网络检索用户行为可靠性分析

基于大规模真实网络用户的行为日志,对用户与网络搜索引擎系统的交互过程和用户决策过程展开研究.通过比较具有相关信息的用户点击和普通点击的分布,对用户点击的3类上下文背景特征进行分析,从而实现对用户点击的可靠性评估.实验结果表明,通过对用户点击的上下文背景的特征分析,能够发现用户检索行为中的思维决策过程,并进而对用户点击的可靠性进行有效的评估.     

复杂网络环境下用户行为的信任评估方法

本文以复杂网络为研究背景,运用AHP原理,研究并提出了一种新的基于网络用户行为的信任评估方法。论文首先对行为证据进行量化分析,计算出用户一次行为的可信值,然后融合了行为的活跃度以及惩罚因子等决策属性对用户的综合信任度进行计算,最后通过一个实例对该方法进行了可行性论证,结果表明使用该方法得到的用户综合信任值具有动态可变性,它更能适应复杂的网络环境,能够为网络信任决策提供一种很好的方法。     

可信网络中一种基于行为信任预测的博弈控制机制

近年来,网络可信的研究已成为一个研究热点,其中用户的行为信任研究是网络可信研究的重要内容之一.由于用户行为信任的评估是基于过去交往的行为证据之上,而我们需要的是未来的用户行为信任等级,因此科学地预测未来用户的行为信任等级是非常必要的,文中首先论述了如何利用贝叶斯网络对用户的行为信任进行预测,提供的机制不仅可以预测单属性条件下的行为信任等级,而且可以预测多属性条件下的行为信任等级.由于信任和风险是并存的,单独依靠预测的信任等级进行决策是非常片面和危险的,因此该文的其余部分将行为信任预测结果和博弈分析相结合对双方的支付矩阵进行分析,计算出了基于用户安全行为属性的混合纳什均衡策略,证明了服务提供者进行控制的决策条件,得出了相关的一些重要性质,最后通过一个例子来说明论文的应用.该文的结果对于量化分析用户行为信任具有重要的理论意义.文章在分析过程和实例中结合了数字化电子资源的实际网络应用背景,因此该机制在实际的网络应用中同样具有重要的指导意义.     

基于用户行为分析的广告欺诈点击检测

在网络广告业中出现的欺诈点击行为,使得搜索引擎企业以及广告主的利益受到了严重损害,致使点击付费模式遭到质疑,欺诈点击已经成为阻碍网络广告业健康发展的一大顽疾。针对网络广告业发展所面临的此种困境,提出一种基于用户行为分析的广告欺诈点击检测技术。首先创建用户行为数据仓库,然后运用贝叶斯分类方法对用户行为数据进行点击合法等级预测,最后结合博弈控制机制对用户点击有效性进行最终判断。     

锚文本检索有效性分析

锚文本对网络信息检索性能的提升作用已经得到验证,并被广泛地应用于商用网络搜索引擎.然而,锚文本制作的不可控性导致其中蕴含大量与目标网页不相关或具有作弊倾向的无用信息.另外,对于需要衡量检索结果服务质量的事务类查询,原始锚文本推荐的目标网页也往往与真实的用户体验不一致.为了解决上述问题,基于大规模真实用户的互联网浏览行为日志展开研究.首先提出了锚文本检索有效性的评估框架,然后分析了用户网络浏览点击行为与锚文本检索有效性之间的联系,挖掘了用户网络浏览点击行为中有助于筛选高质量锚文本的特征.基于这些特征,提出了两种超链接文档生成方法.实验结果表明,基于用户网络浏览点击行为特征筛选出的锚文本,与原始锚文本相比,能够明显地提升网络检索的性能.     

基于验证的自适应系统决策:一种模型驱动的方法

自适应系统需要根据运行时上下文和自身的变化进行其行为的调节.为实现自主调节,自适应系统必须被赋予运行时监测上下文和自身变化,分析需求满足程度的变化,以及推理得到自适应决策的能力.这种在线决策的行为在满足功能需求的同时,还需要保证系统满足特定的非功能需求,如可靠性和性能等.本文提出了一种基于验证的自适应系统优化决策方法,以保证非功能需求的满足.该方法在识别可调节目标以建模自适应机制的同时,将系统的目标模型映射为相应的行为模型,用标签转移系统表示;以可靠性需求为例,用标记目标模型规约任务的可靠性;然后将系统行为模型和可靠性规约整合为带可变状态的离散时间马尔可夫链,将候选自适应配置描述为不同可变状态间的组合;最终通过相关需求的在线验证,使系统找到关于某类上下文的最优决策配置.本文通过一个移动信息系统的案例展示了该方法的可行性和有效性.     

