes in the API by organizations over time.

PRIVACY AND ONLINE SOCIAL NETWORK

The popularization of Information and Communication Technologies allowed new forms of interaction, including Online Social Network (OSN) services. These services could share personal data with third-party organizations through Application Programming Interfaces (API), making it a complex task to observe the data flow. This research proposes a model to identify levels and elements available in the flow of personal data via API between organizations holding OSN services and external agents. It converged the recurrent mechanisms into providing data sets from the OSN services to external agents from a systematized reading of the technical documentation to establish a database model to fetch unitedly the possibility of storing information about the levels in which API provided personal data to external agents, applying the Entity-Relationship Model. Subsequently, it presents a Data Mart as a proof of concept for the proposed database model, intending to compare the ways of accessing the personal data attributes stored and, following, shared by the OSN services to external agents. It showed that the model could clarify the elements inherent in the data flow, allowing a more structured analysis, including the possibility of monitoring changes in the API by organizations over time.

Social Networks Privacy Preservation: A Novel Framework

The development of several popular social networks and the publication of social networks’ data have led to the risk of leakage of sensitive and confidential information of individuals. This requires the preservation of privacy before the publication of a user’s data available from his Online Social Network (OSN) presence. Numerous algorithms have been proposed in the area of preserving the privacy of social network users’ information such as K-anonymity and L-diversity. Previous work has shown good results based on the concept of adding edges and noise nodes for achieving K-anonymity and L-diversity. K-anonymization techniques are able to prevent identity disclosure of users but are not sufficient to prevent the disclosure of sensitive information of users. In this direction, a number of techniques for preserving the sensitive information of social network users have been proposed. Although these techniques have shown reasonably good results to achieve anonymity, but they also lead to a substantial change in the original structure of the OSNs. In this article, the problems of preventing sensitive attribute disclosure and reducing the noisy nodes have been addressed by perturbing the sensitive attributes. Existing research uses L-diversity for preventing sensitive attribute disclosure resulting in skewness and similarity attacks. We have addressed the skewness attacks by removing the duplicate noisy nodes from the final dataset to be published for stakeholders by the OSN service providers. All the information of duplicate nodes has been stored in a table named Reference Attribute Table (RAT). This table will be accessible only to the service providers for the purpose of de-anonymizing the data of users. The proposed technique has been extensively evaluated using five metrics viz. APL, ACSPL, RRTI, number of noisy nodes, and information loss using four real-time datasets collected for OSNs namely CORA, ARNET, DBLP, and Twitter. Results of evaluation parameters viz. APL and RRTI show that there is less change in the structure of datasets after anonymization. Results of ACSPL show that our proposed technique is able to preserve sensitive attributes in the datasets. The maximum number of noisy nodes amongst all four datasets is 5.4% and the maximum information loss is 2.2%. Evaluation results make it evident that our proposed technique ensures privacy preservation with less loss of information and thus preserving the utility of published data.

ESPOUSAL OF ONLINE SOCIAL NETWORKS (OSNS) IN TOURISM SUPPLY CHAIN NETWORK (TSCN) DURING COVID-19

The COVID-19 epidemic has broken the original business network structure and globally affected the tourism supply chains. Online social networks (OSNs) have become a necessary component of ICT-enabled services, affecting every area of human existence. The espousal of OSNs into tourism supply chain networks during a pandemic is crucial. However, scarce studies have been conducted on the espousal of OSNs in tourism supply chain networks. The study developed a research model based on the IS success model, uses and gratifications (U&amp;G) theory, institutional theory, and transaction cost theory to analyze the espousal of OSNs in the tourism supply chain network (TSCN) during COVID-19. The study employed structural equation modeling (SEM) to examine 99 data acquired via online surveys from supply chain specialists in the travel and hospitality sectors. The research model outperforms better and fulfills all model fitness requirements. The research found that tourism supply chain experts adopt online social networks to address supply and demand disruptions caused by COVID-19. Utilitarian features (e.g., supply chain perceptibility), technological features (e.g., system quality), and cost-benefit aspects substantially influence the espousal of OSNs in the tourism supply chain network. Espousals of OSNs improve tourism supply chain performance during Covid-19. As a result of this research, tourism supply chain management, MIS, and social media literature will be enriched by introducing OSNs in the tourism supply chain environment. The research will also provide adequate implications to supply chain managers and OSNs service provider to adopt OSNs in the tourism supply chain during COVID-19.

