在线社交网络的UNI64采样方法

在对社交网络采样方法进行研究时,常以拒绝-接受采样法得到的样本作为对照来评价其他采样方法的优劣.由于各种在线社交网络陆续将其用户ID系统由32位升级为64位,导致拒绝-接受采样法的采样命中率近乎为零.本文根据在线社交网络的特点,以新浪微博为例,对其用户ID分布情况进行分析,提出了一种改进的拒绝-接受采样法UNI64.该方法通过分析网络有效ID样本的分布情况,结合聚类的方法将整个样本空间划分为有效区间和无效区间,并使采样算法避开无效区间,仅在有效区间内生成待测样本,从而有效提高了拒绝-接受采样法在有效样本极为稀疏的样本空间内采样的命中率.     

一种新的在线社交网络的隐私保护方案

针对用户数据隐私容易被截取的问题,提出了一种新的用户在线社交网络隐私保护方案.传统解决方案依赖于公共密钥基础设施或传统密钥分布技术,而新的方案则充分利用朋友和用户的私有属性熵之间的信任.通过重新构建密码模块建立安全协议,对在线社交网络提供安全信息服务、安全信息匹配和安全通信三种服务,最终使用户能够安全地存储自己的私有数据,并建立一个会话密钥的安全通信.     

在线社交网络的自适应UNI采样方法

在线社交网络采样方法常作为其他采样方法的评估基准,但是该方法采样命中率和采样效率较低,影响了其应用。为此,提出一种自适应UNI采样方法。该方法将用户ID系统空间划分为若干区间进行采样,根据各区间命中率自适应地调节在各区间的采样概率,以提高采样命中率和效率。设定采样概率下限阈值解决冷启动问题,同时利用区间的采样率调节区间采样概率,防止陷入局部最优。将该方法应用于新浪微博的采样数据进行验证,实验结果表明,该方法可提高采样效率和采样命中率。     

一种新型在线社交网络协作访问控制机制

在线社交网络可以为数字用户提供社会互动和信息共享,但是它存在隐私安全问题。针对用户隐私保护问题,提出了一种保护机制,允许用户在协作条件下控制访问共享资源。这种新的在线社交网路协作访问控制机制,通过定义数据拥有者、利益相关者和信任度三个因素来描述其控制机制,对于新方案重点协作策略规则和信任度的计算,给出了具体的解释。研究结果表明,用户共享内容的安全问题很大程度上得到保护,且不论单用户访问还是多用户访问,隐私安全大大得到加强。     

在线社交网络社区的启发式挖掘框架

指出基于全局优化的社区挖掘方法的不足,给出OSNs网络及其社区挖掘的形式定义,提出一个启发式社区挖掘框架,在此框架下对包括LWP,Clauset,Schaeffer,Papadopoulos,Bagrow与Chen在内的6种启发式社区挖掘算法进行分析比较.通过3个真实OSNs网络的实验比较,验证了启发式社区挖掘框架的可行性,在结果社区有效性与时间效率上对6种启发式算法进行比较,实验结论为网络社区挖掘的工程实践与理论研究提供了借鉴.     

在线社交网络中基于标签的访问控制研究

随着互联网的发展,在线社交网络在人们的生活中越发显得重要。用户在自己的社交网络上发布信息促进与他人交流的同时也产生了隐私暴露的隐患。针对用户无法有效管理自己发布信息的问题,提出了一个基于标签的细粒度的访问控制模型,用户给其好友、好友的不同类型的行为以及用户发布的不同类型的信息分配标签,只有这些标签之间满足了一定的条件,好友才能对用户发布的信息进行操作,该模型能够对用户发布的信息进行有效的管理,保护用户隐私。     

社交网络的隐私保护

随着Facebook的上市,社交网络再次成为全球的焦点,网络中无时无刻不在产生用户数据,通过对海量的非结构化数据进行价值挖掘,社交网络引领其他互联网领域的应用率先进入大数据时代。本文描述了现阶段社交网络的特点及其对当今社会的影响,并对其存在的安全问题进行了分析,最后给出了相应的对策。     

在线社交网络影响力分析

社交影响力分析是社交网络分析的关键问题之一.近十几年间,随着在线社交网络的蓬勃发展,研究人员才开始有机会在大量现实数据的基础上对社交影响力进行建模和分析,并取得了丰硕的研究成果和广泛的应用价值.文中回顾了近些年在线社交网络影响力分析的主要成果,阐述了社交影响力的相关概念和它们之间的关系,重点从网络拓扑、用户行为和交互信息等几个方面总结了影响力分析的建模和度量方法,介绍了与影响力传播密切相关的意见领袖发现和影响力最大传播问题的研究现状,并对在线社交网络影响力分析的前景进行了展望.     