基于多维决策属性的网络用户行为可信度评估

网络用户行为可信的评估具有不确定性、复杂性等特点。针对已有模型在动态适应性、主观分类权重、决策属性建模粗糙等方面的不足,本文提出了一种新的网络用户行为可信评估模型。采用更完善的决策属性来衡量用户行为可信性,基于AHP原理计算直接可信度,运用信息熵理论客观的分类方法,确定各个决策属性的权重,并通过加权几何平均融合各决策属性。实验结果表明,该模型能够准确评价网络用户行为的可信性,反映网络用户行为可信性的动态变化特性。与传统模型相比,在准确度和安全性方面有了很大提高。     

移动云计算中的上下文相关身份认证

上下文相关信息,例如可操作的、用户个人的、空间的、环境的信息能够为用户提供他们确实需要而没有明确表示的服务。利用上下文内容相关的方法分析移动设备提供的用户通话记录、日程表、GPS和用户安装的应用。在收集这几方面信息之后,加以考虑时间和地点的因素,使整个认证过程更有可靠性。提出在移动云计算背景下的上下文相关身份认证框架,并详细描述框架的各个组件及决策器的算法模型和通信协议部分,使用户能够更加方便、安全地使用移动云。     

基于信用机制的网络用户管理方法研究

网络用户管理是网络管理的重点也是难点,为了进一步提高网络管理的稳定性和可靠性,在分析网络用户上网行为的基础上,提出基于信用机制的网络用户管理方法.以金融领域较为成熟的信用模型对网络用户行为进行信用评估,利用信用值对网络用户进行管理.实验结果表明,利用信用模型的网络管理方法,减轻了网络管理员工作负担,并且提高了网络的稳定性和网络用户管理的有效性,该方法具有良好的鲁棒性和较强的适应能力,为网络管理提供一种新思路.     

基于用户点击流的标签兴趣模型的研究与实现

分析用户的网络交互行为与用户兴趣之间的关系,针对目前的兴趣标签建模方法的不足,提出将用户的点击对象进行标签量化,通过用户的点击行为建立用户兴趣模型的方法,并在社交网络环境中对模型进行用户兴趣分析与测试。测试结果表明,该方法能有效地构建用户兴趣模型,证明了该方法的可行性。     

Learning to rank: new approach with the layered multi-population genetic programming on click-through features

Users’ click-through data is a valuable source of information about the performance of Web search engines, but it is included in few datasets for learning to rank. In this paper, inspired by the click-through data model, a novel approach is proposed for extracting the implicit user feedback from evidence embedded in benchmarking datasets. This process outputs a set of new features, named click-through features. Generated click-through features are used in a layered multi-population genetic programming framework to find the best possible ranking functions. The layered multi-population genetic programming framework is fast and provides more extensive search capability compared to the traditional genetic programming approaches. The performance of the proposed ranking generation framework is investigated both in the presence and in the absence of explicit click-through data in the utilized benchmark datasets. The experimental results show that click-through features can be efficiently extracted in both cases but that more effective ranking functions result when click-through features are generated from benchmark datasets with explicit click-through data. In either case, the most noticeable ranking improvements are achieved at the tops of the provided ranked lists of results, which are highly targeted by the Web users.     

基于用户行为分析的搜索引擎自动性能评价

基于用户行为分析的思路,提出了一种自动进行搜索引擎性能评价的方法.此方法能够基于对用户的查询和点击行为的分析自动生成导航类查询测试集合,并对查询对应的标准答案实现自动标注.基于中文商业搜索引擎日志的实验结果表明,此方法能够与人工标注的评价取得基本一致的评价效果,同时大大减少了评价所需的人力资源,并加快了评价反馈周期.     

Sponsored Search: Is Money a Motivator for Providing Relevant Results?

Analysis of data from a major metasearch engine reveals that sponsored-link click-through rates appear lower than previously reported. Combining sponsored and nonsponsored links in a single listing, while providing some benefits to users, does not appear to increase clicks on sponsored listings. In a competitive market, rivals continually strive to improve their information-retrieval capabilities and increase their financial returns. One innovation is sponsored search, an "economics meets search" model in which content providers pay search engines for user traffic going from the search engine to their Web sites. Sponsored search has proven to be a successful business model for Web search engines, advertisers, and online vendors, as well as an effective way to deliver content to searchers. The "impact of sponsored search" sidebar describes some of the model's notable benefits.     

User behavior modeling for better Web search ranking

Modern search engines record user interactions and use them to improve search quality. In particular, user click-through has been successfully used to improve clickthrough rate (CTR), Web search ranking, and query recommendations and suggestions. Although click-through logs can provide implicit feedback of users’ click preferences, deriving accurate absolute relevance judgments is difficult because of the existence of click noises and behavior biases. Previous studies showed that user clicking behaviors are biased toward many aspects such as “position” (user’s attention decreases from top to bottom) and “trust” (Web site reputations will affect user’s judgment). To address these problems, researchers have proposed several behavior models (usually referred to as click models) to describe users? practical browsing behaviors and to obtain an unbiased estimation of result relevance. In this study, we review recent efforts to construct click models for better search ranking and propose a novel convolutional neural network architecture for building click models. Compared to traditional click models, our model not only considers user behavior assumptions as input signals but also uses the content and context information of search engine result pages. In addition, our model uses parameters from traditional click models to restrict the meaning of some outputs in our model’s hidden layer. Experimental results show that the proposed model can achieve considerable improvement over state-of-the-art click models based on the evaluation metric of click perplexity.     

