基于MKL-SVM的网络购物评论分类方法

购物网站在线评论系统收集了大量的顾客评价。支持向量机（SVM）是一种有效的文本分类方法,可以用于跟踪和管理顾客意见,但是SVM存在训练收敛速度慢,分类精度难以提高等缺点。文章提出利用异质核函数性的不同特性,解决支持向量机（SVM）数据泛化学习能力弱的问题,提高SVM的分类精度,通过对顾客购物评论进行分类,解决购物网站海量顾客评论分析的问题,帮助企业及时进行顾客反馈,提升服务水平。     

MASACAD: a multiagent based approach to information customization

MASACAD is a multiagent information customization system that adopts the machine-learning paradigm to advise students by mining the Web. In the distributed problem-solving paradigm, systems can distribute among themselves the processes necessary to accomplish a given task. Given the number of problems that distributed processing can address, AI researchers have directed significant effort toward developing specialized problem-solving systems that can interact in their search for a solution. The multiagent-system paradigm embodies this approach.     

潜在网络购物者与有经验者购买意愿比较研究*

感知风险和信任缺失被认为是阻碍网络购物发展的主要因素。以技术接受模型为理论基础,将感知风险和信任引入模型,把消费者分为潜在网络购物者和有经验网络购物者两大类,采用结构方程模型方法对影响我国消费者网络购物意愿的因素进行实证对比研究。实证结果表明：消费者感知网络购物有用性对其购买意愿的影响路径系数高于信任和风险因子对购买意愿的路径系数;感知风险对网络购买意愿有直接的负向影响;对于潜在消费者群体,信任显著影响其网络购物意愿,但对有购物经验的消费者群体信任却对网络购买意愿没有显著影响。     

Improving the quality of predictions using textual information in online user reviews

Online reviews are often accessed by users deciding to buy a product, see a movie, or go to a restaurant. However, most reviews are written in a free-text format, usually with very scant structured metadata information and are therefore difficult for computers to understand, analyze, and aggregate. Users then face the daunting task of accessing and reading a large quantity of reviews to discover potentially useful information. We identified topical and sentiment information from free-form text reviews, and use this knowledge to improve user experience in accessing reviews. Specifically, we focus on improving recommendation accuracy in a restaurant review scenario. We propose methods to derive a text-based rating from the body of the reviews. We then group similar users together using soft clustering techniques based on the topics and sentiments that appear in the reviews. Our results show that using textual information results in better review score predictions than those derived from the coarse numerical star ratings given by the users. In addition, we use our techniques to make fine-grained predictions of user sentiments towards the individual topics covered in reviews with good accuracy.     

Impact of information systems on customers

The distinction between “users” of information systems of an organization and “customers” of the organization has not surfaced clearly in the literature on information systems planning and implementation. Also, the impact of the organization's information system on its customer is neither assessed nor clarified. This paper seeks to expose and, to some extent, fill these gaps. Based on his experience, the author derives three classes of assumptions likely to be made by organizations in managing the interface with their customers. Possible implications of such assumptions are discussed, and suggestions for planning the interface are offered.     

基于网络新闻评论的四度用户影响力分析模型

由于网络新闻评论的开放性和传播性,经常引发舆论事件,为能正确引导社会舆论,需要重点关注某些具有较高影响力的用户.针对已有方法未能全面考虑表征网络新闻评论用户影响力的因素,提出四度用户影响力分析模型——FDRank(four-degree influence rank),通过综合考虑用户的评论内容、评论情感值、自身质量以...     

