基于关系度的群体观点演化模型与仿真*

针对传统的连续观点动力学模型中,缺乏对观点传播过程中人与人之间关系的考虑,通过扩展Hegselmann-Krause模型,引入关系度和关系阈值,研究个体间关系程度对群体观点演化的影响以及关系度在具有观点领袖的团体中所发挥的作用。研究结果表明：在关系阈值的影响范围内,关系度有利于群体观点达成共识并能够缩短系统观点的收敛时间;另外,观点领袖的支持者越多且支持者初始观点越接近观点领袖的观点,观点演化的收敛时间越短,系统平衡时的观点值越接近观点领袖的初始观点值。     

基于关系HK模型的群体观点演化建模与仿真

针对传统HK模型中,未考虑个体间人际关系对观点阈值外个体观点交互的影响,提出一种关系HK模型,以研究关系度对群体观点演化时间和系统观点簇的影响,以及关系度在两个意见观点趋向相反的观点领袖及其支持者中发挥的作用。研究结果表明,群体中关系度的存在有利于观点达成共识,缩短系统观点演化时间。特别地,在具有观点领袖的群体中,观点领袖支持者的特征因素对系统观点演化结果起着决定性的作用,如支持者初始观点、观点阈值、关系度阈值和初始观点坚持度。当群体中存在两个意见趋向相反且彼此间没有关系度的观点领袖时,系统最终出现分裂状态,而观点领袖及其支持者之间关系度的存在,有利于系统观点达成共识。     

基于节点亲密度和影响力的社交网络舆论形成模型

针对舆论传播过程中个体交互的广泛性和个体社会影响力的差异性,在Hegselmann-Krause模型的基础上建立了社交网络舆论形成模型。新模型通过引入个体间亲密度、人际相似性和交互强度等概念,对个体交互集合进行了扩展,并对影响力权重进行了合理量化,进而构建更切合实际的观点交互规则。通过一系列仿真实验,分析了模型主要参数在舆论演化中的作用。结果表明：在不同信任阈值下,群体观点均能收敛到一致,形成舆论共识;且信任阈值越大,收敛时间越短;当信任阈值为0.2时,收敛时间仅为10。同时,扩大交互集合、提高人际相似性的作用强度会促进舆论共识的形成。此外,当无标度网络的聚类系数和平均度较高时,群体观点更容易产生趋同效应。研究结果有助于理解舆论形成的动力学过程,对社会管理者进行决策分析具有指导作用。     

基于片段的企业信任网络演化图聚类算法

针对动态信任网络中企业信任联盟的识别及演变问题,提出一种基于片段的演化图聚类（GC）算法。首先,通过考虑企业信任网络演化的时间信息来对信任网络进行编码;其次,构建划分和表示信任网络结构编码成本的评价函数,如信任联盟稳定则将该时间段内信任网络组成片段压缩表示,如联盟突变则开始新的信任网络片段并重新划分结构;最后,通过搜索最小编码成本,得到信任联盟的稳定结构和结构突变的时间点。仿真实验表明,所提算法能有效识别信任联盟及其结构的突变,且其准确性和运行效率均高于经典社区发现算法。     

以退为进，IntelliJ开源

一年一度的GNOME亚洲峰会按照惯例每年会选在亚洲的一个城市举办，第二届的GNOME亚洲峰会将于2009年11月20日至22日在越南的胡志明市召开。500名来自10个国家的GNOME领袖和开源贡献者们将共聚一堂。峰会将会为GNOME的用户、开发者、基金会成员、社区贡献者、学生、政府及企业提供一个平台，向大家介绍最新的GNOME技术以及GNOME在亚洲各地不同社区的状况。     

分层演化趋向行为的网络舆情传播模型

通过构建带有分层行为演化趋向的舆情传播模型,研究了媒体作用下分层行为舆情演变的内在规律。在参考疾病传播模型SIR（susceptible infected recovered）和带媒体干预的SIaIbR（susceptible infected-a infected-b recovered）模型基础上,提出了带有媒体干预的具有分层演化趋向行为的舆情演变模型（SI）³R,与SIR模型不同的是（SI）³R模型引入了群体分层这一概念,并且在演化过程中处于群体不同分层中的个体带有不同的演化趋势。通过对不同层次中个体的影响,媒体能够发挥更有效的作用。给出了分层演化群体模型及其动力学方程,通过数值求解,模拟了分层媒体作用对传播过程的影响以及初始分层密度对传播过程的影响。     