A Comprehensive Analysis of Privacy-Preserving Solutions Developed for Online Social Networks

Owning to the massive growth in internet connectivity, smartphone technology, and digital tools, the use of various online social networks (OSNs) has significantly increased. On the one hand, the use of OSNs enables people to share their experiences and information. On the other hand, this ever-growing use of OSNs enables adversaries to launch various privacy attacks to compromise users’ accounts as well as to steal other sensitive information via statistical matching. In general, a privacy attack is carried out by the exercise of linking personal data available on the OSN site and social graphs (or statistics) published by the OSN service providers. The problem of securing user personal information for mitigating privacy attacks in OSNs environments is a challenging research problem. Recently, many privacy-preserving solutions have been proposed to secure users’ data available over OSNs from prying eyes. However, a systematic overview of the research dynamics of OSN privacy, and findings of the latest privacy-preserving approaches from a broader perspective, remain unexplored in the current literature. Furthermore, the significance of artificial intelligence (AI) techniques in the OSN privacy area has not been highlighted by previous research. To cover this gap, we present a comprehensive analysis of the state-of-the-art solutions that have been proposed to address privacy issues in OSNs. Specifically, we classify the existing privacy-preserving solutions into two main categories: privacy-preserving graph publishing (PPGP) and privacy preservation in application-specific scenarios of the OSNs. Then, we introduce a high-level taxonomy that encompasses common as well as AI-based privacy-preserving approaches that have proposed ways to combat the privacy issues in PPGP. In line with these works, we discuss many state-of-the-art privacy-preserving solutions that have been proposed for application-specific scenarios (e.g., information diffusion, community clustering, influence analysis, friend recommendation, etc.) of OSNs. In addition, we discuss the various latest de-anonymization methods (common and AI-based) that have been developed to infer either identity or sensitive information of OSN users from the published graph. Finally, some challenges of preserving the privacy of OSNs (i.e., social graph data) from malevolent adversaries are presented, and promising avenues for future research are suggested.

Fact-checking a wolność słowa

Fact-checking and freedom of speech The article discusses the impact of the fact-checking process on freedom of speech. On the one hand, it was pointed out that the verification of the facts by specialized organizations, for various reasons, cannot be regarded as a fully reliable way of distinguishing between truth and falsehood in socially important matters. The findings made within the framework of fact-checking often fit into the public debate by taking a partisan position on a specific issue, and not so much objectively determining the truthfulness of certain statements formulated in public discourse. On the other hand, it was noted that fact-checking, although it does not undermine the freedom of speech – on the contrary, being an expression of it – is at the basis of the decisions of online social networking services, which may be viewed as an interference with the freedom of expression. While labeling content as untrue or misleading is not a violation of the freedom of speech of people formulating or disseminating it, removing such content from social networking services as well as blocking and obstructing access to legal content considered to be disinformation does constitute the infringement of freedom of expression.

