A Proposal for Book Oriented Aspect Based Sentiment Analysis: Comparison over Domains - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Proposal for Book Oriented Aspect Based Sentiment Analysis: Comparison over Domains

Résumé

Aspect-based sentiment analysis (ABSA) deals with extracting opinions at a fine-grained level from texts, providing a very useful information for companies which want to know what people think about them or their products. Most of the systems developed in this field are based on supervised machine learning techniques and need a high amount of annotated data, nevertheless not many resources can be found due to their high cost of preparation. In this paper we present an analysis of a recently published dataset, covering different subtasks, which are aspect extraction, category detection, and sentiment analysis. It contains book reviews published in Amazon, which is a new domain of application in ABSA literature. The annotation process and its characteristics are described , as well as a comparison with other datasets. This paper focuses on this comparison, addressing the different subtasks and analyzing their performance and properties.
Fichier principal
Vignette du fichier
NLDB_23.pdf (365.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01958697 , version 1 (21-02-2019)

Identifiants

  • HAL Id : hal-01958697 , version 1

Citer

Tamara Álvarez-López, Milagros Fernández-Gavilanes, Enrique Costa-Montenegro, Patrice Bellot. A Proposal for Book Oriented Aspect Based Sentiment Analysis: Comparison over Domains. Natural Language Processing and Information Systems. NLDB 2018, May 2018, Paris, France. pp.3-14. ⟨hal-01958697⟩
102 Consultations
425 Téléchargements

Partager

Gmail Facebook X LinkedIn More