Social Network Messages Research Articles

Discovery of repost patterns by topic analysis in enterprise social networking

PurposeAn increasing number of users are inspired by enterprises to repost social media messages, which greatly contributes to the dissemination of such messages in an online social network. The purpose of this paper is to discover the repost patterns of users regarding enterprise social media messages to help enterprises improve information management abilities for social media.Design/methodology/approachThis paper proposes a novel method to discover the repost patterns of users in enterprise social networking (ESN) at the macro-level through topic analysis. Specifically, it proposes the message-diversity metric to measure the latent topic diversity degree of the social media messages. Through this technique, the paper analyzes the message-diversity characteristics of the enterprise social media messages and then explores the repost patterns of users.FindingsThe experimental results show that a high repost rate is more prominent for the messages with diverse latent topics, where message-diversity is as high as 0.5.Practical implicationsThe findings have great potential in several management areas, such as employing social media marketing, predicting popular messages, helping enterprises strengthen their online presence, and gathering more potential customers.Originality/valueThis study explores how the repost patterns of users in ESN can be determined through general macro-level behavior of users instead of their micro-level processes. The patterns can also lead to a deeper understanding of which contents can drive people to diffuse information. This study gives an important insight into the information behavior of social media users for enterprise management researchers.

The Effect of Social Network and Short Messages through E-Content on Reducing Negative Thoughts in Women

Background Nowadays, there is an ongoing development in virtual social networks and their application for patients' support, diagnosis, self-care, and education. On the other hand, applying short messages as the easiest, simplest, and cheapest way of presenting information would be helpful in this regard. Thus, in this study the effect of social network and sending short messages was assessed on negative thinking status of women. Methods This was an experimental study with pretest-posttest design performed in 2015. Out of 1165 women in Mohajeran city, 75 were randomly assigned into three groups of social network, short message, and control. The participants received a compact disc containing e-content about reducing negative thoughts. They filled out the Crandell cognition inventory (CCI) before and immediately after the intervention and also one month later for assessing their negative thoughts. A Telegram group was established for the social network group while follow-up short messages were sent for the other intervention group. SPSS V.21 was used for data analysis by paired t test, one way analysis of variance, analysis of covariance and repeated measures tests. Validity (in terms of content and structure) of the questionnaire was confirmed by comments from experts and professors and Bartlett test (KMO = 0.846, p and lt; 0.001); the reliability was confirmed by Cronbach’s alpha coefficient (0.69) and test-retest coefficient (0.928). Results There were significant differences between pretest and posttest scores in social network, short message, and control groups (P value 0.45, 0.001 and lt; 0.001 and lt; respectively). There were also significant differences between pretest and follow-up scores in the abovementioned groups (P value 0.003, 0.012, 0.001 respectively). There was no significant difference in the follow-up scores between three groups (P = 0.917). Conclusions The results showed that multimedia e-content merely would reduce participants’negative thoughts. Therefore, providing multimedia e-content could be beneficial in improving the effectiveness of public health education.

A genetic-algorithm-based information evolution model for social networks

the existing information diffusion models focus on analyzing the spatial distribution of certain pieces of messages in social networks. However, these conventional models ignored another important characteristic of diffusion: gradually changing of message contents due to the `new' and `comment' mechanisms. A novel genetic-algorithm-based information evolution model is proposed to reproduce both the diffusion and development process of information in social networks. This model firstly proposes a five-tuple to represent three types of topics: independent, competitive and mutually exclusive. Furthermore, it adopts mutation operator and forms new crossover and mutation rules to simulate four typical interactions between individuals, which bring the advantage of reproducing the information evolution process in both popularity and content. A series of experiments tested on public datasets demonstrate that: (1) independent and competitive topics of information rarely affect each other while mutually exclusive topics significantly suppress the diffusion processes of each other; (2) lower mutation probability leads to decreasing of final information amount. The experimental results show that our evolution model is more reasonable and feasible in demonstrating the evolution of information in social networks.

What makes it likeable? A study on the reactions to messages in a digital social network: the case of Facebook in Farsi.

