摘要
随着Internet的深入发展和不断的普及,Web已经成为人们获取信息,进行学习的最重要的手段之一。但是目前Web系统为所有用户提供相同的服务,其典型的服务方式是通过建立一个Web站点来向所有用户发布相同的信息,Web站点是被动的,然而Web用户的需求却千差万别,用户希望Web系统能够根据他们特性的不同提供个性化的服务,并且WWW上信息的不断增加也使得信息服务的个性化成为必要。一个学校的学生千差万别,普通的学习系统已经不能适应他们的学习,不能体现他们的个性化,因此,根据他们的不同特性开发个性化的学习系统已变得相当重要。
本文首先介绍论文研究的目的及意义、研究现状、主要的内容及论文的组织结构;其次介绍本论文中所需要的相关知识,特别是数据挖掘的方法和Web挖掘的分类等相关知识;然后针对本单位的学生,进行数据源的收集,并对于这些学生的数据进行预处理,给出了相应的算法;利用建造网站的形式来设计个性化的学习系统,对经典的Apriori算法进行改进,用于发现个性化学习系统中上网学生的频繁访问路径,基于关联规则的个性化页面推荐,利用模糊聚类方法对个性相似的学生进行模糊聚类;利用页面的形式给出应用实例;最后对所做的工作进行总结。
Followed the in-depth development and the continued popularity of the Internet, the Web has become one of significant methods with which people access to information and learn. However the Web system does only provide the same service to all users. The typical of its services is through the establishment of a Web site to offer the same information to all users so that Web site is passive. But because of the vastly different needs of Web users, Web users want Web System to content them with individuation service. At the same time the increasing of information on WWW makes it necessary to build individuation services. The ordinary system of learning, for varied students’needs in a school, is no longer suitable to their learning, not reflects their individuation. Therefore, the development of individuation learning system has become very important in accordance with the different individual requirements.
The purpose and significance of this paper is firstly introduces followed by the research evolvement, the main contents and organizational structure of this paper. And then, the required relevant knowledge, special in methods of data mining and Web mining classification, is presented. Then, an algorithm is brought about to preprocess the data collected from students in our school. A new learning system is designed through the way of the construction site in individuation form. The classical Apriori algorithm has been improved to find the paths accessed frequently by students adopted Individuation Learning System. According to the recommended individuation pages based on association rules a Fuzzy clustering methods is adopted to cluster the similar students and examples are given in the form of pages. At last, the whole work done is sum up.
引文
[1] R Cooley, J. Srivastava. Data preparation for mining worldwide web browsing patterns [J]. Journal of Knowledge and Information Systems, 1999. 1(1):531.
[2] Han J.w., Micheline K[加].数据挖掘概念与技术[M].范明,孟小峰译.北京:机械工业出版社,2001.8. 283-284.
[3] Usama F., Gregory P. S.,Smyth P. Knowledge discovery and data mining cowards a unifying framework .In: proc. of the 2"d int' 1 conf. on knowledge discovery and data mining .Portland ,Oregon .August 1996.
[4] [81 (美 )RichardJ .Ro iger,Mi chaelW .Ge atz著,翁敬农译.数据挖掘教程,清华大学出版社.2003.1
[5] Usama F. Gregory P.S., Smyth P.. Knowledge discovery and data mining: towards a unifying framework.In: Proc. of the 20d int' I conf. on knowledge discovery and data mining. Portland, Oregon. August 1996.
[6] Han J., Chiang J., Chee S., etal. Dbminer: A system for data mining in relation database and data warehouse.IN:Proc. CASCON'97 Meeting of Minds,Toronto, Canda, November1997.
[7] 李敬社,张小木,黄泽贵.数据挖掘技术的方法和最新进展[[J]计算机应用,2004(22):54-56.
[8] 邹媛 ,牛振东.基于模糊理论的远程教育网站自调整策略.现代图书情报技术.2004.6.
[9] P er kowitzM ,E tzioni0 ,A daptiveW ebsites:Automatically Synthesizing Web Pages.Proc AAA198, Madison, Wisconsin, 1998:727一732
[10] 谢季坚,刘承平.模糊数学方法及其应用.华中科技大学出版.2002.07
[11] 李华,何茜,吴中福.基于Web的个性化学习系统研究.计算机工程与应用.2002. 13.
[12] 韩家炜,孟小峰,王静,李盛恩.Web 挖掘研究.计算机研究与 发展,Vo1.38,No.4,2001.