一种基于社交网络的按需在线学习模式

随着互联网的发展,在线学习成为学生获取知识的重要途径。文章通过对传统在线学习模式的研究分析,提出一种基于社交网络的按需在线学习模式的总体框架,设计思路和研究内容。阐述如何通过社交关系和面向服务架构SOA对学习资源进行整合,从而快速、准确地提供感兴趣的学习资源给学习者。     

A privacy self-assessment framework for online social networks

During our digital social life, we share terabytes of information that can potentially reveal private facts and personality traits to unexpected strangers. Despite the research efforts aiming at providing efficient solutions for the anonymization of huge databases (including networked data), in online social networks the most powerful privacy protection “weapons” are the users themselves. However, most users are not aware of the risks derived by the indiscriminate disclosure of their personal data. Moreover, even when social networking platforms allow their participants to control the privacy level of every published item, adopting a correct privacy policy is often an annoying and frustrating task and many users prefer to adopt simple but extreme strategies such as “visible-to-all” (exposing themselves to the highest risk), or “hidden-to-all” (wasting the positive social and economic potential of social networking websites). In this paper we propose a theoretical framework to i) measure the privacy risk of the users and alert them whenever their privacy is compromised and ii) help the users customize semi-automatically their privacy settings by limiting the number of manual operations. By investigating the relationship between the privacy measure and privacy preferences of real Facebook users, we show the effectiveness of our framework.     

A survey on privacy in decentralized online social networks

Decentralized Online Social Networks (DOSNs) have recently captured the interest of users because of the more control given to them over their shared contents. Indeed, most of the user privacy issues related to the centralized Online Social Network (OSN) services (such as Facebook or Google+) do not apply in the case of DOSNs because of the absence of the centralized service provider. However, these new architectures have motivated researchers to investigate new privacy solutions that allow DOSN’s users to protect their contents by taking into account the decentralized nature of the DOSNs platform.In this survey, we provide a comprehensive overview of the privacy solutions adopted by currently available DOSNs, and we compare them by exploiting several criteria. After presenting the differences that existing DOSNs present in terms of provided services and architecture, we identify, for each of them, the privacy model used to define the privacy policies and the mechanisms for their management (i.e., initialization and modification of the privacy policy). In addition, we evaluate the overhead introduced by the security mechanisms adopted for privacy policy management and enforcement by discussing their advantages and drawbacks.     

A review of online learning in supervised neural networks

Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented.     

复杂网络中的在线社交网络演化模型

在线社交网络是一种广泛存在的社会网络,其节点度遵循幂率分布规律,但对于其结构演化模型方面的相关研究还不多。基于复杂网络理论研究在线社交网络内部结构特征,提出一种结合内增长、外增长及内部边更替的演化模型,借助平均场理论分析该模型的拓扑特性,实验和理论分析表明由该模型生成的网络,其度分布服从幂率分布,且通过调整参数,幂率指数在1~3,能较好地反映不同类型的真实在线社交网络的度分布特征,因此具有广泛适用性。     

Personality assessment using multiple online social networks

Personality plays an important role in various aspects of our daily life. It is being used in many application scenarios such as i) personalized marketing and advertisement of commercial products, ii) designing personalized ambient environments, iii) personalized avatars in virtual world, and iv) by psychologists to treat various mental and personality disorders. Traditional methods of personality assessment require a long questionnaire to be completed, which is time consuming. On the other hand, several works have been published that seek to acquire various personality traits by analyzing Internet usage statistics. Researchers have used Facebook, Twitter, YouTube, and various other websites to collect usage statistics. However, we are still far from a successful outcome. This paper uses a range of divergent features of Facebook and LinkedIn social networks, both separately and collectively, in order to achieve better results. In this work, the big five personality trait model is used to analyze the five traits: openness to experience, conscientiousness, extroversion, agreeableness, and neuroticism. The experimental results show that the accuracy of personality detection improves with the use of complementary features of multiple social networks (Facebook and LinkedIn, in our case) for openness, conscientiousness, agreeableness, and neuroticism. However, for extroversion we found that the use of only LinkedIn features provides better results than the use of only Facebook features or both Facebook and LinkedIn features.     

Querying dynamic communities in online social networks简

Online social networks （OSNs） offer people the opportunity to join communities where they share a common interest or objective. This kind of community is useful for studying the human behavior, diffusion of information, and dynamics of groups. As the members of a community are always changing, an efficient solution is needed to query information in real time. This paper introduces the Follow Model to present the basic relationship between users in OSNs, and combines it with the MapReduce solution to develop new algorithms with parallel paradigms for querying. Two models for reverse relation and high-order relation of the users were implemented in the Hadoop system. Based on 75 GB message data and 26 GB relation network data from Twitter, a case study was realized using two dynamic discussion communities：#musicmonday and #beatcancer. The querying performance demonstrates that the new solution with the implementation in Hadoop significantly improves the ability to find useful information from OSNs.     

Finding email correspondents in online social networks

Email correspondents play an important role in many people’s social networks. Finding email correspondents in social networks accurately, though may seem to be straightforward at a first glance, is challenging. Most of the existing online social networking sites recommend possible matches by comparing the information of email accounts and social network profiles, such as display names and email addresses. However, as shown empirically in this paper, such methods may not be effective in practice. To the best of our knowledge, this problem has not been carefully and thoroughly addressed in research. In this paper, we systematically investigate the problem and develop a practical data mining approach. We find that using only the profiles or the graph structures is far from effective. Our method utilizes the similarity between email accounts and social network user profiles, and at the same time explores the similarity between the email communication network and the social network under investigation. We demonstrate the effectiveness of our method using two real data sets on emails and Facebook.