BackgroundAfter a piece of information is put into a network, its fate depends on the behaviors of the nodes of the network; nodes that are equipped with the hardware and software of the age of information and are more powerful than any time in the past. This study suggests that a useful research for communication, marketing and advertising would be one that looks for patterns in the reactions of the nodes toward different pieces of information.ResultsThis study has used Facebook to see how people have reacted to different types of messages in terms of liking, sharing and commenting. Rather than looking for universal, generalizable patterns we have tried to examine the practicality of the proposed method. The practical aspect of the study comes after a short theoretical discussion on the issue of flow of information in a digital world. The results revealed dozens of significant relations between the examined variables.ConclusionsThis study, its theoretical discussion and results suggest that it would be practical to study the relations between the characteristics of Facebook messages and the type of reactions (liking, sharing and commenting) that they attract.

Video gaming in a hyperconnected world: A cross-sectional study of heavy gaming, problematic gaming symptoms, and online socializing in adolescents

AimsExamining online social interactions along with patterns of video gaming behaviors and game addiction symptoms has the potential to enrich our understanding of disorders related to excessive video game play. MethodsWe performed latent class analysis in a sample of 9733 adolescents based on heavy use of games, social networking and instant messaging, and game addiction symptoms. We used latent class regression to determine associations between classes, psychosocial well-being and friendship quality. ResultsWe identified two types of heavy gaming classes that differed in probability of online social interaction. Classes with more online social interaction reported fewer problematic gaming symptoms than those with less online social interaction. Most adolescents estimated to be in heavy gaming classes had more depressive symptoms than normative classes. Male non-social gamers had more social anxiety. Female social gamers had less social anxiety and loneliness, but lower self-esteem. Friendship quality attenuated depression in some male social gamers, but strengthened associations with loneliness in some male non-social gamers. ConclusionsIn adolescents, symptoms of video game addiction depend not only on video game play but also on concurrent levels of online communication, and those who are very socially active online report fewer symptoms of game addiction.

Shall I post this now? Optimized, delay-based privacy protection in social networks

Despite the several advantages commonly attributed to social networks such as easiness and immediacy to communicate with acquaintances and friends, significant privacy threats provoked by unexperienced or even irresponsible users recklessly publishing sensitive material are also noticeable. Yet, a different, but equally significant privacy risk might arise from social networks profiling the online activity of their users based on the timestamp of the interactions between the former and the latter. In order to thwart this last type of commonly neglected attacks, this paper proposes an optimized deferral mechanism for messages in online social networks. Such solution suggests intelligently delaying certain messages posted by end users in social networks in a way that the observed online activity profile generated by the attacker does not reveal any time-based sensitive information, while preserving the usability of the system. Experimental results as well as a proposed architecture implementing this approach demonstrate the suitability and feasibility of our mechanism.

A Web-Based Psychosocial Intervention for Family Caregivers of Older People: Results from a Mixed-Methods Study in Three European Countries.

BackgroundInformal caregiving is the main source of care for older people in Europe. An enormous amount of responsibility and care activity is on the shoulders of family caregivers, who might experience problems in their psychological well-being and in reconciling caregiving and their personal sphere. In order to alleviate such burden, there is increasing interest and growing research in Europe on Web-based support addressing family caregivers and their needs. However, the level of development and penetration of innovative Web-based services for caregivers is still quite low and the access to traditional face-to-face services can be problematic for logistic, availability, and quality reasons.ObjectiveAs part of the European project INNOVAGE, a pilot study was conducted for developing and testing a Web-based psychosocial intervention aimed at empowering family caregivers of older people in Italy, Sweden, and Germany. The program offered information resources and interactive services to enable both professional and peer support.MethodsA mixed-methods, sequential explanatory design was adopted. Caregivers’ psychological well-being, perceived negative and positive aspects of caregiving, and social support received were assessed before and after the 3-month intervention. Poststudy, a subsample of users participated in focus groups to assist in the interpretation of the quantitative results.ResultsA total of 94 out of 118 family caregivers (79.7%) from the three countries used the Web platform at least once. The information resources were used to different extents in each country, with Italian users having the lowest median number of visits (5, interquartile range [IQR] 2-8), whereas German users had the highest number (17, IQR 7-66) (P<.001). The interactive services most frequently accessed (more than 12 times) in all countries were the social network (29/73, 40%) and private messages (27/73, 37%). The pretest-posttest analysis revealed some changes, particularly the slight worsening of perceived positive values of caregiving (Carers of Older People in Europe [COPE] positive value subscale: P=.02) and social support received (COPE quality-of-support subscale: P=.02; Multidimensional Scale of Perceived Social Support subscale: P=.04), in all cases with small effect size (r range -.15 to -.18). Focus groups were conducted with 20 family caregivers and the content analysis of discussions identified five main themes: online social support, role awareness, caregiving activities, psychological well-being, and technical concerns. The analysis suggested the intervention was useful and appropriate, also stimulating a better self-efficacy and reappraisal of the caregivers’ role.ConclusionsThe intervention seemed to contribute to the improvement of family caregivers’ awareness, efficacy, and empowerment, which in turn may lead to a better self-recognition of their own needs and improved efforts for developing and accessing coping resources. A major implication of the study was the finalization and implementation of the InformCare Web platform in 27 European countries, now publicly accessible (www.eurocarers.org/informcare).

