News Bias Analysis Based on Stakeholder Mining
News Bias Analysis Based on Stakeholder Mining
复制标题
DOI：
10.1587/transinf.e94.d.578
复制
发表时间：
2011-03-01
影响因子：
0.7
通讯作者：
Yoshikawa, Masatoshi
中科院分区：
文献类型：
--
作者：
Ogawa, Tatsuya;Ma, Qiang;Yoshikawa, Masatoshi
在本文中，我们提出了一种新的利益相关者挖掘机制，通过比较利益相关者的描述来分析新闻文章中的偏见。我们的机制是基于这样一个假设，即利益往往会导致新闻机构的偏见。正如我们所使用的术语，“利益相关者”是新闻文章中描述的事件的参与者，他应该与文章中的其他参与者有一些关系。我们的方法试图从利益相关者、利益相关者的利益和每个利益相关者的描述极性三个方面来阐明文章的偏见。挖掘利益相关者和他们的利益是通过分析句子结构和使用的词汇资源，我们开发的WordNet。为了分析利益相关者描述的极性，我们提出了一种基于词汇资源SentiWordNet的意见挖掘方法。作为分析的结果，我们构建了一个利益相关者关系图，以集团利益相关者共享的共同利益，并代表利益相关者的利益。我们还描述了一个应用系统，我们开发的新闻比较的基础上挖掘机制。本文给出了一些实验结果来验证所提出的方法。
In this paper, we propose a novel stakeholder mining mechanism for analyzing bias in news articles by comparing descriptions of stakeholders. Our mechanism is based on the presumption that interests often induce bias of news agencies. As we use the term, a "stakeholder" is a participant in an event described in a news article who should have some relationships with other participants in the article. Our approach attempts to elucidate bias of articles from three aspects: stakeholders, interests of stakeholders, and the descriptive polarity of each stakeholder. Mining of stakeholders and their interests is achieved by analysis of sentence structure and the use of RelationshipWordNet, a lexical resource that we developed. For analyzing polarities of stakeholder descriptions, we propose an opinion mining method based on the lexical resource SentiWordNet. As a result of analysis, we construct a relations graph of stakeholders to group stakeholders sharing mutual interests and to represent the interests of stakeholders. We also describe an application system we developed for news comparison based on the mining mechanism. This paper presents some experimental results to validate the proposed methods.