Analyzing users’ activity in online social networks over time through a multi-agent framework

The number of people and organizations using online social networks as a new way of communication is continually increasing. Messages that users write in networks and their interactions with other users leave a digital trace that is recorded. In order to understand what is going on in these virtual environments, it is necessary systems that collect, process, and analyze the information generated. The majority of existing tools analyze information related to an online event once it has finished or in a specific point of time (i.e., without considering an in-depth analysis of the evolution of users’ activity during the event). They focus on an analysis based on statistics about the quantity of information generated in an event. In this article, we present a multi-agent system that automates the process of gathering data from users’ activity in social networks and performs an in-depth analysis of the evolution of social behavior at different levels of granularity in online events based on network theory metrics. We evaluated its functionality analyzing users’ activity in events on Twitter.     

Understanding Chinese users’ continuance intention toward online social networks: an integrative theoretical model

This study explores users’ continuance intention in online social networks by synthesizing Bhattacherjee’s IS continuance theory with flow theory, social capital theory, and the unified theory of acceptance and use of technology (UTAUT) to consider the special hedonic, social and utilitarian factors in the online social network environment. The integrated model was empirically tested with 320 online social network users in China. The results indicated that continuance intention was explained substantially by all hypothesized antecedents including perceived enjoyment, perceived usefulness, usage satisfaction, effort expectancy, social influence, tie strength, shared norms and trust. Based on the research findings, we offer discussions of both theoretical and practical implications.     

Predicting the influence of users’ posted information for eWOM advertising in social networks

Many social network websites have been aggressively exploring innovative electronic word-of-mouth (eWOM) advertising strategies using information shared by users, such as posts and product reviews. For example, Facebook offers a service allowing marketers to utilize users’ posts to automatically generate advertisements. The effectiveness of this practice depends on the ability to accurately predict a post’s influence on its readers. For an advertising strategy of this nature, the influence of a post is determined jointly by the features of the post, such as contents and time of creation, and the features of the author of the post. We propose two models for predicting the influence of a post using both sources of influence, post- and author-related features, as predictors. An empirical evaluation shows that the proposed predictive features improve prediction accuracy, and the models are effective in predicting the influence score.     

Using social networks to distort users’ profiles generated by web search engines

The Internet is one of the most important sources of knowledge in the present time. It offers a huge volume of information which grows dramatically every day. Web search engines (e.g. Google, Yahoo…) are widely used to find specific data among that information. However, these useful tools also represent a privacy threat for the users: the web search engines profile them by storing and analyzing all the searches that they have previously submitted. To address this privacy threat, current solutions propose new mechanisms that introduce a high cost in terms of computation and communication. In this paper, we propose a new scheme designed to protect the privacy of the users from a web search engine that tries to profile them. Our system uses social networks to provide a distorted user profile to the web search engine. The proposed protocol submits standard queries to the web search engine; thus it does not require any change in the server side. In addition to that, this scheme does not require the server to collaborate with the users. Our protocol improves the existing solutions in terms of query delay. Besides, the distorted profiles still allow the users to get a proper service from the web search engines.     

Does cyberbullying overlap with school bullying when taking modality of involvement into account?

Education professionals and researchers are concerned by school bullying and cyberbullying because of its repercussions on students’ health and the school climate. However, only a few studies investigating the impact of school versus cyberbullying have systematically explored whether student victims and perpetrators are involved in school bullying only, cyberbullying only, or both. The aim of the present study was thus to examine the possible overlap, as well as the similarities and/or differences, between these two forms of bullying when taking modality of involvement into account. Individual interviews were conducted with 1422 junior high- and high-school students (girls = 43%, boys = 57%, mean age = 14.3 ± 2.7 years). Results showed that cyberbullying and school bullying overlapped very little. The majority of students involved in cyberbullying were not simultaneously involved in school bullying. Moreover, results indicated that psychosocial problems (psychological distress, social disintegration, general aggression) varied according to the form of bullying. Victims of school bullying had greater internalizing problems than cybervictims, while school bullies were more aggressive than cyberbullies. Given the sizable proportion of adolescents involved in bullying (school and cyber) and its significant relationship with mental health, the issue warrants serious attention from school and public health authorities.     

