Just how mad are you? Finding strong and weak opinion clauses

by: Theresa Wilson, Janyce Wiebe, Rebecca Hwa

(2004), pp. 761-769.

View FullText article

http://www.cs.pitt.edu/~hwa/aaai04.pdf

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

zador, hehrig

Find related articles with these CiteULike tags

sentiment-analysis, sentiment-orientation

Abstract

There has been a recent swell of interest in the automatic identification and extraction of opinions and emotions in text. In this paper, we present the first experimental results classifying the strength of opinions and other types of subjectivity and classifying the subjectivity of deeply nested clauses. We use a wide range of features, including new syntactic features developed for opinion recognition. In 10-fold crossvalidation experiments using support vector regression, we achieve improvements in mean-squared error over baseline ranging from 57\% to 64\%.

@inproceedings{Wilson2004, abstract = {There has been a recent swell of interest in the automatic identification and extraction of opinions and emotions in text. In this paper, we present the first experimental results classifying the strength of opinions and other types of subjectivity and classifying the subjectivity of deeply nested clauses. We use a wide range of features, including new syntactic features developed for opinion recognition. In 10-fold crossvalidation experiments using support vector regression, we achieve improvements in mean-squared error over baseline ranging from 57\% to 64\%.}, address = {San Jose, US}, author = {Wilson, Theresa and Wiebe, Janyce and Hwa, Rebecca }, booktitle = {Proceedings of AAAI-04, 21st Conference of the American Association for Artificial Intelligence}, citeulike-article-id = {1444203}, keywords = {sentiment-orientation}, pages = {761--769}, posted-at = {2008-03-08 18:18:10}, priority = {2}, publisher = {AAAI Press / The MIT Press}, title = {Just how mad are you? Finding strong and weak opinion clauses}, url = {http://www.cs.pitt.edu/\~{}hwa/aaai04.pdf}, year = {2004} }

RIS record

TY - CONF ID - Wilson2004 L3 - citeulike-article-id:1444203 TI - Just how mad are you? Finding strong and weak opinion clauses T2 - Proceedings of AAAI-04, 21st Conference of the American Association for Artificial Intelligence SP - 761 EP - 769 AD - San Jose, US PB - AAAI Press / The MIT Press N2 - There has been a recent swell of interest in the automatic identification and extraction of opinions and emotions in text. In this paper, we present the first experimental results classifying the strength of opinions and other types of subjectivity and classifying the subjectivity of deeply nested clauses. We use a wide range of features, including new syntactic features developed for opinion recognition. In 10-fold crossvalidation experiments using support vector regression, we achieve improvements in mean-squared error over baseline ranging from 57\% to 64\%. KW - sentiment-orientation AU - Wilson, Theresa AU - Wiebe, Janyce AU - Hwa, Rebecca PY - 2004/// UR - http://www.cs.pitt.edu/~hwa/aaai04.pdf ER -

RIS BibTeX