A clustering-based topic model using word networks and word embeddings

Online social networking services like Twitter are frequently used for discussions on numerous topics of interest, which range from mainstream and popular topics (e.g., music and movies) to niche and specialized topics (e.g., politics). Due to the popularity of such services, it is a challenging task to automatically model and determine the numerous discussion topics given the large amount of tweets. Adding on this complexity is the need to identify these topics with the absence of prior knowledge about both the types and number of topics, while having the requirement of the relevant technical expertise to tune the numerous parameters for the various models. To address this challenge, we develop the Clustering-based Topic Modelling (ClusTop) algorithm that first constructs different types of word networks based on different types of n-grams co-occurrence and word embedding distances. Using these word networks, ClusTop is then able to automatically determine the discussion topics using community detection approaches. In contrast to traditional topic models, ClusTop does not require the tuning or setting of numerous parameters and instead uses community detection approaches to automatically determine the appropriate number of topics. The ClusTop algorithm is also able to capture the syntactic meaning in tweets via the use of bigrams, trigrams, other word combinations and word embedding techniques in constructing the word network graph, and utilizes edge weights based on word embedding. Using three Twitter datasets with labelled crises and events as topics, we show that ClusTop outperforms various traditional baselines in terms of topic coherence, pointwise mutual information, precision, recall and F-score.

PeGraph: A System for Privacy-Preserving and Efficient Search Over Encrypted Social Graphs

With the widespread adoption of cloud computing, it is increasingly popular for online social network (OSN) service providers to leverage the public cloud as a back-end to manage their services for the cloud&#x2019;s well-understood benefits. However, the cloud is also notoriously subject to a wide attack surface, making it an imperative need to embed security in the cloud-backed OSN service from the very beginning. In light of this, in this paper, we design, implement, and evaluate PeGraph, the first system simultaneously allowing private, efficient, and rich queries over encrypted social graphs. PeGraph is aimed at safeguarding the confidentiality of the social graph at the cloud, while preserving the functionality of social search, a key enabler for quality OSN services like friend discovery and user targeting. PeGraph is built from a delicate synergy of insights from social graph modelling and lightweight cryptography such as searchable encryption and additive secret sharing, supporting rich social search queries like exact queries, fuzzy queries, and mixed queries. PeGraph also allows the cloud to obliviously render the encrypted social search results in a ranked order according to their importance, as per users&#x2019; preferences. Extensive experiments demonstrate that PeGraph can securely process a wide range of practical social search queries within 1 second, over a real-world social graph consisting of millions of entities.

Social Engineering Attacks on Facebook – A Case Study

Background/Purpose: Facebook is an American business that offer online social networking services. Facebook was founded in 2004 by Harvard University freshmen Mark Zuckerberg, Eduardo Saverin, Dustin Moskovitz, and Chris Hughes. Free access to Facebook enables new users to create profiles, upload photos to existing groups, and start new ones. Every user's profile page has a Timeline area where they can upload material and their social network connections may reply with messages and Status updates informing them of their current location or condition. Additionally, Facebook includes a function called News Feed that notifies users of updates to their friends' profiles and statuses. Users can communicate with one another and exchange private messages using Facebook Messenger. Additionally, Facebook users may express their approval of a type of content by clicking the "Like" button. Every day, more than a billion people use Facebook, making it the most common social network on the planet. Menlo Park, California, is where the company's headquarters are located. Objective: To analyse how Facebook is misused and turned into an attack platform, in order to get sensitive information that can be used to create an attack profile against an individual. Design/Methodology/Approach: SWOT framework is being used to analyse and display information gathered from scholarly publications, web articles, and other sources. Findings/Results: Social Engineering Attacks using Facebook help the attackers to steal sensitive private information from unaware users. Using a false profile is one of the most frequent techniques to execute a large-scale data harvesting attack. Cyber Criminals use Facebook as the main target for social engineering attacks because of its high number of users and popularity. Originality/Value: This paper study gives a brief overview of Social Engineering Attacks on Facebook based on a variety of data collected. Paper Type: Case study-based Research Analysis

Факторы, взаимосвязанные с ростом потребления алкоголя в первые месяцы пандемии COVID‑19 среди пользователей социальных онлайн‑сетей в России

