Exploring the use of linguistic features in sentiment analysis

M. Genereux, M. Santini

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNpeer-review

Abstract

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.
Original languageEnglish
Title of host publicationCorpus Linguistics 2007
Publication statusPublished - 2007
EventCorpus Linguistics 2007 - Birmingham, UK
Duration: 1 Jan 2007 → …

Conference

ConferenceCorpus Linguistics 2007
Period1/01/07 → …

Keywords

  • Linguistics
  • Sentiment analysis
  • Corpus linguistics

Fingerprint

Dive into the research topics of 'Exploring the use of linguistic features in sentiment analysis'. Together they form a unique fingerprint.

Cite this