Paper Info
Title
Stylometric features for emotion level classification in news related blogs
Abstract
Breaking news and events are often posted in the blogo-sphere before they are published by any media agency. Therefore, the blogosphere is a valuable resource for news-related blog analysis. However, it is crucial to first sort out news-unrelated content like personal diaries or advertising blogs. Besides, there are different levels of emotionality or involvement which bias the news information to a certain extent. In our work, we evaluate topic-independent stylometric features to classify blogs into news versus rest and to assess the emotionality in these blogs. We apply several text classifiers to determine the best performing combination of features and algorithms. Our experiments revealed that with simple style features, blogs can be classified into news versus rest and their emotionality can be assessed with accuracy values of almost 80%.
Year
Venue
Keywords
2010
RIAO
emotion level classification,stylometric feature,advertising blogs,different level,news-related blog analysis,simple style feature,news information,media agency,certain extent,news-unrelated content,accuracy value,personal diary,news,classification
Field
DocType
ISBN
World Wide Web,Emotionality,sort,Psychology,Blogosphere
Conference
978-2-905450-09-8
Citations 
PageRank 
References 
4
0.65
2
Authors
4
Name
Order
Citations
PageRank
Elisabeth Lex120129.65
Michael Granitzer282280.14
Markus Muhr3745.53
Andreas Juffinger4689.22