Influence des lexiques d'émotions et de sentiments sur l'analyse de sentiments - Application à des critiques de livres

Abstract : Consumers are used to consulting posted reviews on the Internet before buying a product. But it's difficult to know the global opinion considering the important number of those reviews. Sentiment analysis afford detecting polarity (positive, negative, neutral) in a expressed opinion and therefore classifying those reviews. Our purpose is to determine the influence of emotions on the polarity of books reviews. We define "bag-of-words" representation models of reviews which use a lexicon containing emotional (anticipation, sadness, fear, anger, joy, surprise, trust, disgust) and sentimental (positive, negative) words. This lexicon afford measuring felt emotions types by readers. The implemented supervised learning used is a Random Forest type. The application concerns Amazon platform's reviews. Mots-clés : Analyse de sentiments, Analyse d'émotions (texte), Classification de polarité de sentiments
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02442701
Contributor : Patrice Bellot <>
Submitted on : Tuesday, January 21, 2020 - 11:42:29 AM
Last modification on : Friday, February 7, 2020 - 3:08:01 PM

File

RJCRI_2019_paper_9.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02442701, version 1
  • ARXIV : 2001.07987

Collections

Citation

Patrice Bellot, Lerch Soëlie, Bruno Emmanuel, Elisabeth Murisasco. Influence des lexiques d'émotions et de sentiments sur l'analyse de sentiments - Application à des critiques de livres. COnférence en Recherche d'Informations et Applications - CORIA 2019, 16th French Information Retrieval Conference, Mar 2019, Lyon, France. ⟨hal-02442701⟩

Share

Metrics

Record views

34

Files downloads

12