Web挖掘技术及其在网络教学评价中的应用

结合W eb日志挖掘技术和数据立方体技术应用于网络教学评价体系,以网络教学体系的W eb服务端和客户端的日志作为数据源,使用数据挖掘技术采集有用的数据进行分析抽取,建立数据库,再应用数据立方体技术、OLAP进行分析处理,得到所需的评价结果。结果表明,此算法可以客观的评价网络教学结果。     

Beauty is more than screen deep: Improving the web survey respondent experience through socially-present and aesthetically-pleasing user interfaces

Web surveys are rapidly becoming standard issue in many researchers’ toolkits; however, measurement error has been shown to affect web surveys to a greater extent than paper-and-pencil surveys (Couper, 2000, Manfreda and Vehovar, 2002). Principles of aesthetic design and social presence have been applied to web surveys to reduce the prevalence of such error with promising results, which were further investigated in this research. A sample of 181 first-year psychology undergraduate students participated in this study. Participants were randomly allocated to view one of eight web survey interfaces, which varied by aesthetic quality and social presence. Exploratory structural equation modeling using the partial least squares method revealed that classical aesthetic quality and social presence were both positively related to perceived ease of use of the web survey interface and positive state affect; social presence and perceived ease of use were positively related to trust in the web survey researcher; classical aesthetic quality was negatively related to negative state affect; and, expressive aesthetic quality was negatively related to perceived ease of use and positively related to positive state affect. Interestingly, expressive aesthetic quality was also positively related to negative state affect. These relationships between aesthetic quality and social presence should inform best practice web survey design recommendations, and future empirical work should extend and test the generalizability of these findings.     

A UNIFIED FRAMEWORK OF TARGETED MARKETING USING CUSTOMER PREFERENCES

One of the fundamental tasks of targeted marketing is to elicit associations between customers and products. Based on the results from information retrieval and utility theory, this article proposes a unified framework of targeted marketing. The customer judgments of products are formally described by preference relations and the connections of customers and products are quantitatively measured by market value functions. Two marketing strategies, known as the customer‐oriented and product‐oriented marketing strategies, are investigated. Four marketing models are introduced and examined. They represent, respectively, the relationships between a group of customers and a group of products, between a group of customers and a single product, between a single customer and a group of products, and between a single customer and a single product. Linear and bilinear market value functions are suggested and studied. The required parameters of a market value function can be estimated by exploring three types of information, namely, customer profiles, product profiles, and transaction data. Experiments on a real‐world data set are performed to demonstrate the effectiveness of the proposed framework.     

BiOSS: A system for biomedical ontology selection

In biomedical informatics, ontologies are considered a key technology for annotating, retrieving and sharing the huge volume of publicly available data. Due to the increasing amount, complexity and variety of existing biomedical ontologies, choosing the ones to be used in a semantic annotation problem or to design a specific application is a difficult task. As a consequence, the design of approaches and tools addressed to facilitate the selection of biomedical ontologies is becoming a priority. In this paper we present BiOSS, a novel system for the selection of biomedical ontologies. BiOSS evaluates the adequacy of an ontology to a given domain according to three different criteria: (1) the extent to which the ontology covers the domain; (2) the semantic richness of the ontology in the domain; (3) the popularity of the ontology in the biomedical community. BiOSS has been applied to 5 representative problems of ontology selection. It also has been compared to existing methods and tools. Results are promising and show the usefulness of BiOSS to solve real-world ontology selection problems. BiOSS is openly available both as a web tool and a web service.     

Implementation of Web‐based argumentation in facilitating elementary school students to learn environmental issues

This research develops a Web‐based argumentation system named the Web‐based Interactive Argumentation System (WIAS). WIAS can provide teachers with the scaffolding for argumentation instruction. Students can propose their statements, collect supporting evidence and share and discuss with peers online. This research adopts a quasi‐experimental design, applying WIAS to the teaching of environmental issues, including mudslides, global warming and nuclear power. Fifty‐seven elementary school fifth graders from two classes participated in this research. With each class as a unit, they were divided into the WIAS group (n = 30) and the traditional argumentation instruction (TAI) group (n = 27). Before research, all students took the pre‐test of the ‘achievement test for environmental issues (ATEI)’ and the ‘environmental literacy scale (ELS).’ Then all students received argumentation training and six classes of argumentation instruction. Students in the WIAS group performed argumentation in the WIAS, while those in the TAI group performed argumentation in a traditional classroom. After the six‐class argumentation instruction, all students took the post‐test of the ATEI and ELS. The results show that students in the WIAS group have significantly better learning effectiveness than those in the TAI group. Students in the WIAS group also exhibited significantly better improvement in their environmental literacy.     

基于引用启发式和URL语义相结合的会话识别方法

会话识别是Web日志的用户行为分析的关键步骤, 精准的会话识别是有效进行用户行为分析的基础。已有的会话识别方法不能有效地动态适应不同的用户（如多IP单用户、单IP多用户）行为, 在Web日志分析的基础上, 提出了一种基于引用启发式和URL语义相结合的会话识别方法。实验结果表明, 改进后的会话识别方法能更有效地识别出用户的真实会话。     

基于群体动力学的协同过滤算法及应用

针对传统协同过滤算法稀疏矩阵和推荐精度不高的问题,根据一种社会心理学模型提出了基于群体动力学的协同过滤算法.该算法综合考虑了个体因素和环境因素对用户评分行为的影响,以此来调整传统的评分预测方法,然后为用户进行推荐.实验结果表明,该算法可以明显地提高推荐的精确度,有效地缓解稀疏矩阵问题;同时该算法还可以有效减少积累误差.最后将该算法成功运用在西安景点的推荐服务上.     

基于随机词汇迭代模型的POI分类检索

从特征选择、局部区域划分和词汇语义相似性计算入手,利用随机词汇迭代模型(random terms iterativemodel,RTIM)进行海量兴趣点(point of interest,POI)文本分类.通过词汇频度、集中度和离散度方法筛选出特征词汇;依据文本与各POI类别间的相似度进行局部区域划分;在每个局部区域内基于词汇在文本中的排列顺序构建词频向量,基于词频向量中词频的随机删除和重构,获取特征映射矩阵;通过特征映射矩阵将文本转为特征向量,并采用SVM分类器进行POI文本分类.实验证明,该方法有效提升了POI文本分类准确性和覆盖率.     

面向在线社区用户的群体推荐算法研究

结合现有两种主要群体推荐算法的优势, 建立新的算法框架, 并引入差异度因素对模型进行优化。另外, 考虑到在线社区用户的特点, 定义互动度指标来描述群体成员间的互动程度, 通过分析其与推荐精度之间的关系, 探讨互动度对群体推荐的影响。选取豆瓣网数据进行实验, 并与传统方法进行比较, 结果表明, 融入差异度的算法具有更好的推荐效果, 且有效的互动机制能够保证较高的推荐精度。     

一种支持服务关联的Web服务选择方法

目前存在的大多数基于QoS(quality of service)的Web服务选择方案都忽略了服务之间的关联关系, 认为服务之间是相互独立的, 使得组合服务的结果与实际有所偏差。为了提高组合Web服务QoS的精确性, 考虑到服务之间的关联关系对组合服务质量的影响, 分别对服务之间的接口关联、业务关联和统计关联三种关联关系进行研究, 提出了一种基于关联度的关联服务集合发现方法, 将支持服务关联的选择问题转换为混合整数规划模型进行求解。实验结果表明, 考虑服务之间的关联关系会提高组合Web服务的质量。