Emoticon based Sentiment Analysis using Parallel Analytics on Hadoop

Objectives: The major objective of this approach is to provide a sentiment analysis architecture that can operate on streaming big data to provide effective results at tolerable time limits. Method/Analysis: An effective mechanism for analyzing the social networking messages to identify the sentiment levels has been proposed. This is a generic model that can be used for product or organization specific analysis. Further, this method also considers emoticons, which form the integral part of any expressed emotion. The entire process is carried out in Hadoop Architecture using the MapReduce paradigm. Findings: Experiments have been conducted on a Hadoop cluster. Inputs were passed from a client node connected to the cluster. Map Reduce programs were executed in six phases, each phase performing a single task in map and reduce phases. The ROC plot exhibits excellect accuracies with most of the points being clustered in the top left region, some even approaching 100% effectiveness. Even the PR plots exihibits similar efficiency scenario with high positive retrieval rates. Incorporating the emoticons plays a major role in increasing the efficiency of this approach. Novelty/Improvement: This approach uses Hadoop based implementations, involving Map and Reduce operations. Using this approach provides data scalability and improves the efficiency of the results in acceptable time limits.

A comparison of classifiers and features for authorship authentication of social networking messages

SummaryThis paper develops algorithms and investigates various classifiers to determine the authenticity of short social network postings, an average of 20.6 words, from Facebook. This paper presents and discusses several experiments using a variety of classifiers. The goal of this research is to determine the degree to which such postings can be authenticated as coming from the purported user and not from an intruder. Various sets of stylometry and ad hoc social networking features were developed to categorize 9259 posts from 30 Facebook authors as authentic or non‐authentic. An algorithm to utilize machine‐learning classifiers for investigating this problem is described, and an additional voting algorithm that combines three classifiers is investigated. This research is one of the first works that focused on authorship authentication in short messages, such as postings on social network sites. The challenges of applying traditional stylometry techniques on short messages are discussed. Experimental results demonstrate an average accuracy rate of 79.6% among 30 users. Further empirical analyses evaluate the effect of sample size, feature selection, user writing style, and classification method on authorship authentication, indicating varying degrees of success compared with previous studies. Copyright © 2016 John Wiley &amp; Sons, Ltd.

A personalized interface for supporting multi-users in smart TVs

Smart TVs provide various forms of entertainment including live TV, games, messaging and web search. Though a smart TV is usually shared by all family members, personalization is also necessary. For example, social network service (SNS), e-mail and messaging require privacy, and TV channel navigation will be efficient if each user's preference is separately managed. This paper presents a personalized interface for smart TV with multiple users. A smart TV platform is developed by integrating hardware and software systems, and then an efficient interface on that platform is designed to support personalization. Specially, the proposed interface focuses on a personalized TV channel navigation scheme as current channel navigation systems do not consider each user's preference and thus inefficient to navigate large numbers of TV channels. The proposed scheme addresses this problem by providing personalized channel lists for individual users. It has been implemented on a smart TV development platform, and assessed by simulation and a user test. Experimental results show that the proposed navigation scheme significantly reduces the channel changing delay. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Detection of Spam Messages in Social Networks based on SVM

