基于交互行为和连接分析的社交网络社团检测

社交网络的迅猛发展极大地方便了人们的日常生活、工作和学习,但也带来了大量复杂的交互行为和连接模式。如何有效地综合分析网络中的交互信息和网络节点之间存在的连接信息,进而完成高效的社团检测,是在当前网络多维属性的复杂背景下进行网络分析所面临的关键难题。基于此,从有效融合两类不同的异质信息研究出发,提出了一种基于交互行为和连接分析的社交网络社团检测(CDUILS)方法。该方法基于两类信息能够从不同的角度反映网络同一个社团归属的假设,采用联合非负矩阵分解架构,以迭代更新的方式,同时利用两类信息进行社团结果的获取。在真实网络数据集上的实验表明,与已有方法相比,所提方法能够有效融合两类信息进行社团检测,取得了更好的社团划分质量。     

基于重叠社区搜索的传播热点选择方法

随着社交网络的蓬勃发展,信息传播问题由于具有广泛的应用前景而受到广泛关注,影响力最大化问题是信息传播中的一个研究热点.它致力于在信息传播过程开始之前选取能够使预期影响力达到最大的节点作为信息传播的初始节点,并且多采用基于概率的模型,如独立级联模型等.然而,现有的影响力最大化解决方案大多认为信息传播过程是自动的,忽略了社交网站平台在信息传播过程中可以起到的作用.此外,基于概率的模型存在一些问题,如无法保障信息的有效传播、无法适应动态变化的网络结构等等.因此,本文提出了一种基于重叠社区搜索的传播热点选择方法,该方法通过迭代式推广模型根据用户行为反馈逐步选择影响力最大化节点,使社交网站平台在信息传播过程中充分发挥控制作用,并提出一种新型的基于重叠社区结构的方法来衡量节点影响力,根据这种衡量方式来选择传播热点.本文提出了解决该问题的两种精确算法,包括一种基本方法和一种优化方法,以及该问题的近似算法.并通过大量实验验证了精确及近似算法的效率和近似算法的准确率以及迭代式传播热点选择方法的有效性.     

Interactive visual analysis of set-typed data

While it is quite typical to deal with attributes of different data types in the visualization of heterogeneous and multivariate datasets, most existing techniques still focus on the most usual data types such as numerical attributes or strings. In this paper we present a new approach to the interactive visual exploration and analysis of data that contains attributes which are of set type. A set-typed attribute of a data item--like one cell in a table--has a list of n > or = 0 elements as its value. We present the set'o'gram as a new visualization approach to represent data of set type and to enable interactive visual exploration and analysis. We also demonstrate how this approach is capable to help in dealing with datasets that have a larger number of dimensions (more than a dozen or more), especially also in the context of categorical data. To illustrate the effectiveness of our approach, we present the interactive visual analysis of a CRM dataset with data from a questionnaire on the education and shopping habits of about 90000 people.     

大规模接警日志语义时空模式交互探索

接警日志包含时间、空间和案件描述信息,属于非结构时空数据.与时空社交媒体相比,接警日志的数据项之间存在较少的联系,数据项之间不能形成复杂网络关系,在挖掘其数据模式时难以提供有价值的线索,因此,其分析更加依赖于其中的语义挖掘和语义时空模式探索.针对这一问题,提出了一个可视分析框架支持对大规模非结构接警日志时空模式的交互探索.首先,提出了一种基于主题模型集成的方法,实现从异构文本中抽取主题;其次,该框架包含一个数据立方体,实现快速响应用户的查询请求;第三,设计并实现了一个可视化交互系统,支持对数据立方体的可视化交互探索.最后,使用国内某城市真实接警日志进行实验,找到的丰富的模式和主题预测准确性证明了方法的有效性.     

基于级联时空特征的信息传播预测方法

现有信息传播预测方法对级联序列和拓扑结构独立建模,难以学习级联时序特征和结构特征在嵌入空间的交互表达,造成对信息传播动态演化的刻画不足.因此,文中提出基于级联时空特征的信息传播预测方法.基于社交关系网络和传播路径构建异质图,使用图神经网络学习异质图和社交关系网络节点的结构上下文,引入门控循环单元提取级联时序特征,融合结构上下文和时序特征,构建级联时空特征,进行信息传播的微观预测.在Twitter、Memes数据集上的实验表明,文中方法性能得到一定提升.     