基于在线社交网络的动态消息传播模型

传统传播模型较难描述在线社交网络中的复杂活跃模式以及节点间的拓扑差异,并且其接触式的传播者退化方式也与现实不符。针对理论模型模拟与现实消息传播的不符,提出一个基于在线社交网络的动态消息传播模型D-SIR。该模型考虑了在线社交网络中影响消息传播的一些实际因素,引入基于传播延迟的退化方式使传播者自发地退化成免疫者,动态指定节点的权威度和免疫力以适应非均质网络,并考虑接收增强信号效应以及外部社会加强效果。在采集的新浪微博真实传播网络数据中,通过参数变化的传播仿真实验验证了D-SIR模型可以有效反映在线社交网络的现实传播情形,并且较传统模型更具灵活性及可扩展性。     

基于在线地图的气象信息管理系统

随着国家信息化建设力度的不断加强,有越来越多的气象综合观测系统得以建立和完善.全国各地观测收集了大量的气象信息.而随着国民经济的不断发展,社会对于气象信息系统的需求不断提高,因此现有的气象信息系统越来越难以满足社会不同层面的需求.本文通过利用较为成熟的在线地图与气象信息进行结合,开发了一款简单易用、界面友好、性能优良的气象信息管理系统.     

Segmenting customers in online stores based on factors that affect the customer’s intention to purchase

This study has proposed an approach that enables online stores to offer customized marketing by segmenting their customers based on customers’ psychographic data. Online stores can concentrate on more profitable activities by identifying customers’ value as they segment their customers into a few groups of customers with similar intentions to purchase. To segment online customers, based on previous research that explains the behavior of online customers regarding purchasing, the approach has employed the factors that affect the customers’ intention to purchase on the Web. We integrated the clustering results of SOM (self-organized map) and the k-means algorithm into a single model. Online stores can develop promotional marketing and offer personalized service for e-customers, who are more valuable and more promising, according to the market segments presented by our approach.     

基于社交媒体的在线评论感知有用性预测模型

社交媒体的广泛应用使得人们获取、分享信息更加便捷,在线评论是内容共享型社交媒体的典型代表,能帮助消费者快速制定购买决策。依据信息经济学理论和信息采纳模型,研究影响商品在线评论感知有用性的主要因素,构建了在线商品评论感知有用性预测模型,并以亚马逊网站上商品的实际评论数据进行了实证分析。结果表明,评论深度、评论者可信度、评论情感倾向和评论及时性与感知有用性为正相关关系,并根据研究结果对电商企业管理提出相关建议。     

The effect of negative online consumer reviews on product attitude: An information processing view

Online consumer reviews provide product information and recommendations from the customer perspective. This study investigates the effects of negative online consumer reviews on consumer product attitude. In particular, it examines the proportion and quality of negative online consumer reviews from the perspective of information processing. The elaboration likelihood model is used to explain the persuasive effect of the proportion and quality depending on product involvement. A high proportion of negative online consumer reviews elicits a conformity effect. As the proportion of negative online consumer reviews increases, high-involvement consumers tend to conform to the perspective of reviewers, depending on the quality of the negative online consumer reviews; in contrast, low-involvement consumers tend to conform to the perspective of reviewers regardless of the quality of the negative online consumer reviews. The experiment in this study uses 248 college students in Korea. The proposed hypotheses are tested by three-way analysis of covariance.     

Presenting dynamic information on mobile computers

A problem with mobile computing devices is the output of dynamic information owing to their small screens. This paper describes an experiment to investigate the use of non-speech sounds to present dynamic information without using visual display space. Results showed that non-speech sound could be used in a simple share-dealing scenario to present a “sound graph” of share prices. This allowed participants to reduce the workload they had to invest in share-price monitoring as they could listen to the graph whilst they worked in a share accumulation window.     

An evaluation of medical residents utilization of tablet computers

Today’s medical students are digital natives who, for their entire life, have been surrounded by digital technology. Our research focuses on a tablet computer’s usability in medical education, and the subsequent transfer from the classroom to the work environment. For a period of three years, all incoming pediatric residents at a large southeastern university were provided an iPad. At the end of the 3-year program, we surveyed the residents measuring perceptions of iPad use and satisfaction. Fifty-six (60%) of the residents responded to the survey. A statistically significant number reported an increased amount of time spent with the tablet throughout their medical education. Similarly, a significant difference exists between those who believe the device to be a necessary part of medical education versus those stating it would be nice but not necessary. We present figures detailing how three conceptual areas: receiving information, inputting information, and collaboration (consisting of ten different facets of the tablet’s use) impacted their medical education. Residents throughout their medical education use the tablet extensively. There is variance in the areas where the tablet is the preferred tool versus a smartphone or computer. A clear majority of students expect to transition the tablet into their workplace upon completing residency. We argue a tablet is a useful tool for graduate medical education and later medical practice.     