Detection of Spam Messages in Social Networks based on SVM

Sports lottery game prediction system development and evaluation on social networks

Purpose – The purpose of this paper is to establish a social-network sp.orts lottery system to support users in predicting and simulating sports lottery betting. The community data were generated to support user decision and featured instant game records and odds data synchronisation. Furthermore, the next development cycle were evaluated through a questionnaire. Design/methodology/approach – An extended prototype website development methodology was applied to develop the system. An online sample was collected to evaluate the function, interface, operation, and prediction designs. The χ2 test and variance analysis were used to determine the association between facets and basic demographics. Finally, the regression model was used to identify the potentially essential predictors that influence the measurement facets. Findings – The high frequency of Facebook users, sports lottery purchases, and sports game viewers prefer the ability to predict the results of future sports games as advanced decision-making functions. However, the agent-based virtual gift presentation function was the least preferred function. Research limitations/implications – The study sample was limited only to users: who used PTT and Facebook; were of uneven age, education, and gender; and none segment groups. The study sample primarily comprised Taiwanese respondents. These differences might influence the practicality and prediction bias of the designed website and related models. Practical implications – The proposed method integrates social-network messages with real-time data access by using APIs, crawler schemes, and prediction mechanisms that enable developers to devise strategies for obtaining high system satisfaction. The system can be improved by adding the results of future sports games and excluding authorised Facebook message posts. Originality/value – A social-network-based sports lottery and prediction prototyping website was evaluated through a user-preference survey regarding design functions. The measurement results indicated that users share their opinions, predictions, and personal betting results and interact with their friends.

User-driven geo-temporal density-based exploration of periodic and not periodic events reported in social networks

In this paper we propose a procedure consisting of a first collection phase of social network messages, a subsequent user query selection, and finally a clustering phase, defined by extending the density-based DBSCAN algorithm, for performing a geographic and temporal exploration of a collection of items, in order to reveal and map their latent spatio-temporal structure. Specifically, both several geo-temporal distance measures and a density-based geo-temporal clustering algorithm are proposed. The approach can be applied to social messages containing an explicit geographic and temporal location. The algorithm usage is exemplified to identify geographic regions where many geotagged Twitter messages about an event of interest have been created, possibly in the same time period in the case of non-periodic events (aperiodic events), or at regular timestamps in the case of periodic events. This allows discovering the spatio-temporal periodic and aperiodic characteristics of events occurring in specific geographic areas, and thus increasing the awareness of decision makers who are in charge of territorial planning. Several case studies are used to illustrate the proposed procedure.

E-inclusion and perception of time among elderly: Russian regional perspective

Messages in online social networks can be considered as private archives (letters, photos and videos of ordinary people). But digital writing and images have no physical substance. These new recourses impact social time and collective memory. In this paper, we present the results of empirical study the perception of time of the Russian elderly (60+) who use online social networks. We have examined the important trends which are connected with perception of time among the elderly (disembodiment, linearity and synchronisation of time). We have analysed vectors of time and discussed the construction of past as possible everyday practice for contemporary senior users.

E-inclusion and perception of time among elderly: Russian regional perspective

Messages in online social networks can be considered as private archives (letters, photos and videos of ordinary people). But digital writing and images have no physical substance. These new recourses impact social time and collective memory. In this paper, we present the results of empirical study the perception of time of the Russian elderly (60+) who use online social networks. We have examined the important trends which are connected with perception of time among the elderly (disembodiment, linearity and synchronisation of time). We have analysed vectors of time and discussed the construction of past as possible everyday practice for contemporary senior users.

