Polarity Shifting: Corpus Construction and Analysis

Author

Zhang, Xiaoqian ; Li, Shoushan ; Zhou, Guodong ; Zhao, Hongxia

Author_Institution

Natural Language Process. Lab., Soochow Univ., Suzhou, China

fYear

2011

fDate

15-17 Nov. 2011

Firstpage

272

Lastpage

275

Abstract

Polarity shifting has been a challenge to automatic sentiment classification. In this paper, we create a corpus which consists of polarity-shifted sentences in various kinds of product reviews. In the corpus, both the sentimental words and shifting trigger words are annotated. Furthermore, we analyze all the polarity shifted sentences and categorize them into five categories: opinion-itself, holder, target, time and hypothesis. Experimental study shows the agreement of annotation and the distribution of the five categories of polarity shifting.

Keywords

data analysis; pattern classification; text analysis; corpus analysis; corpus construction; holder category; hypothesis category; opinion-itself category; polarity shifting; polarity-shifted sentence; product review; sentiment classification; sentimental words; shifting trigger words; target category; text classification; time category; Computational linguistics; Data mining; Dictionaries; Machine learning; Manuals; Noise; Vectors; corpus annotation; polarity shifting; sentiment classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Asian Language Processing (IALP), 2011 International Conference on

Conference_Location

Penang

Print_ISBN

978-1-4577-1733-8

Type

conf

DOI

10.1109/IALP.2011.27

Filename

6121519