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 Relationship WordNet, a lexical resource that we developed. For analyzing polarities of stakeholder descriptions, we propose an opinion mining method based on the lexical resource Senti WordNet. We also describe an application system we developed for news comparison based on the mining mechanism. This paper presents a user study to validate the proposed methods.
[1]
Masatoshi Yoshikawa,et al.
Topic and Viewpoint Extraction for Diversity and Bias Analysis of News Contents
,
2009,
APWeb/WAIM.
[2]
Katsumi Tanaka,et al.
A comparative web browser (CWB) for browsing and comparing web pages
,
2003,
WWW '03.
[3]
Jiahui Liu,et al.
LocalSavvy: aggregating local points of view about news issues
,
2008,
LocWeb.
[4]
George A. Miller,et al.
WordNet: A Lexical Database for English
,
1995,
HLT.
[5]
Seungwoo Kang,et al.
NewsCube: delivering multiple aspects of news to mitigate media bias
,
2009,
CHI.
[6]
Christopher D. Manning,et al.
The Stanford Typed Dependencies Representation
,
2008,
CF+CDPE@COLING.
[7]
Andrea Esuli,et al.
SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining
,
2006,
LREC.