Securing Recommender Systems Against Shilling Attacks Using Social-Based Clustering

Recommender systems (RS) have been found supportive and practical in e-commerce and been established as useful aiding services. Despite their great adoption in the user communities, RS are still vulnerable to unscrupulous producers who try to promote their products by shilling the systems. With the advent of social networks new sources of information have been made available which can potentially render RS more resistant to attacks. In this paper we explore the information provided in the form of social links with clustering for diminishing the impact of attacks. We propose two algorithms, CluTr and WCluTr, to combine clustering with "trust" among users. We demonstrate that CluTr and WCluTr enhance the robustness of RS by experimentally evaluating them on data from a public consumer recommender system Epinions.com.     

基于图学习的社会网络图像标签排序算法

提出一种社会网络图像标签排序算法。将SIFT特征、卷积神经网络特征以及视觉词袋模型相结合,从图像训练集中获取目标图像的视觉近邻图像集;令所有视觉近邻图像为目标图像的初始标签进行加权投票,通过对图像视觉相似度和标签语义相似度的线性融合,计算投票权值;利用目标图像及其视觉近邻图像的标签,构造标签图模型;利用加权投票结果在标签图上执行随机漫步,完成标签排序任务。实验结果验证了提出方法的有效性。     

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.     

容迟网络中基于演化博弈的合作行为

针对容迟网络中节点由于资源有限而表现出来的自私特性,为改善网络中节点的合作行为,进而提高网络的整体性能,提出一种基于演化博弈(EGT)的节点合作行为促进机制。首先,采用囚徒困境模型建立节点与其邻居博弈的收益矩阵;其次,基于度中心性定义节点的社会权威性;进一步地,在节点策略更新规则时考虑社会权威的影响,选择当前邻居中社会权威较高的节点进行模仿学习;最后,在机会网络环境仿真器上基于真实的动态网络拓扑数据进行仿真实验。仿真结果表明,与随机选择邻居的费米(Fermi)更新规则相比,考虑社会权威的更新规则能够更好地促进节点合作行为的涌现,进而提升网络的整体性能。     

Conceptualizing and Measuring Personality Vulnerability to Depression: Comment on Coyne and Whiffen (1995).

J. C. Coyne and V. E. Whiffen (1995) reviewed research on personality vulnerability to depression, focusing on S. J. Blatt's (1974, 1990) concepts of dependency and self-criticism and A. T. Beck's (1983) concepts of sociotropy and autonomy. The authors discuss 6 issues raised in that review: (a) the typological or dimensional nature of vulnerability, (b) the theoretical implications of "mixed" vulnerability, (c) the relations of vulnerability to Neuroticism. (d) the potential confounding of vulnerability with concurrent depression, (e) the potential confounding of vulnerability with social context, and (f) the differentiation of dependency from relatedness. The authors conclude that Blatt's and Beck's concepts are continuous, nearly orthogonal dimensions that can be identified and measured independently from Neuroticism, depression, and social context. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

On the Subjective Quality of Social Justice: The Role of Affect as Information in the Psychology of Justice Judgments.

This article argues that it is not uncommon for people forming justice judgments to lack information that is most relevant in the particular situation. In information-uncertain conditions, people may therefore construct justice judgments by relying on how they feel about the events they have encountered, and justice judgments may hence be strongly influenced by affect information. Findings show that in information-uncertain conditions, the affective states that people had been in prior and unrelated to the justice event indeed strongly influenced their justice judgments. These findings thus reveal that in situations of information uncertainty, people's judgments of justice can be very subjective, susceptible to affective states that have no logical relationship with the justice judgments they are constructing. Implications for the social psychology of justice and the literature on social cognition and affect are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

基于模糊层次分析法的公共建筑综合效益评价研究

针对公共建筑效益评价研究现状,提出对于公共建筑的评价更应当注重包括经济、社会、环境效益的综合效益评价．为此,应用模糊综合评判方法构建了公共建筑综合效益评价模型,并以徐州市奥体中心项目为例进行了实证研究．研究表明：将模糊综合评判方法应用于公共建筑综合效益评价,其评价结果真实可靠,具有较强的实用性和良好的应用价值．     

二战后年鉴派社会史研究片论

在20世纪西方新史学的几大流派中,法国年鉴学派影响最大。该学派以社会史、经济史为发展方向,其中社会史的研究经过几代学者的努力,逐渐发展壮大并不断开辟新的领域。从社会经济史到心态史、政治史,从计量方法的使用到叙事史的复兴,年鉴派的社会史不拘一格,却不断引领史学潮流的发展。年鉴派社会史在二战后的成就,说明社会史主要是一种研究思想和视角,而非僵化的概念和体系。     

梯级水库群优化调度精英集聚蛛群优化方法

将蛛群优化方法(SSO)这一新型群体智能寻优方法引入梯级水库群优化调度领域,并提出精英集聚蛛群优化方法(ESSO)进一步改善SSO的性能表现。ESSO在标准SSO方法寻优机制基础上,从精英个体动态更新策略与邻域变异搜索机制等两方面予以改进,提升蜘蛛群体的多样性与优秀个体领导能力,均衡方法的全局开采能力与局部勘探能力。澜沧江流域工程实例表明,所提ESSO方法能有效克服标准SSO的"早熟"缺陷,有效提升方法的搜索能力,可望为大规模梯级水库群优化调度提供一种新的高效求解思路。     

TSP问题的自适应进化算法

提出了一种 TSP问题的进化计算方法。此方法结合边自适应和边重组的进化过程处理方法 ,在本质上符合 TSP问题的求解的需要。本文给出了边适应性函数的数学模型 ,并且构造了一种易于实现的路径重组算法。对于 TSP问题的求解是一种新的见解