Consumer Concern Extraction in Social Web Reviews - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2014

Consumer Concern Extraction in Social Web Reviews

Origine des inquiétudes des consommateurs dans les critiques sur les sites sociaux

Sebastián Peña Saldarriaga
  • Fonction : Auteur
  • PersonId : 965687
Fabien Poulard
  • Fonction : Auteur
Sylvain Ornetti
  • Fonction : Auteur

Résumé

The main goal we adress in this work is text comprehension in social web through Natural Language Processing. The type of content we are interested in includes noisy sentences for the most part and thus standard topic extraction is generally not applicable. We present here a semi-automatic method based on machine learning and human defined linguistic features that performs points of interest extraction in consumer reviews. We first run a classification of subjective adjectives with a high precision and then use this extracted lexicon to identify co-occurring common nouns. While there is still room for improvement on several levels of our process, the results we obtain with this first method are very promising.
Fichier principal
Vignette du fichier
consumer-concern-extraction.pdf (195.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01142648 , version 1 (15-04-2015)

Identifiants

  • HAL Id : hal-01142648 , version 1

Citer

Joseph Lark, Sebastián Peña Saldarriaga, Emmanuel Morin, Fabien Poulard, Sylvain Ornetti. Consumer Concern Extraction in Social Web Reviews. International Conference on Digital Intelligence 2014, Sep 2014, Nantes, France. . ⟨hal-01142648⟩
259 Consultations
98 Téléchargements

Partager

Gmail Facebook X LinkedIn More