摘要
为了准确计算WJkipedia中作者可信度,本文通过分析比较现有的Wikipedia作者信任算法,提出一种基于编辑文本与结构的Wikipedia作者信任模型。该模型从作者编辑视角切入,以词条为单位,采用文本分析法对词条各版本内容按照先后顺序进行对比获取各作者的编辑文本,并结合作者插入参考文献和图片的结构信息,获取作者动态信任值。实验结果证明该模型能够很好地区分高信任作者和捣乱者。
In order to accurately calculate the credibility of the authors on Wikipedia,a trust model for the authors on Wikipedia based on the texts and structures is provided in this paper through analyzing and comparing of the existing author- trust algorithm. From the author-texting perspective, each article is a processing unit in our model. The different texts edited by every individual author for an article are acquired by employing the method of text analysis to compare all revisions' texts of the article in a chronological order. And,the dynamic trust value of each author is obtained through using the data of editing text and inserting references and images by the author. The experiment results indicate that our model can perfectly distinguish trustworthy authors from troublemakers.
出处
《情报学报》
CSSCI
北大核心
2015年第7期743-753,共11页
Journal of the China Society for Scientific and Technical Information
基金
国家自然科学基金青年基金项目“基于可信语义wiki的知识库构建方法与应用研究”(项目编号:71203173)的研究成果之一