期刊名称：Annals of the University of Oradea : Economic Science
印刷版ISSN：1222-569X
电子版ISSN：1582-5450
出版年度：2007
卷号：XVI
期号：01
页码：1093-1096
出版社：University of Oradea
摘要：Starting as personal journals maintained online, blogs evolved and gradually transformed into
genuine media channels. As a digital, centered version of word-of-mouth, they have become a major topic in
both academic and industry. Weblogs and message boards provide online forums for discussion that record the
voice of the public. Woven into this mass of discussion is a wide range of opinion and commentary about
consumer products. This presents an opportunity for companies to understand and respond to the consumer by
analyzing this unsolicited feedback. Given the volume, format and content of the data, the appropriate approach
to understand this data is to use large-scale web and text data mining technologies. We present a system that
learns to recognize emotions based on textual resources and test it on a large number of blog entries where we
used human expertise to determine the attitude of the authors towards the discussion topic.
关键词：blog, marketing, Internet, text analysis, information retrieval