The significant proportion of the Russian population are active online social media users. Changes in alcohol consumption in this target group during the COVID-19 pandemic remain understudied. The aim of this survey was to investigate changes in alcohol consumption and factors associated with the increase in alcohol use among online social media users in Russia during the first months of the COVID-19 pandemic. An online survey was conducted among 1,518 users of online social networking services popular in Russia from June to September 2020. The survey revealed that 35.4% of men and 25.6% of women started drinking more frequently during the first months of the pandemic; 24.9% of men and 17.7% of women increased their usual consumption (volume) of alcohol on a typical drinking occasion, whereas 28.5% of men and 27.9% of women increased the frequency of heavy episodic drinking. Adjusted binary logistic regression analysis revealed a positive association between the increase in the frequency of alcohol consumption and the following factors: age from 18 to 29 years (OR: 1.710; 95% CI: 1.002–2.917), severe restrictions in everyday private life (OR: 3.127; 95% CI: 1.011–9.675) and severe negative professional or financial consequences due to the spread of SARS-CoV-2 (OR: 2.247; 95% CI: 1.131–4.465). The odds of an increase in the frequency of heavy episodic drinking were more than twice higher (OR: 2.329; 95% CI: 1.001–5.428) among those who had experienced severe negative consequences of the pandemic to their professional and financial situation. Higher typical frequency and usual consumption (volume) of alcohol on a typical drinking occasion and higher typical frequency of heavy episodic drinking before the pandemic were positively significantly associated with the increase in these parameters of alcohol consumption during the first months of the pandemic. In times of large-scale epidemics and public health crises, it is advisable to consider the possibility of implementing screening and brief interventions, including via online social media, to prevent problems associated with alcohol use.

Differential Private Social Network Publication and Persistent Homology Preservation

Online social networks (OSNs) service providers share and analyze users’ data for better performance. Hence, they are responsible for the protection of sensitive information. Previous researchers proposed several anonymization techniques for OSN data. Some anonymization techniques based on differential privacy claim to preserve privacy and graph utility under certain graph metrics. However, these graph utility metrics can partially describe the whole graph. In this paper, we employ persistent homology to have a comprehensive description of the OSN graph utility. The proposed scheme novelly preserves the persistent structures and differential privacy. In the proposed scheme, we employ the adjacency matrix model as the graph abstraction model. To strengthen privacy protection, we add exponential noise to the adjacency matrix. We then find the number of adding/deleting edges under the guidance of differential privacy. To preserve persistent homology, we collect edges along with the persistent structures. The proposed scheme carefully perturbs the edges while preserving those structures. Two anonymization sub-schemes, PHDP and rPHDP, have been proposed to balance the computation complexity and utility preservation. The evaluation results show that the proposed scheme outperforms other traditional anonymization schemes under graph utility metrics and graph application metrics.

Evaluating Outcomes of a Social Media-Based Peer and Clinician-Supported Smoking Cessation Program in Preventing Smoking Relapse: Mixed Methods Case Study.

BackgroundSmoking relapse prevention after completion of a smoking cessation program is highly germane to reducing smoking rates.ObjectiveThe purpose of this study was to evaluate the 1-year outcomes of a social media–based and peer and clinician-supported smoking cessation program on Facebook and examine communication patterns that could support smoking cessation and identify risk of relapse.MethodsWe used a mixed methods case study evaluation approach featuring a single-case holistic design. We recruited volunteers who signed up after successful completion of a 12-week clinical smoking cessation program in a general medicine department in Japan. Participants contemporaneously accessed a closed Facebook page, and we analyzed their posts including text and emoticons. We used joint display analysis, which involved iterative structuring and restructuring construct-specific tables with both types of data to find the most effective approach for integrating the quantitative results with the qualitative results of content analysis.ResultsOne successful participant and 2 relapsed participants were analyzed to explore the specific patterns of postings prior to relapse. Decisive comments about quitting smoking were common among participants, but encouraging messages for peers were more common from the successful participant. Comments seeking social support and reassurance were warning signs of relapse. Conflicted comments also may be a warning sign of relapse risk.ConclusionsThese findings based on a mixed methods case study of a social media platform supporting smoking cessation could be used to guide messaging in other online social networking service communities after a smoking cessation program to help reduce smoking relapse.Trial RegistrationUMIN Clinical Trials Registry UMIN000031172; https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000035595