Information mining and similarity computation for semi- / un-structured sentences from the social data

In recent years, with the development of the social Internet of Things (IoT), all kinds of data accumulated on the network. These data, which contain a lot of social information and opinions. However, these data are rarely fully analyzed, which is a major obstacle to the intelligent development of the social IoT. In this paper, we propose a sentence similarity analysis model to analyze the similarity in people’s opinions on hot topics in social media and news pages. Most of these data are unstructured or semi-structured sentences, so the accuracy of sentence similarity analysis largely determines the model’s performance. For the purpose of improving accuracy, we propose a novel method of sentence similarity computation to extract the syntactic and semantic information of the semi-structured and unstructured sentences. We mainly consider the subjects, predicates and objects of sentence pairs and use Stanford Parser to classify the dependency relation triples to calculate the syntactic and semantic similarity between two sentences. Finally, we verify the performance of the model with the Microsoft Research Paraphrase Corpus (MRPC), which consists of 4076 pairs of training sentences and 1725 pairs of test sentences, and most of the data came from the news of social data. Extensive simulations demonstrate that our method outperforms other state-of-the-art methods regarding the correlation coefficient and the mean deviation.     

Predicting motorcyclists’ intentions to speed: Effects of selected cognitions from the theory of planned behaviour, self-identity and social identity

This study sought to identify cognitive predictors of motorcyclists’ intentions to speed using a model that comprised selected constructs from the theory of planned behaviour (TPB), supplemented with constructs from identity theory and social identity theory. Participants (N = 110) were sampled from motorcycle clubs in Scotland and they completed web-based questionnaire measures of all cognitive variables, operationalized with respect to speeding on both 30 mph urban roads and 70 mph dual carriageways and motorways. In support of the TPB element of the model, affective attitude and perceived controllability accounted for significant variance in intention to speed on each road type. The identity constructs accounted for additional variance in intentions to speed on 70 mph roads. The significant independent predictors of speeding intentions on 30 mph roads were affective attitude and perceived controllability. For 70 mph roads, the independent predictors of intention were affective attitude, self-identity, perceived group norm, group identification, and an interaction between perceived group norm and group identification. Consistent with predictions derived from social identity theory, decomposition of the interaction showed that perceived group norm had an increasing effect on intention with increases in group identification. Implications for theory development and safety interventions are discussed.     

包装生态理论研究

提出了包装生态的概念,构造了包装生态理论的框架,论述了其特定内涵及其它的研究的经济价值与社会意义。     

大规模数据下的社交网络结构洞节点发现算法研究

随着社会网络数据规模的递增,结构洞节点计算涉及的计算量呈几何级增长,如何构建有效的并行化算法并缩短算法运行的时间成为当前研究的难点。针对大规模数据量下结构洞节点发现算法的不足,利用并行化思想设计实现了基于MapReduce的结构洞节点发现算法。该算法通过DBLP,YouTube和Califonia公路网这3组规模不同的数据集在Hadoop集群上运行的实验结果表明,增加DataNode机器节点的数量能够缩短算法运行的时间,提高运行效率且具有良好的并行加速比和扩展性能。     

Some of these things are not like the others: Examining motivations and political predispositions among political Facebook activity

Political engagement via social media has evolved, and web sites including Facebook continue to be a place for individuals, especially young ones, to engage politically. Because politics on social media is diverse, it makes sense that the reasons for participating in it vary. In addition, because current events information and political news is accessible via social media, the role of attention to traditional news sources in this type of political engagement is debatable. The study takes up the opportunity to address these questions by examining young people’s attention to television, print, and online news, their engagement with four Facebook political activities, and their psychological motivations for using the website politically just prior to the 2012 U.S. Presidential election. The results suggest that the primary motivations for using Facebook politically are not universal, and indeed vary by activity. They revolve around connecting with others socially, sharing information with others, and presenting oneself to others. In addition, attention to offline and online news largely do not matter. The study moves research forward by describing the variety of psychological predispositions some Facebook users bring to their political engagement with the web site, and how these predispositions vary across different Facebook political behavior.     