Aggregation of web search engines based on users’ preferences in WebFusion

The required information of users is distributed in the databases of various search engines. It is inconvenient and inefficient for an ordinary user to invoke multiple search engines and identify useful documents from the returned results. Meta-search engines could provide a unified access for their users. In this paper, a novel meta-search engine, named as WebFusion, is introduced. WebFusion learns the expertness of the underlying search engines in a certain category based on the users’ preferences. It also uses the “click-through data concept” to give a content-oriented ranking score to each result page. Click-through data concept is the implicit feedback of the users’ preferences, which is also used as a reinforcement signal in the learning process, to predict the users’ preferences and reduces the seeking time in the returned results list. The decision lists of underling search engines have been fused using ordered weighted averaging (OWA) approach and the application of optimistic operator as weightening function has been investigated. Moreover, the results of this approach have been compared with those achieve by some popular meta-search engines such as ProFusion and MetaCrawler. Experimental results demonstrate a significant improvement on average click rate, and the variance of clicks as well as average relevancy criterion.     

一种融合用户学习过程的用户查询意图模型

用户查询意图模型是查询扩展和查询推荐研究中的一个热点。然而,日志包含的大量噪声对主流的用户查询意图模型构建过程具有较大负面影响。观察日志发现,用户试探性点击是日志噪声的一个主要来源。由此,基于试探性点击的特征提出了一种融合用户学习过程的用户查询意图模型。该模型对用户从试探性点击中学习到的经验进行建模,并基于用户学习到的经验对试探性点击进行识别和过滤。一系列实验结果表明,该模型在日志噪声较高的情况下能够有效过滤试探性点击产生的噪声,提高用户查询意图描述的准确率。将该模型应用于查询推荐后,能有效提高查询条件间的相似性计算结果,并提高查询推荐结果的准确率。     

基于用户搜索行为的query-doc关联挖掘

query和doc之间的关联关系是搜索引擎期望获取的一类有价值的信息. query和doc间准确的关联分析不仅可以帮助搜索结果排序,也在query和doc之间的桥接中起到重要作用,以实现相关query和doc之间的信息传递,有利于更深入的query理解和doc理解,并在此基础上开展相关应用.本文提出了一种基于用户搜索行为的query和doc关联关系挖掘算法,该方法首先对用户搜索点击日志中的数据进行整理与分析,构建query与doc间的二部图,再通过采用马尔可夫随机游走模型对二部图数据进行建模,挖掘二部图中的点击数据和session数据,最终挖掘出点击日志中用户没有点击到的doc数据,从而预测出query和doc间的隐含关联关系,同时也可以利用该算法得到query和query潜在的关联关系.基于以上理论基础,我们实现了一套完整的日志挖掘系统,通过大量的实验对比,该系统在各方面均取得了优异的表现,其中对检索结果相关性的性能提升可以达到71.23%,这充分表明,本文所提出的理论和算法能够很好地解决query和doc之间的隐含关系挖掘问题,为提高搜索结果的召回率、实现查询推荐和检索结果聚类奠定了良好的前提基础.     

Cursor momentum for fascination measurement

We present a very different cause of search engine user behaviors—fascination. It is generally identified as the initial effect of a product attribute on users’ interest and purchase intentions. Considering the fact that in most cases the cursor is driven directly by a hand to move via a mouse (or touchpad), we use the cursor movement as the critical feature to analyze the personal reaction against the fascinating search results. This paper provides a deep insight into the goal-directed cursor movement that occurs within a remarkably short period of time (<30 milliseconds), which is the interval between a user’s click-through and decision-making behaviors. Instead of the fundamentals, we focus on revealing the characteristics of the split-second cursor movement. Our empirical findings showed that a user may push or pull the mouse with a slightly greater strength when fascinated by a search result. As a result, the cursor slides toward the search result with an increased momentum. We model the momentum through a combination of translational and angular kinetic energy calculations. Based on Fitts’ law, we implement goal-directed cursor movement identification. Supported by the momentum, together with other physical features, we built different fascination-based search result reranking systems. Our experiments showed that goal-directed cursor momentum is an effective feature in detecting fascination. In particular, they show feasibility in both the personalized and cross-media cases. In addition, we detail the advantages and disadvantages of both click-through rate and cursor momentum for re-ranking search results.