Older adults’ perceptions and experiences of online social support

This paper reports an investigation of older adults’ needs and preferences concerning online social support. We focused our analysis on seven different aspects of online support: Self disclosure, Deep support, Light support, Community building, Information/Facts, Off topic, and Technical issues. For each aspect we were interested in how older adults perceive this aspect of support, what they think are the similarities and differences of this aspect of support in online settings vs offline settings, and what they perceive are the advantages and disadvantages of communicating this aspect of support online. We did this by conducting detailed interviews with three groups of older adults (31 people in total) with different levels of expertise in using the internet and online communication (older adults who do not use the internet, older adults who use only email, and older adults who participate in online support communities). Interviews were transcribed verbatim and analyzed. Our findings describe older adults’ perception of different aspects of support and identify their motivation for turning to online support and the reasons for any reluctance to do so. Thus, our findings give insight into how online support communities could best be utilized to improve older people’s experience with online support.     

Exploiting users’ social relations to forward data in opportunistic networks: The HiBOp solution

Opportunistic networks, in which nodes opportunistically exploit any pair-wise contact to identify next hops towards the destination, are one of the most interesting technologies to support the pervasive networking vision. Opportunistic networks allow content sharing between mobile users without requiring any pre-existing Internet infrastructure, and tolerate partitions, long disconnections, and topology instability in general. In this paper we propose a context-aware framework for routing and forwarding in opportunistic networks. The framework is general, and able to host various flavors of context-aware routing. In this work we also present a particular protocol, HiBOp, which, by exploiting the framework, learns and represents through context information, the users’ behavior and their social relations, and uses this knowledge to drive the forwarding process. The comparison of HiBOp with reference to alternative solutions shows that a context-aware approach based on users’ social relations turns out to be a very efficient solution for forwarding in opportunistic networks. We show performance improvements over the reference solutions both in terms of resource utilization and in terms of user perceived QoS.     

Detecting and tagging users’ social circles in social media

As a media and communication platform, microblog becomes more popular around the world. Most users follow a large number of celebrities and public medias on microblog; however, these celebrities do not necessarily follow all their fans. Such one-way relationship abounds in ego network and is displayed by the forms of users’ followees and followers, which make it difficult to identify users’ real friends who are contained in merged lists of followees and followers. The aim of this paper is to propose a general algorithm for detecting users’ real friends in social media and dividing them into different social circles automatically according to the closeness of their relationships. Then we analyze these social circles and detect social attributes of these social circles. To verify the effectiveness of the proposed algorithm, we build a microblog application which displays algorithm results of social circles for users and enables users to adjust proposed results according to her/his real social circles. We demonstrate that our algorithm is superior to the traditional clustering method in terms of F value and mean average precision. Furthermore, our method of tagging social attributes of social circles gets high performance by NDCG (normalized discounted cumulative gain).     

Differentiation of online text-based advertising and the effect on users’ click behavior

Online syndicated text-based advertising is ubiquitous on news sites, blogs, personal websites, and on search result pages. Until recently, a common distinguishing feature of these text-based advertisements has been their background color. Following intervention by the Federal Trade Commission (FTC), the format of these advertisements has undergone a subtle change in their design and presentation. Using three empirical experiments, we investigate the effect of industry-standard advertising practices on click rates, and demonstrate changes in user behavior when this familiar differentiator is modified. Using three large-scale experiments (N₁ = 101, N₂ = 84, N₃ = 176) we find that displaying advertisement and content results with a differentiated background results in significantly lower click rates. Our results demonstrate the strong link between background color differentiation and advertising, and reveal how alternative differentiation techniques influence user behavior.     

Discovering mobile users’ moving behaviors in wireless networks

Wireless networks and mobile applications have grown very rapidly and have made a significant impact on computer systems. Especially, the usage of mobile phones and PDA is increased very rapidly. Added functions and values with these devices are thus greatly developed. If some regularity can be known from the user mobility behavior, then these functions and values can be further expanded and used intelligently. This paper thus attempts to discover personal mobility patterns for helping systems provide personalized service in a wireless network. The classification and the duration of each location area visited by a mobile user are used as important attributes in representing the results. A data mining algorithm has then been proposed, which is based on the AprioriAll algorithm, but different from it in several ways. Experiments are also made to show the effect of the proposed algorithm.     

