XJIPC OpenIR  > 多语种信息技术研究室
基于区域——频道访问度的民意热点信息挖掘算法
孟令达; 周喜
2013
Source Publication计算机应用研究
ISSN1001-3695
Volume30Issue:2
Abstract电子政务网站的Web日志中包含大量用户浏览信息,为了有效地从中挖掘民众关注的热点信息,提出基于区域-频道访问度的民意热点信息挖掘算法—PHIMA算法。该算法在分析目前Web日志挖掘算法存在的问题基础上,利用提出的区域-频道访问度概念,设计Web访问矩阵,并基于该矩阵结合区域-频道访问度和灰关联分析法提出。实验表明算法能有效的挖掘民意热点信息。算法可用于电子政务网站站点优化、个性化服务和为决策者提供决策支持等。 更多还原
Other AbstractWeb logs of e-government contain a lot of user browsing information. This paper proposed a Web log mining algorithm named PHIMA, which based on area-channel to mine public hotspot information accurately and efficiently. On the analysis of the applicability of present Web log mining algorithms on e-government Web log mining, area-channel can be used for mining public hotspot information. According to the conception, we proposed a User Access Matrix based preferred public hotspot information mining algorithm. PHIMA was proved accurate and scalable in the experiments. It's suitable for application in E-government, such as to optimize web site or to provide decision support for policy-makers.
Keyword民意热点信息 区域-频道访问度 电子政务 Web使用挖掘 关联分析
Document Type期刊论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/2403
Collection多语种信息技术研究室
Affiliation中国科学院新疆理化技术研究所
Recommended Citation
GB/T 7714
孟令达,周喜. 基于区域——频道访问度的民意热点信息挖掘算法[J]. 计算机应用研究,2013,30(2).
APA 孟令达,&周喜.(2013).基于区域——频道访问度的民意热点信息挖掘算法.计算机应用研究,30(2).
MLA 孟令达,et al."基于区域——频道访问度的民意热点信息挖掘算法".计算机应用研究 30.2(2013).
Files in This Item:
File Name/Size DocType Version Access License
基于区域_频道访问度的民意热点信息挖掘算(409KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[孟令达]'s Articles
[周喜]'s Articles
Baidu academic
Similar articles in Baidu academic
[孟令达]'s Articles
[周喜]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[孟令达]'s Articles
[周喜]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于区域_频道访问度的民意热点信息挖掘算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.