基于智能合约的数据共享激励机制研究

随着大数据时代的到来,构建数据共享社区成为一种促进数据收集、流通和使用的新模式,但是在传统社区组织方式下,成员由于互不信任导致不愿共享数据,且共享社区普遍缺乏有效的激励机制,从而限制了数据共享社区的发展。区块链的本质是一个分布式账本,能够提升数据共享的透明性,防止信息滥用,所有存在区块链上的数据可溯源且不可篡改,可以保证数据的归属权,这些都为成员之间的信任打下了基础。在基于区块链的数据共享社区平台上,结合演化博弈理论构建一种数据共享激励模型EGDSI,并通过复制动态力学方程与演化稳定策略分析,得出影响数据共享的关键因素与数据共享激励的3种策略。在此基础上,利用区块链智能合约技术实现安全、高效且动态可调节的数据共享模板引擎。对共享策略影响因素和智能合约激励机制进行仿真分析,结果表明,该数据共享激励机制可以有效促进用户参与数据共享,相较EGI模型,EGDSI模型能够更快地达到数据共享饱和状态。     

微博话题符号网络下的意见领袖挖掘算法研究*

随着移动互联网的快速发展,用户逐渐成为社交媒体的主导者,新媒体的迅速崛起,改变了传统的信息传播的格局以及规律,经典的大众传播理论中的意见领袖、把关人等有了新的时代意义,在一定程度上得到进一步的扩展和延伸。在现有的意见领袖的挖掘中主要是从网络结构和用户行为研究方向,没有考虑到是否真正对用户产生影响这一重要的属性,本文以符号网络作为研究工具,通过赋予用户之间的观点关系链接相应的代表支持或者反对的符号,将传统的意见领袖挖掘算法结合符号网络中的能够描述用户观点变化的符号关系,将真正对用户产生影响的意见领袖挖掘出来,从而挖掘得出更加精准有效地意见领袖。     

多社区网络上的命名博弈

为了模仿人类对新物体认知和命名的过程,提出了一种新型的命名博弈模型,它通过词汇的权重表示个体的认知程度,低权重词汇被删除模拟个体有限记忆的过程.实验发现,在单社区网络上,所有个体的词汇最终能够统一,通过总词汇数、不同词汇数和平均协议成功率的分析解释了新个体命名的演化过程.衰减因子和删除阈值的取值对于演化速度影响较大,当它们之间存在线性关系时演化收敛较快.通过将该模型应用到多社区网络模型上,发现收敛词汇数可能不唯一,会与社区数相同,且收敛词汇数的稳定性与网络社区化强度和社区内节点的平均度有关,而与社区内节点数无关.最后,使用微分动力学的方法对这种情况进行了定量分析.     

一种虚拟社区信任机制模型的构建方法

虚拟社区是网络社会化的重要产物,在众多网络应用中发展极为迅速.虚拟社区以现实社区为原型,社区成员间的交互行为很大程度上依赖于信任关系,稳定良好的信任环境对于虚拟社区的健康发展十分重要.通过分析虚拟社区的特性,结合现有实现机制的相关经验,在课题信任模型研究的基础上提出了一种基于结构化P2P网络环境的虚拟社区的信任模型构建方法.通过分析现实社会社区与虚拟社区的层次关系和映射关系,结合结构化P2P网络环境的特点和优势,使得社区构建更为真实合理,从而有效地提高了虚拟社区的运作性能.     

虚拟学习社区中意见领袖识别模型研究

虚拟学习社区是传统教育突破空间资源限制形成的便捷性学习环境,其中意见领袖是构成社区信息通路的重要角色,对其他用户有强大的影响力。为了准确识别社区中的意见领袖,构建出虚拟学习社区网络,分析各用户的中心性和社会网络角色特征,选取入度、出度、介数、特征向量中心性、用户活跃度、用户帖子转发量、用户帖子评论量等七个特征值作为筛选条件,结合基于K-means的用户聚类算法,提出基于K-means算法的意见领袖识别模型。最后,将该识别模型应用于某虚拟社区,根据各个聚类子类的特征向量,提取理论意义上的意见领袖集合。实验证明,获取意见领袖集合具有很高的准确性,识别出的意见领袖均处于中心者或桥梁位置,占据着社会网络的优势位置,在虚拟社区中承担着核心或中介等特殊作用。     