Two-dimensional model of imbibition into paper-based networks using Richards’ equation

The prediction of the imbibition into two-dimensional geometries is extremely important to develop new paper-based microfluidics design principles. In this regard, a two-dimensional model using Richard’s equation, which has been extensively applied in soil mechanics, is applied in this work to model the imbibition into paper-based networks. Compared to capillary-based models, the developed model is capable of predicting the imbibition into two-dimensional domains. The numerical solution of the proposed model shows a good agreement with the experimental measurements of water imbibition into different chromatography paper-based designs. It is expected that this framework can be applied to develop new design rules for controlling the flow in paper-based microfluidics devices.     

Permanently online – Permanently connected: Explorations into university students’ use of social media and mobile smart devices

BackgroundWith the availability of mobile smart devices, many adolescents have developed the habit of being online and connected with other users almost all the time.ObjectiveThe aim of this paper is to provide a definition of being permanently online (PO) and permanently connected (PC) and to explore students’ current PO/PC behaviors.MethodsAn online survey was conducted with 178 university students in Germany to explore the intensity of their PO/PC behaviors in various social situations, the differences in being PO and being PC, students’ feelings about a possible loss of Internet access, and their online responding behaviors. We also shed some light on the associations between being PO/PC and various aspects of well-being, as well as between PO/PC and demographics and lifestyle.ResultsSmart device usage behaviors at night and behaviors in various social situations during the day indicate that PO and PC behaviors are occurring frequently. The results show that being connected to others (PC) seems to be more relevant to the participants than browsing the web (PO). Moreover, the participants expressed strong emotional responses about a temporary loss of Internet access. Coping behaviors in response to increasing number of incoming messages and permanent availability are reported.ConclusionThis exploratory study demonstrates the relevance of the concepts of being PO and PC to students, and points out further research gaps.     

The interplay between users’ intraorganizational social media use and social capital

The wide acceptance of social media by the public has caused companies try to use intraorganizational social media to increase employee work performance. However, simply implementing a platform is insufficient for success. Companies must encourage employees to use social media for work-related purposes. This study divided the use of intraorganizational social media into social- and work-related use and proposed a model based on the theory of social capital to explore the effects of social-related use on work-related use. The model was tested using a survey of users of intraorganizational microblog systems in China. The results indicate the relationships among two types of intraorganizational use and the dimensions of social capital, and that social-related use fosters work-related use directly and indirectly by enhancing social capital. These results facilitate an understanding of the value of social activities conducted using intraorganizational social media in organizations.     

Exploring users’ social responses to computer counseling interviewers’ behavior

We explore the effect of behavioral realism and reciprocal self-disclosure from computer interviewers on the social responses of human users in simulated psychotherapeutic counseling interactions. To investigate this subject, we designed a 3 × 3 factorial between-subjects experiment involving three conditions of behavioral realism: high realism, low realism, and audio-only (displaying no behavior at all) and three conditions of reciprocal self-disclosure: high disclosure, low disclosure, and no disclosure. We measured users’ feelings of social presence (Copresence, Social Attraction, and Emotional Credibility), rapport, perception of the quality of users’ own responses (Embarrassment and Self-Performance), emotional state (PANAS), perception of an interaction partner (Person Perception), self-reported self-disclosure, speech fluency (Pause Fillers and Incomplete Words), and Verbal Self-Disclosure. We observed some contradictory outcomes in users’ subjective reports. However, the results of objective data analysis demonstrated that users disclosed greater Verbal Self-Disclosure (medium level of intimacy) when interacting with computer interviewers that displayed high behavioral realism and high self-disclosure. Users also delivered more fluent speech when interacting with computer interviewers that displayed high behavioral realism.     

Skewing users’ rational risk considerations in social commerce: An empirical examination of the role of social identification

Social commerce has emerged as a new platform that enables users to conduct shopping assisted by inputs from other members and to publicly comment on transactions or products. It therefore adds a social aspect to traditional online commerce environments. Nevertheless, the role of the social facet embedded in such transactions in influencing user behaviors is not fully understood. In this study, we rely on theories of risk deterrence in decision-making and the “risky/choice shift” logic to suggest that the social identification of users regarding their community members skews the way they consider risks in decision-making on these sites. Using data from 175 users of etsy.com, we show that perceived commerce risk reduces intentions to buy from the website and that perceived participation risk curtails intentions to post comments on social commerce forums. The findings further show that the influence of these risk assessments is reduced when the degree of social identification with the website community increases; these risk considerations become negligible in decision-making processes when ’social identification is one standard deviation above the mean. Hence, users’ social identification with the social commerce website community skews their rational decision-making.     