RTPMF: Leveraging User and Message Embeddings for Retweeting Behavior Prediction

Understanding retweeting mechanism and predicting retweeting behavior is an important and valuable task in user behavior analysis. In this paper, aiming at providing a general method for improving retweeting behavior prediction performance, we propose a probabilistic matrix factorization model (RTPMF) incorporating user social network information and message semantic relationship. The contributions of this paper are three-fold: (1) We convert predicting user retweeting behavior problem to solve a probabilistic matrix factorization problem; (2) Following the intuition that user social network relationship will affect the retweeting behavior, we extensively study how to model social information to improve the prediction performance; and (3) We also incorporate message semantic embedding to constrain the objective function by making a full use of additional the messages’ content-based and structure-based features. The empirical results and analysis demonstrate that our method significantly outperform the state-of-the-art approaches.

High quality information extraction and query-oriented summarization for automatic query-reply in social network

In this paper, we propose a new method for automatic query-reply in social network. Information extraction and query-oriented summarization method are applied here to reply people’s query. There are few effective and commonly used methods on filtering the redundancy and noise of the raw data, which results in the poor quality of the reply. Due to the characteristics of social network messages, we pay more attention to reducing the noise and eliminating the redundancy of the messages to ensure the quality of the final reply. First, we propose an information extraction method to extract high quality information from social network messages, which is based on time-frequency transformation. Second, query-oriented text summarization is implemented to generate a brief and concise summary as the final reply, which is based on the scoring, ranking and selection of sentences of high quality social network messages produced by previous step. Experimental results show that the research is effective in filtering the redundancy and noise of social network messages, the final query-reply results outperform other commonly used methods’ results in both automatic evaluation and manual evaluation. Through our approach, noise and redundancy of social network messages are effectively filtered. Certainly, our method improves the quality of the reply for people’s query.

Social networks and substance use among at-risk emerging adults living in disadvantaged urban areas in the southern United States: a cross-sectional naturalistic study

Substance use and risk-taking are common during emerging adulthood, a transitional period when peer influences often increase and family influences decrease. Investigating relationships between social network features and substance use can inform community-based prevention programs. This study investigated whether substance use among emerging adults living in disadvantaged urban areas was influenced by peer and family social network messages that variously encouraged and discouraged substance use. Cross-sectional, naturalistic field study. Lower-income neighborhoods in Birmingham, Alabama, USA with 344 participants (110 males, 234 females, ages 15-25 years; mean = 18.86 years), recruited via respondent-driven sampling. During structured interviews conducted in community locations, the Alcohol, Smoking and Substance Involvement Screening Test assessed substance use and related problems. Predictor variables were network characteristics, including presence of substance-using peers, messages from friends and family members about substance use and network sources for health information. Higher substance involvement was associated with friend and family encouragement of use and having close peer network members who used substances (Ps < 0.001). Peer discouragement of substance use was associated with reduced risk (b = - 1.46, P < 0.05), whereas family discouragement had no protective association. Social networks appear to be important in both promoting and preventing substance use in disadvantaged young adults in the United States.

Wired to mobilize: The effect of social networking messages on voter turnout

Recent scholarship has documented the effect of online social networking on political participation, a relationship hypothesized to be due to the generation of social capital. This paper tests the hypothesis that impersonal get-out-the-vote messages delivered via an online social network can increase voter turnout. Specifically, this study uses a field experiment of randomly assigned students from a large southern public university to test the effect of exposure to political messages via Facebook on the likelihood of them voting in the November 2010 election. The results indicate that encouragements to vote delivered through a social networking site can have substantively large effects on political behavior.

City-Scale Social Event Detection and Evaluation with Taxi Traces

A social event is an occurrence that involves lots of people and is accompanied by an obvious rise in human flow. Analysis of social events has real-world importance because events bring about impacts on many aspects of city life. Traditionally, detection and impact measurement of social events rely on social investigation, which involves considerable human effort. Recently, by analyzing messages in social networks, researchers can also detect and evaluate country-scale events. Nevertheless, the analysis of city-scale events has not been explored. In this article, we use human flow dynamics, which reflect the social activeness of a region, to detect social events and measure their impacts. We first extract human flow dynamics from taxi traces. Second, we propose a method that can not only discover the happening time and venue of events from abnormal social activeness, but also measure the scale of events through changes in such activeness. Third, we extract traffic congestion information from traces and use its change during social events to measure their impact. The results of experiments validate the effectiveness of both the event detection and impact measurement methods.