摘要随着互联网的发展,Web2.0网站为互联网用户的信息生成、信息共享及信息获取提供了便利的平台。用户已经从过去的被动接受信息转变到现在的主动发布信息,产生了许多的用户生成内容,标签就是其中的一种。标签可以用于Web 资源的自动分类、信息检索、信息推荐等不同应用场合,用户可以根据自己的意愿给标注对象添加标签,而标签多采取自由标引方式,部分标签并不能有效地揭示资源的内容或主题,就产生了许多低质量的标签,干扰了社会标注系统中资源组织的秩序,降低了标签在应用场合中的质量和用户满意度。64307
本文首先从有关标签质量的文献出发,简要介绍现有标签质量评估的研究工作,同时对标签类型进行划分,根据以上的研究成果,设计了标签质量评测系统,用于用户对中文IT专业博客网的标签进行打分和标签类型选择,收集标签质量评估和标签类型分类用的训练数据集与测试数据集,为以后标签质量的评估提供数据支持。最后根据用户的评价结果对中文IT专业博客网的标签质量进行分析,并发现标签类型为内容相关的标签拥有很高的质量。
关键词:社会化标签,标签质量,评测网站
毕业论文 外 文 摘 要
Title The Study of Chinese Professional Blog Tag Quality Evaluatioin—Case in Chinese IT Professional Blog
Abstract With the development of the Internet, Web2.0 website provides a convenient platform for Internet users to conduct information generation, information sharing and access to information .The users have shift from passive acceptance of information in the past to take the initiative to publish information, and created a lot of user-generated content, the label is one of them.Tags can be used for automatic classification of Web resources, information retrieval, information recommendation , and users can add tags to label objects according to their wishes.But tags take a more free indexing way , part of the tags do not reveal the content or subject matter of the resources ,so a lot of low-quality tags generated to interfere the order of the social tagging system resource organizations, reduce the tags quality in the application and customer satisfaction.
The paper starting with the literature of the tag quality, introduce existing research work of tag quality evaluation briefly, while the tag type be classificated, based on the above findings, the design of the system of tag quality evaluation is used to be rated and selected tag type by users about the tag of the Chinese IT professional blog, collect the training data set and test data set of the use of the tag quality evaluation and tag type classification, provide the support of the tag quality evaluation in the future. Finally, according to the user's evaluation results on Chinese IT professional blog network to analyze the tag quality and found tag type for the content related tags have high quality.
Keywords: social tag, tag quality, evaluation website
目 录
1绪论 1
1.1选题背景 1
1.2研究意义 1
1.3本文的研究思路及内容 1
1.3.1本文的研究思路 1
1.3.2 本文的组织结构 2
2 文献综述 4
2.1 社会化标注系统 4
2.2 社会化标签的统计 4
2.3 标签质量相关研究 4
2.3.1 标签可信度 5
中文专业博客的标签质量评估研究:http://www.youerw.com/jisuanji/lunwen_71401.html