Understanding the determinants of users’ subjective well-being in social networking sites: an integration of social capital theory and social presence theory

In order to understand the factors affecting users’ well-being perception derived from social networking sites usage, this study integrates the perspectives of social presence theory and social capital theory to develop a research model. Data were collected from 305 users of Facebook in Taiwan to test the model. The findings reveal that structural capital, relational capital, and cognitive capital exert significant influences on subjective well-being. The results also reveal that structural capital and cognitive capital have positive influence on relational capital, while structural capital influences cognitive capital significantly. The results, on the other hand, show that awareness and affective social presence are the antecedents of structural capital, whereas cognitive social presence and affective social presence influence cognitive capital significantly. Finally, affective social presence is associated with relational capital positively. Theoretical and practical implications are discussed.     

Feedback types and users’ behavior in online innovation contests: Evidence of two underlying mechanisms

Online innovation contests (OIC) provide companies, via a dedicated community, an important means to access remote knowledge and ideas of users and thereby a creative playground for fueling innovation. Our literature review shows that our understanding of the impact of diverse types of feedback on user participation, especially continued participation, and success in OIC is at a nascent stage. The present study therefore seeks to examine why and how different types of feedback influence users’ behavior in OIC, and the detailed mechanisms underlying such influences. While our results do not show a significant relationship between receiving peer dynamic feedback and user success, we find that receiving sponsor static feedback in users’ first submission is positively associated with their continued participation in OIC. Also, when compared to peer dynamic feedback, sponsor static feedback has a stronger effect on users’ continued participation. Our goal is to confer a holistic picture of how the timing, source, and form of feedback shape user continuous participation and success in OIC.     

Age differences in online social networking – A study of user profiles and the social capital divide among teenagers and older users in MySpace

The aim of this research was to investigate age differences and similarities in the use of the social networking website MySpace, to explore potential differences in social capital among older people (users over 60 years of age) compared to teenagers (users between 13 and 19 years of age). We used locally developed web crawlers to collect data from MySpace’s user profile pages, and to quantify any differences that exist in the networks of friends of older people and teenagers. Content analysis was applied to investigate differences in social activities between the two age groups on MySpace, and the way they represent themselves on their profile pages. Our findings show a social capital divide: teenagers have larger networks of friends compared to older users of MySpace. On the other hand, we found that the majority of teenage users’ friends are in their own age range (age ± 2 years), whilst older people’s networks of friends tend to have a more diverse age distribution. In addition, our results show that teenagers tend to make more use of different media (e.g. video, music) within MySpace and use more self-references and negative emotions when describing themselves on their profile compared to older people.     

How users’ participation affects reputation management systems: The case of P2P networks

In this work human factor is explored by means of agent based simulation and analyzed in the framework of a reputation management system (RMS), within a peer-to-peer (P2P) network. Reputation is about evaluating an agent’s actions and other agents’ opinions about those actions, reporting on those actions and opinions, and reacting to that report, thus creating a feedback loop. This social mechanism has been successfully used to classify agents within normative systems. The systems rely on the feedbacks given by the members of the social network in which the RMS operates. Reputation can thus be seen as an endogenous and self produced indicator, created by the users for the users’ benefit. This implies that users’ participation and collaboration is a key factor for the effectiveness a RMS.     

Is online trust and trust in social institutions associated with online disclosure of identifiable information online?

This study investigated the association between trust in individuals, social institutions and online trust on the disclosure of personal identifiable information online. Using the Internet attributes approach that argues that some structural characteristics of the Internet such as lack of social cues and controllability are conducive to a disinhibitive behavior it was expected that face to face trust and online trust will not be associated. In addition, it was expected that from the three components of trust, online trust only will be associated with the disclosure of identifiable personal information online. A secondary analysis of the 2009 Pew and American Life of Internet users (n = 1698) survey was conducted. In contrast with the Internet attribute approach the effect of trust in individuals and institutions was indirectly associated with the disclosure of identifiable information online. Trust in individuals and institutions were found to be associated with online trust. However, online trust only, was found to be associated with the disclosure of personal identifiable information. While trust online encourages the disclosure of identifiable information, perception of privacy risks predicted refraining from posting identifiable information online. The results show a complex picture of the association of offline and online characteristics on online behavior.