基于书写行为与语义特征的评论有用性评估

针对电子商务网站充斥着大量有用性较低的评论,提出一种基于用户书写行为与语义特征的中文评论有用性评估方法。方法通过在Web客户端实时监听评论文本框值的变化,识别出句尾插入、非句尾插入、句尾删除、非句尾删除等书写行为,在服务器端根据书写行为、评论的语义特征建立的线性评估模型计算用户评论的有用性。实验结果表明该方法能够较为准确地识别有用性较高的评论。     

在线投保系统中信息安全技术的应用研究

以在线投保系统的信息安全技术为主线,研究了信息安全技术在保险行业的应用。首先搭建了在线投保系统的框架结构,然后结合具体问题建立了具体分析机制,重点对该系统的安全模式和系统实现方式展开了深入研究,最后建立一套有效的监督维护体系,为投保系统的安全运行、信息安全技术管理水平的优化提供了有力保障。     

基于多维度体感信息的在线考试异常行为监测

考试者监测是在线考试面临的主要难题之一。传统监测方案主要集中在考试者的身份识别方面,缺乏对考试者异常行为的有效识别。面向在线考试异常行为监测,提出通过体感数据采集仪Kinect获得考试者的骨骼关节点位置以及头部偏转角度等姿态数据,判别在线考试过程中考试者的异常行为。同时,针对单一的动作事件判别方法存在的虚警率高的问题,提出利用多维度体感信息识别考试者行为的新思路。通过分析一个时间窗口内异常事件发生的频次以及持续时间等信息,判断考试者当前的行为是否异常。实验表明,所提方案可以有效地监测考试者在考试过程中出现的异常行为。     

Predicting the use of online information services based on a modified UTAUT model

There is a growing consensus that the conventional technology acceptance model should be modified and expanded to provide a better understanding of the behaviour related to Internet services. Recognising this need, this study re-evaluates the utility of Venkatesh et al.’s [2003. User acceptance of information technology: toward a unified view. MIS Quarterly, 27 (3), 425–478] Unified Theory of Acceptance and Use of Technology (UTAUT) model. First, this study proposes a new modified model of technology acceptance by adding the concepts of trust and flow experience to the original UTAUT model. Second, the study investigates how the model's explanatory power changes for different types of Internet services. For this, this study considers two services – ‘e-learning’ and ‘online gaming’ – for their utilitarian and hedonic characteristics, respectively. The results of this study suggest that the proposed model can better explain behavioural intentions towards Internet services than the original model. The two variables – flow experience and trust – contributed to the overall significance of the model. Furthermore, the type of Internet service moderated the effects of the independent variables on behavioural intentions and use behaviour.     

基于FPGA快速实现定制化RISC-V处理器

随着RISC-V指令集的流行,出现了一批应用于IoT智能硬件、嵌入式系统、人工智能芯片、安全设备及高性能计算等不同领域的开源和商业IP软核。性能、功耗和面积三者之间的平衡需要指令集可裁剪、易扩展,以及软件开发环境的配套支持。为此,按照增加自定义指令、扩展ALU功能单元、连接控制信号和数据通路、FPGA原型验证、定制交叉编译环境和应用程序测试的流程,基于FPGA快速实现了定制化RISC-V处理器。以加速矩阵运算为例,基于FPGA在开源IP蜂鸟E203上设计了一条计算向量内积的自定义指令,并在FPGA上进行了原型验证。应用测试程序表明,定制化的RISC-V处理器的计算性能有显著提升,矩阵乘法运算的性能加速比达到了5.3～7.6。     

Applying uncertainty theory into the restaurant recommender system based on sentiment analysis of online Chinese reviews

World Wide Web - In this study, we utilize users’ reviews to a restaurant recommender system to further explore users’ opinions by the proposed recommender approach. Considering the...