[13] 唐菁,张前.,陈泓婕,刘宁,杨炳儒。基于 Web 的文本挖掘。 计算机工程与应用,2002 年 21 期.
[14] KDW 综述:基于 Web 的数据挖掘计算机工程,2003 年 01 期.
[15] 王继成,潘金贵,张福炎.Web 文本挖掘技术研究.计算机研究与发展,Vo1.37,No.5,2000.
[16] Armstrong,R.,Freitag,D.,Joachims,T.,Mitchell,T.,WebWatcher:A Learning Apprentice for the World Wide Web, AAAISpring Symposium on Information Gathering ti-om Heterogeneous,Distributed Environments,Stanford,March 1995.
[17] Joachims,T. Mitchell,T.,Freitag,D.,Armstrong,R.,WebWatcher:Machine Learning and Hypertex[t , Fachgruppentreffen MaschinellesLernen, Dormund,August 1995.
[18] Joachims,T.,Freitag,D.,Mitchell,T.,WebWatcher:ATour Guide for the World Wide Web,http://www.citeseer.com.
[19] 石晶,龚震宇,裘杭萍。基于 Web 使用挖掘的个性化服务系统。 电子科技大学学报 ,2002 年 04 期.
[20] Billsus, D. , Pazzani, M. , Revising User Profiles:The Search forInteresting Web Sites , In Proceedings of the Third International Workshopon:Will tistrategy Learning. AAAI Press.
[21] Lieberman,hl.,Letizia:An Agent that Assists Web Browsing,International, Joint Conference on Artificial Intelligence.http://www.citeseer.com.
[22] Richard J. Roiger,Michael W. Geatz,Data Mining A Tutorial-Based Primer.
[23] 李煊,庄镇泉.web 访问挖掘预处理的用户识别算法.计算机工程与应用. 2002 (7):173-176. [ 24] Cooley R, Mobasher B, Srivastava J. Data preparation for mining world wide web browsing patterns. Knowledge and Information Systems,1999, 1(1):5-32.
[25] 陈宝树,党齐民.Web 数据挖掘中的预处理技术.计算机工程,2002, Vol. 38,No. 3:125-127.
[26] John R Punin,Mukkai S Lrishnamoorthy Mohammed J Zaki.Logml: log markup language for Web usage mining[C].In: Web KDD Work-shop,2001.
[27] http://www.kdnuggets.com/subscribe.html.
[28] 〔钊 (美 )W.H. In m on 著,王志海,林友芳等译,数据仓库,机械工业出版社,2003.03.
[29] 曲红亭,申瑞民.基于数据挖掘的个性化学习导航系统的设计与实现.计算机T程,Vol.29 N o.8, 20 03.0
[30] R A rmstrong,D F reitag,T J oachimse ta l.W ebW atcher:A L earning Apprentice for the World Wide Web In: procc AAAI Spring Symp on Information Gathering from heterogeneous, Distributed Environments, 1995.
[31] 蒋孝明,戴虹,胡现.数据挖掘的关联分析在研究信用卡客户消费行为中的应用.计算机与现代化.2003.11 .
[32] 丁振国,陈静.基于关联规则的个性化推荐系统.计算机集成制造系统,Vol.9 N o.10 ,20 03.10
[33] 陶欢华.基于数据挖掘的 WEB 个性化服务系统的分析研究新疆财经学院学报.总第11期,2004.01.
[34] 邓晖.论网络环境下的学生特征分析系统设计.西南师范大学学报.2002. 12.
[35] 董一鸿,庄越挺基于新型的竞争型神经网络的 Web 日志挖掘.计算机研究与发展.Vol,40 N o.5, 20 03.05 .
[36] 周水银,陈荣秋.基于工 nternet 的客户关系管理研究.工业工程与管 理.2002.02.
[37] Bamshad Mobasher, Robert Cooley, Jaideep Srivastava. Creating daptive Web Sites Through Usage-Based Clustering of URLs.
[38] Magdalini Eirinaki,Michalis Vazirgiannis. Web Mining for Web Personalization.
[39] 边肇祺、张学工等,模式识别,清华大学出版社.
[40] 石建 ,孔样成,苏春萍.论个性化信息提取中的 Web 挖掘技术.情报技术.2003.02.
[41] ] 宋擒豹,沈钧毅.Web 页面和客户群体的模糊聚类算法.小型微型计算机系统.Vo1.22 No.2 2001.2