Interactive visual analysis of families of function graphs

The analysis and exploration of multidimensional and multivariate data is still one of the most challenging areas in the field of visualization. In this paper, we describe an approach to visual analysis of an especially challenging set of problems that exhibit a complex internal data structure. We describe the interactive visual exploration and analysis of data that includes several (usually large) families of function graphs f_i(x, t). We describe analysis procedures and practical aspects of the interactive visual analysis specific to this type of data (with emphasis on the function graph characteristic of the data). We adopted the well-proven approach of multiple, linked views with advanced interactive brushing to assess the data. Standard views such as histograms, scatterplots, and parallel coordinates are used to jointly visualize data. We support iterative visual analysis by providing means to create complex, composite brushes that span multiple views and that are constructed using different combination schemes. We demonstrate that engineering applications represent a challenging but very applicable area for visual analytics. As a case study, we describe the optimization of a fuel injection system in diesel engines of passenger cars     

An interactive approach for CBIR using a network of radial basis functions

An important requirement for constructing effective content-based image retrieval (CBIR) systems is accurate characterization of visual information. Conventional nonadaptive models, which are usually adopted for this task in simple CBIR systems, do not adequately capture all aspects of the characteristics of the human visual system. An effective way of addressing this problem is to adopt a "human-computer" interactive approach, where the users directly teach the system about what they regard as being significant image features and their own notions of image similarity. We propose a machine learning approach for this task, which allows users to directly modify query characteristics by specifying their attributes in the form of training examples. Specifically, we apply a radial-basis function (RBF) network for implementing an adaptive metric which progressively models the notion of image similarity through continual relevance feedback from users. Experimental results show that the proposed methods not only outperform conventional CBIR systems in terms of both accuracy and robustness, but also previously proposed interactive systems.     

Forecasting social CRM adoption in SMEs: A combined SEM-neural network method

The growth of social media usage questions the old-style idea of customer relationship management (CRM). Social CRM strategy is a novel version of CRM empowered by social media technology that offers a new way of managing relationships with customers effectively. This study aims to forecast the predictors of social CRM strategy adoption by small and medium enterprises (SMEs). The proposed model used in this study derived its theoretical support from IT/IS, marketing, and CRM literature. In the proposed Technology-Organization-Environment-Process (TOEP) adoption model, several hypotheses are developed which examine the role of Technological factors, such as Cost of Adoption, Relative Advantages, Complexity, and Compatibility; Organizational factors, such as IT/IS knowledge of employee, and Top management support; Environmental factors such as Competitive Pressure, and Customer Pressure; and Process factors such as Information Capture, Information Use, and Information Sharing; all having a positive relationship with social CRM adoption. This research applied a following two staged SEM-neural network method combining both structural equation modelling (SEM) and neural network analyses. The proposed hypothetical model is examined by using SEM on the collected data of SMEs in Kuala Lumpur, the central city of Malaysia. The SEM approach with a neural network method can be used to investigate the complicated relations involved in the adoption of social CRM. The study finds that compatibility, information capture, IT/IS knowledge of employee, top management support, information sharing, competitive pressure, cost, relative advantage, and customer pressure are the most important factors influencing social CRM adoption. Remarkably, the results of neural network analysis show that compatibility and information capture of social CRM are the most significant factors which affect SMEs' adoption of this form of customer relationship management. The outcomes of this research benefit executives' decision-making by identifying and ranking factors that enable them to discover how they can advance the usage of social CRM in their firms. Furthermore, the findings of this study can help the managers/owners of SMEs assign their resources, according to the ranking of social CRM adoption factors, when they are making plans to adopt social CRM. This study differs from previous studies as it proposes an innovative new approach to determine what influences the adoption of social CRM. By proposing the TOEP adoption model, additional information process factors advance the traditional TOE adoption model.     

Community detection in social networks using user frequent pattern mining

Recently, social networking sites are offering a rich resource of heterogeneous data. The analysis of such data can lead to the discovery of unknown information and relations in these networks. The detection of communities including ‘similar’ nodes is a challenging topic in the analysis of social network data, and it has been widely studied in the social networking community in the context of underlying graph structure. Online social networks, in addition to having graph structures, include effective user information within networks. Using this information leads to enhance quality of community discovery. In this study, a method of community discovery is provided. Besides communication among nodes to improve the quality of the discovered communities, content information is used as well. This is a new approach based on frequent patterns and the actions of users on networks, particularly social networking sites where users carry out their preferred activities. The main contributions of proposed method are twofold: First, based on the interests and activities of users on networks, some small communities of similar users are discovered, and then by using social relations, the discovered communities are extended. The F-measure is used to evaluate the results of two real-world datasets (Blogcatalog and Flickr), demonstrating that the proposed method principals to improve the community detection quality.     

