文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > 互联网 > Research on personalized recommendation system in E-learning
侵权投诉

Research on personalized recommendation system in E-learning

Research on personalized recommendation system in E-learning

2010 2nd International Conforence on Education Technology and Computer (ICETC)

Research on Personalized Recommendation System in E-Iearning

Rong Shan Zhibin Ren

Department of Computer Science Weinan Teachers University Weinan,Shaanxi,P.R .. China 714000

e-mail:gsshanrong@126.com Department of Computer Science Weinan Teachers University Weinan,Shaanxi,P.R.China 714000

e-mail:zbr@wntc.edu.cn

Abstract:With the information explosion in the internet,web personalization becomes more and more important on the web.The paper designs a Browsing Behavior Personalized Information

Recommendation

strategy

System(BBIRS).

A

recommendation puted forward in BBIRS,whitch

through mine the web logs and interactive data by omine and online separately,and the user's intersting degree on the page been caculated by its browsing speed. The system uses two recommendation algorithms according the different intersting degree.

Keywords:personalized recommJ!ntiation;web

mining ;recommJ!ndation model;E-learning

I. INTRODUCTION

As one of the killer internet applications, the emerging e­Education turns out to be an important aspect for the educational area as well as for companies as part of a holistic knowledge management approach[1]. Consequently, it is not surprising that e-Education is now becoming more acceptable to corporations, society, and academia which offer various kinds of online learning environments in support of the flexible, just-in-time, work-on-hand, on­demand learning or training programs regardless of geographical, temporal, physical, social, and economical constraints.

Although the benefits and potentials of the new generation of e-Education are obvious and exiting, unfortunately, so far the great potential of e-Education has been far from being taken full of advantage. Apparently, the current e-Education does not seem to fulfill its promise to become the most important learning paradigm, especially in the context of the increased role of continuous and life-long learning. This is often explained by the fact that, despite their recent impressive developments, most of the currently available e-Education systems and environments are still less appealing than the traditional face-to-face teaching methods for both learners and tutors. From the learner perspective, they often complain about the lack of flexible performance tools in support of personalized and tailored learning, value­added reflection, mutual simulative knowledge sharing, on­demand expertise fmding, just-in-time peer help as well as efficient and timely tutor guidance. From the tutor perspective, the main drawback of current e-Education systems is that they tend to require more effort in terms of

authoring learning materials and preparing tests or examinations than their classical counter parts. The necessity of mastering technology-intensive teaching tools and the lack of the tutor's computer literacy often make tutors reluctant to participate in online teaching activity. Based on the analysis of the aforementioned limitations existing current e­Education systems, it is obvious that on one hand, we need to provide learner with more intelligent learning environment that supports various customized learning services as needed, on the other hand, we need innovative mechanism to all aviate tutor work load in terms of facilitating the development of learning contents and test/exam by hiding as much technique details as possible. Now days more and more educators believe that the above identified factors are a key to the future successful e-Education and thus naturally become the focus and motivation of this dissertation.

Now there are some personalized recommendation system [2], but users are asked to fill out registration information or regularly gives certain products (such as PTV) [3] information to build its user interest model by some of it, or the server access logs been analyzed to understand user behavior and interests to achieve the final recommendation. The former relies heavily on the use of the system, and to some extent will affect the user's normal activities; the latter when the user interest changes, recommended effect declined. For the current recommendation system problems, the paper design a personalized recommendation system which based on the browsing behavior (Browsing Behavior Personalized Information Recommendation System,BBIRS).

II.

A.

ARCHITECTURE OF BBIRS

Browsing Behavior Personalized Information Recommendation System

BBIRS can be divided into online and off-line(see figure 1).

The system mainly consists of Web usage mining, user interest analying, and personalized recommendation . Among them, the framework is based on Web usage mining, its primary task is to complete the preprocessing of web using data which use the results of Web structure preprocessing and Web server logs, that is to form a transation sets by identify users, identify the session and make the path supplement from a large number of Web logs. The transation sets become the treatment object of various

978-1-4244-6370-11$26.00 © 2010 IEEE V4-182

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email