An evidence-based scheme for web service selection

Existing studies on the web service selection problem focus mainly on the functional QoS properties of the service rather than the consumer satisfaction and trust aspects. While a good QoS enhances the reputation of a service, different consumers invariably hold differing views of the service contents. Some service reputation approaches primarily consider the consumer’s prior experience of the service via opinion feedback system, may neglect the effect of social trust transition in the recommendations of others. As a result, the problem of reaching consensus on the level of consumer trust regarding service becomes one of key issues in service selection. This study proposes a trust-based service selection model to estimate the degree of consumer trust in a particular service based on the consumers’ direct experience and indirect recommendation of the service. In the proposed approach, the degree of consumer trust is correctly estimated by extending Dempster–Shafer evidence reasoning theory to the reputation computation using consumers’ direct experience and incorporating Jøsang’s belief model for solving the trust transition problem in the indirect recommendation of the service. The proposed model effectively enables deception detection by means of existing bodies of evidence, and therefore excludes the fraudulent evidence of malicious evaluators from the selection process. In addition, a quality index is proposed to help third party (TTP) examine the body of evidence and make the outranking result more reliable. Importantly, the quality index is based not only on the confidence degree of the evidence, but also on the support degree, and therefore discovers the effects of intentional negative assessments. The validity of the proposed approach is demonstrated numerically by means of two service selection examples.     

Assessing the ripple effects of online opinion leaders with trust and distrust metrics

This study evaluates the influence of opinion leaders on other users in a social network and investigates the impact of the sizes of opinion leaders on the outcome of social network marketing (SNM) campaigns when trust and distrust relationships among users are considered. In particular, we assume that SNM managers utilize one of three trust metrics (knowledge score (KS), matching coefficient (MC), and Jaccard coefficient (JC)) to reflect the strength of trust relationships among users as well as to determine the outcome of SNM campaigns in terms of connected (i.e., who are exposed to marketing campaigns) and activated users (i.e., who actually purchase a product). Our experimental results indicate that while all three simple topological metrics such as in- and out-degree and hybrid measures of in- and out-degree are very useful to identify opinion leaders, the outcome of SNM campaigns with MC trust metric is heavily affected by out-degree and the outcomes of SNM campaigns with KS and JC metrics are much more affected by in-degree. It is also noted that the total numbers of connected and activated users increase as the size of opinion leaders grows, but the net numbers of connected and activated users start to decrease after a certain size of opinion leaders. The greatest impact of distrust relationships is observed in SNM campaigns based on JC followed by MC and KS. Therefore, if SNM managers consider distrust relationships critical to estimate the success of SNM campaigns or they like to under-estimate rather than over-estimate the reach of SNM campaigns, JC trust metric is the most appropriate metric than any other metrics due to its sensitiveness to the distrust relationships among users.     

Understanding civic engagement behaviour on Facebook from a social capital theory perspective

This paper applies the social capital theory to construct a model for investigating the factors that influence online civic engagement behaviour on Facebook. While there is promising evidence that people are making concerted efforts to adopt Facebook to address social issues, research on their civic behaviour from a social capital viewpoint in the social media context remains limited. This study introduces new insights into how Facebook is shaping the landscape of civic engagement by examining three dimensions of social capital – social interaction ties (structural), trust (relational), and shared languages and vision (cognitive). The study contends that these dimensions will influence individuals’ online civic engagement behaviour on Facebook. We also argue that social interaction ties can engender trust, and shared languages and vision among its members, and that shared languages and vision can increase trust among Facebook members. Empirical data collected from 1233 Facebook users provide support for the proposed model. The results help in identifying the motivation underlying the online civic engagement behaviour of individuals in a public virtual community. The implications for theory and practice and future research directions are discussed.     