面向比特币交易网络的拓扑结构可视探索方法

分析比特币交易网络有助于人们理解交易者在比特币交易中的交易模式.比特币交易网络的匿名性和其巨大的规模使得用户很难在分析前对整个交易网络产生大致的认知.提出了一种基于拓扑结构推荐的比特币交易网络可视分析方法.核心思想是为每个节点生成一个向量化表达,在用户交互的基础上,所提算法即可检测一系列相似的结构.案例分析证明了系统能够支持用户对比特币交易中的交易模式进行探索和分析.     

Visual Analysis of Governing Topological Structures in Excitable Network Dynamics

To understand how topology shapes the dynamics in excitable networks is one of the fundamental problems in network science when applied to computational systems biology and neuroscience. Recent advances in the field discovered the influential role of two macroscopic topological structures, namely hubs and modules. We propose a visual analytics approach that allows for a systematic exploration of the role of those macroscopic topological structures on the dynamics in excitable networks. Dynamical patterns are discovered using the dynamical features of excitation ratio and co‐activation. Our approach is based on the interactive analysis of the correlation of topological and dynamical features using coordinated views. We designed suitable visual encodings for both the topological and the dynamical features. A degree map and an adjacency matrix visualization allow for the interaction with hubs and modules, respectively. A barycentric‐coordinates layout and a multi‐dimensional scaling approach allow for the analysis of excitation ratio and co‐activation, respectively. We demonstrate how the interplay of the visual encodings allows us to quickly reconstruct recent findings in the field within an interactive analysis and even discovered new patterns. We apply our approach to network models of commonly investigated topologies as well as to the structural networks representing the connectomes of different species. We evaluate our approach with domain experts in terms of its intuitiveness, expressiveness, and usefulness.     

Detecting Overlapping Community Structures in Networks

Community structure has been recognized as an important statistical feature of networked systems over the past decade. A lot of work has been done to discover isolated communities from a network, and the focus was on developing of algorithms with high quality and good performance. However, there is less work done on the discovery of overlapping community structure, even though it could better capture the nature of network in some real-world applications. For example, people are always provided with varying characteristics and interests, and are able to join very different communities in their social network. In this context, we present a novel overlapping community structures detecting algorithm which first finds the seed sets by the spectral partition and then extends them with a special random walks technique. At every expansion step, the modularity function Q is chosen to measure the expansion structures. The function has become one of the popular standards in community detecting and is defined in Newman and Girvan (Phys. Rev. 69:026113, 2004). We also give a theoretic analysis to the whole expansion process and prove that our algorithm gets the best community structures greedily. Extensive experiments are conducted in real-world networks with various sizes. The results show that overlapping is important to find the complete community structures and our method outperforms the C-means in quality.     

一种基于因子图模型的半监督社区发现方法

社区发现是社交网络分析中一个重要的研究方向.当前大部分的研究都聚焦在自动社区发现问题,但是在具有数据缺失或噪声的网络中,自动社区发现算法的性能会随着噪声数据的增加而迅速下降.通过在社区发现中融合先验信息,进行半监督的社区发现,有望为解决上述挑战提供一条可行的途径.本文基于因子图模型,通过融入先验信息到一个统一的概率框架中,提出了一种基于因子图模型的半监督社区发现方法,研究具有用户引导情况下的社交网络社区发现问题.在三个真实的社交网络数据（Zachary社会关系网、海豚社会网和DBLP协作网）上进行实验,证明通过融入先验信息可以有效地提高社区发现的精度,且将我们的方法与一种最新的半监督社区发现方法（半监督Spin-Glass模型）进行对比,在三个数据集中F-measure平均提升了6.34%、16.36%和12.13%.     

关系数据库中社区发现方法研究

文中在研究了现有社区发现算法的基础上,提出了一种简单的加权网络中社区发现方法。文中基于社区结构最为普遍的性质,受社会网络中真实社区结构和并行计算的任务划分规则的启发,提出了基于核心边的加权网络中社区发现方法。该方法首先依据网络中边的权值寻找核心边;然后依据相似性度量,发现网络中的一个初始社区;最后通过隶属度度量,将发现的初始社区逐步扩展成网络中的社区结构。该方法在进行社区结构发现的过程中,仅仅依赖节点所处位置的局部信息,可以在对网络进行广度优先遍历的过程中完成社区发现工作。因此该方法具有较低的计算复杂度,可以适用于大规模网络中的社区发现。通过有效性实验和效率实验,表明该方法可以有效发现大规模网络中的社区结构。     

