Exploring the use of linguistic features in sentiment analysis

Genereux, M. and Santini, M. (2007) Exploring the use of linguistic features in sentiment analysis In: Corpus Linguistics 2007, 27-30 July 2007, Birmingham, UK.


Download (405kB) | Preview


In this paper we describe some explorations of the potential of genre-revealing features on automatic sentiment analysis. In particular, we use a small subset of the ‘linguistic facets’ employed in recent experiments on automatic genre identification in combination with more traditional sentiment-revealing features on two different single-genre corpora: a corpus of English blogs and a corpus of French reviews(relectures). Although still preliminary, results show that linguistic facets might have a positive influence on sentiment analysis because 6 out of 14 facets used in the experiments are among the first 22 most important discriminative features.

Item Type: Contribution to conference proceedings in the public domain ( Full Paper)
Uncontrolled Keywords: Linguistics; Sentiment analysis; Corpus linguistics
Subjects: Q000 Languages and Literature - Linguistics and related subjects > Q100 Linguistics
Faculties: Faculty of Science and Engineering > School of Computing, Engineering and Mathematics > Natural Language Technology
Depositing User: Helen Webb
Date Deposited: 18 Nov 2007
Last Modified: 21 May 2014 11:01
URI: http://eprints.brighton.ac.uk/id/eprint/3210

Actions (login required)

View Item View Item


Downloads per month over past year