基于社会规范准则和联合抵制的节点激励机制研究

P2P网络中的节点由于固有的理性将产生个人利益与系统性能相冲突的搭便车行为,从而极大地降低网络的性能和效用。在社会规范的基础上结合联合抵制敌我规则的思想,建立了一套应用于P2P网络的社会规范准则模型,该模型惩戒违反社会规范准则的节点,激励节点选择合作策略,并通过博弈收益分析给出模型均衡于合作策略的条件。仿真实验结果表明,该模型能够有效地激励节点协作和抑制节点搭便车行为。     

面向微博话题传播的重要节点测量研究

为了发现在微博网络中对话题传播有巨大影响力的用户,从网络的拓扑结构出发,对微博平台上话题信息的传播进行了研究,测量了话题传播的网络拓扑结构,并利用紧密中心度和介数中心度对传播过程中参与的用户进行了影响力测量。根据测量分析结果,利用随机游走思想,将两种方法进行优化,计算出一个新的参数叫扩张比,用来评价用户在整个话题传播过程中的影响力,实验结果表明优化后的方法能够有效地发现整个网络中影响力最大的重要节点。研究结果有助于控制话题的传播过程,实现网络营销的利益最大化,以及提供研究个人影响力最大化问题新的思路。     

Managing cooperation in e-business systems

E-Business management involves monitoring and controlling all forms of business transactions conducted over the Internet, extranets, and related communications technologies and services. As such, it includes the management of networks, systems, and software applications. E-Business management is beginning to depend increasingly on knowledge of the cooperative aspects of partners in a business chain and the cooperative aspects of stake-holders in e-business operations. The study of cooperation offers many opportunities to apply social network analyses to derive software solutions for the management of e-business. This article provides a methodology and case study that recognises the dimension of cooperation among a multiplicity of organisations, coined “Awareness-based Cooperative Management.” It is aimed towards the design or re-engineering of effective e-business management systems, where the key concept involves the degree of awareness held by e-business stake-holders. Awareness is defined in terms of stake-holder interactions and artefacts used in those interactions such as buyer specifications, requests for proposals, offers, service level agreements, and the like. Since awareness is an indispensable, albeit an inherently vague concept, we cast it and reason about it with the apparatus of fuzzy logic.

基于社交网络的群体信任算法

社交网络(Social Network Service,SNS)中群体之间的信任关系是广泛存在的,目前大部分信任模型的研究基本只涉及一对一之间的个体信任关系,并没有充分考虑一对多、多对一以及多对多之间的群体信任关系。在现有信任模型研究的基础上,给出一种群体信任算法。该算法根据社交网络中群体的特点,将交互的两个群体抽象为两个群体节点,将复杂的多种信任关系转化为一对一之间的信任关系,从而对群体间的信任关系进行描述和度量。仿真结果表明,该算法能合理地度量与计算每个节点在群体中的可信度以及群体间的直接信任度。     

开源软件社区开发者偏好合作行为研究

着重从开发者角度出发,先对SourceForge.net开源社区项目与开发者数量增长情况进行统计分析,以见证社区的快速发展;随后以两个月为时间段分析新增开发者、合作的数目,并将开发者之间新建的合作细分为4种情况,探析4种合作方式情况下的差异,进而判断社区开发者优先选择合作方式的顺序;最后针对新开发者与社区已有开发者之间的合作,分析了新开发者的合作偏好与已有开发者的度数中心性、介数中心性和接近中心性,以及他们的开发项目数与之前项目中角色的关系,发现新成员优先选择与介数中心性或度数中心性大的已有开发者合作,且这些开发者整体上都具有多次开发经验并在开发过程中担任过特定角色。研究结果有利于优化群体软件开发过程,为提高群体软件开发效率与质量水平奠定了基础。