基于话题概率模型的语义社区发现方法研究

语义社会网络(Semantic social network, SSN)是一种由信息节点及社会关系构成的复杂网络, 也是语义信息时代社会网络技术研究的热点, 相较于传统社会网络更具实用价值. 其研究内容包含了社会网络的语义分析及社会关系分析, 因此, 语义社会网络的社区挖掘建模具有一定的复杂性. 在语义社会网络的社区挖掘研究方面, 本文分析了当前基于话题概率模型的语义社区发现方法, 并在综述其内容的同时总结了各方法的优缺点, 为后续研究提供了理论基础. 在语义社会网络社区挖掘结果的评判方面, 本文归纳了相关的评价模型, 并通过实验分析对比了各模型对拓扑相关性和语义相关性的倾向性.     

基于反馈日志分析的图像检索相关反馈方法

基于内容的图像检索是多媒体数据库研究的重要内容之一。近年来，采用用户相关反馈方法提高检索效率的研究已成为新的热点，用户相关反馈是一种交互式的渐进过程，如何提高反馈效率，减少交互次数是该技术面临的主要问题，提出一种通过对相关反馈历史数据进行在线分析从而加快反馈过程的新方法，对10000幅图像数据库的实验表明，与传统相关反馈技术相比，新方法对检索效果有明显改善。     

Toward finding hidden communities based on user profile

We consider the community detection problem from a partially observable network structure where some edges are not observable. Previous community detection methods are often based solely on the observed connectivity relation and the above situation is not explicitly considered. Even when the connectivity relation is partially observable, if some profile data about the vertices in the network is available, it can be exploited as auxiliary or additional information. We propose to utilize a graph structure (called a profile graph) which is constructed via the profile data, and propose a simple model to utilize both the observed connectivity relation and the profile graph. Furthermore, instead of a hierarchical approach, based on the modularity matrix of the network structure, we propose an embedding approach which utilizes the regularization via the profile graph. Various experiments are conducted over two social network datasets and comparison with several state-of-the-art methods is reported. The results are encouraging and indicate that it is promising to pursue this line of research.     

The IKEA effect in collective problem‐solving: When individuals prioritize their own solutions

To improve problem‐solving performance, individuals can rely on social learning. This approach is constrained by an individual's social network, which influences the efficiency of the problem‐solving process. To date, research disagrees on what kind of network structure is preferable, providing support for efficient network structures, as well as for inefficient networks. However, studies implicitly assume that solvers always imitate superior solutions, an assumption that lacks empirical grounding. We propose a simple derivation of an existing simulation framework by incorporating a known cognitive bias (‘IKEA effect’), whereby individuals are assumed to prioritize individual information. This effect allows inefficiencies to be embodied at the individual microlevel, reducing the need for inefficiencies at the structural macrolevel. Simulation results explain discrepancies in previous results, illustrating how more realistic microlevel assumptions substantially impact macrolevel outcomes.     

A framework for exploring organizational structure in dynamic social networks

Recent research has provided promising results relating to discovering communities within a social network. We find that further representing the organizational structure of a social network is an interesting issue that helps gain better understandings of the social network. In this paper, we define a data structure, named Community Tree, to depict the organizational structure and provide a framework for exploring the organizational structure in a social network. In this framework, an algorithm, which combines a modified PageRank and Random Walk on graph, is developed to derive the community tree from the social network. In the real world, a social network is constantly evolving. In order to explore the organizational structure in a dynamic social network, we develop a tree learning algorithm, which employs tree edit distance as the scoring function, to derive an evolving community tree that enables a smooth transition between two community trees. We also propose an approach to threading communities in community trees to obtain an evolution graph of the organizational structure, by which we can reach new insights from the dynamic social network. The experiments conducted on synthetic and real dataset demonstrate the feasibility and applicability of the framework. Based on the theoretical outcomes, we further apply the proposed framework to explore the evolution of organizational structure with the 2001 Enron dataset, and obtain several interesting findings that match the context of Enron.     

研讨信息交互式可视化平台设计与实现

针对传统研讨信息静态可视化视图杂乱、难以辨认等问题,提出研讨信息可视化框架和基于交互式可视化技术的解决方案。利用Java、XML技术,借助JFreeChar、Prefuse软件包实现交互式可视化平台。该平台基于节点链接结构,允许用户交互式操作,支持可视化检索和分析。运行结果表明,该平台改善了研讨信息的可访问性,具有较强的可扩展性。