Behavior‐Based Propagation of Trust in Social Networks with Restricted and Anonymous Participation

Increasing interactions and engagements in social networks through monetary and material incentives is not always feasible. Some social networks, specifically those that are built on the basis of fairness, cannot incentivize members using tangible things and thus require an intangible way to do so. In such networks, a personalized recommender could provide an incentive for members to interact with other members in the community. Behavior‐based trust models that generally compute social trust values using the interactions of a member with other members in the community have proven to be good for this. These models, however, largely ignore the interactions of those members with whom a member has interacted, referred to as “friendship effects.” Results from social studies and behavioral science show that friends have a significant influence on the behavior of the members in the community. Following the famous Spanish proverb on friendship “Tell Me Your Friends and I Will Tell You Who You Are,” we extend our behavior‐based trust model by incorporating the “friendship effect” with the aim of improving the accuracy of the recommender system. In this article, we describe a trust propagation model based on associations that combines the behavior of both individual members and their friends. The propagation of trust in our model depends on three key factors: the density of interactions, the degree of separation, and the decay of friendship effect. We evaluate our model using a real data set and make observations on what happens in a social network with and without trust propagation to understand the expected impact of trust propagation on the ranking of the members in the recommended list. We present the model and the results of its evaluation. This work is in the context of moderated networks for which participation is by invitation only and in which members are anonymous and do not know each other outside the community. Copyright © 2014 John Wiley & Sons, Ltd.     

Simulating the spread of opinions in online social networks when targeting opinion leaders

An increasing number of people are joining online social networks. By interacting with each other, network members influence one another’s opinion. These influencing effects can be utilized by marketing. A wave of influence can be triggered by addressing only a few opinion leaders in the network. Targeting the right opinion leaders is a big challenge. This paper presents a new approach which simulates the spread of opinions when influencing certain opinion leaders. In contrast to other approaches, the influencing effects are not assumed but revealed by real data. The principles of opinion formation are detected by ant mining algorithms before they are applied to simulate the spread of opinions. The approach is applied to an online gaming community and provides valuable insights for marketing.     

Does Twitter motivate involvement in politics? Tweeting,opinion leadership,and political engagement

This paper, in order to deepen our understanding of the role of opinion leadership on Twitter, the world’s largest microblogging service, has investigated the interrelationships between opinion leadership, Twitter use motivations, and political engagement. It finds that Twitter opinion leaders have higher motivations of information seeking, mobilization, and public expression than nonleaders. It has also been found that mobilization and public-expression motivations mediate the association between perceived opinion leadership and Twitter use frequency. Most importantly, this study finds that Twitter opinion leadership makes a significant contribution to individuals’ involvement in political processes, while Twitter use itself or media use motivation does not necessarily help individuals’ political engagement.     

A new method for trust and reputation evaluation in the cloud environments using the recommendations of opinion leaders' entities and removing the effect of troll entities

Trust in the cloud environment is not written into an agreement and is something earned. In any trust evaluation mechanism, opinion leaders are the entities influencing the behaviors or attitudes of others, this makes them to be trustworthy, valid among other characteristics. On the other hand, trolls are the entities posting incorrect and unreal comments; therefore, their effect must be removed. This paper evaluates the trust by considering the influence of opinion leaders on other entities and removing the troll entities’ effect in the cloud environment. Trust value is evaluated using five parameters; availability, reliability, data integrity, identity and capability. Also, we propose a method for opinion leaders and troll entity identification using three topological metrics, including input-degree, output-degree and reputation measures. The method being evaluated in various situation where shows the results of accuracy by removing the effect of troll entities and the advice of opinion leaders.     

Understanding the effects of trust and risk on individual behavior toward social media platforms: A meta-analysis of the empirical evidence

Trust and risk have been theorized and empirically approved as the most influential factors affecting individual behavior toward social media platforms (SMPs). However, the evidence is scattered and the understanding of the effects is ambiguous. To address this problem, a rigorous and quantitative meta-analysis was conducted to investigate the empirical evidence of 43 studies in information systems research between 2006 and 2014. The findings suggested that trust and risk both had significant effects on individual behavior toward SMPs but that trust had a stronger effect. Moderating effects of trust objects (community members vs. platforms) and platform types (virtual communities vs. social networking sites) were found. Surprisingly, culture was found to exert no moderating effect. This paper contributes more generalized knowledge to social media research literature to the theory with regard to the influence of trust and risk on individual behavior toward SMPs. The knowledge serves as the foundation for future research efforts in social media. Implications for practice are discussed.