Dictionary-Based Sentiment Analysis Applied to a Specific Domain

Abstract : The web and social media have been growing exponentially in recent years. We now have access to documents bearing opinions expressed on a broad range of topics. This constitutes a rich resource for natural language processing tasks, particularly for sentiment analysis. Nevertheless, sentiment analysis is usually difficult because expressed sentiments are usually topic-oriented. In this paper, we propose to automatically construct a sentiment dictionary using relevant terms obtained from web pages for a specific domain. This dictionary is initially built by querying the web with a combination of opinion terms, as well as terms of the domain. In order to select only relevant terms we apply two measures AcroDefMI3 and TrueSkill. Experiments conducted on different domains highlight that our automatic approach performs better for specific cases.
Type de document :
Communication dans un congrès
SIMBIg: Symposium on Information Management and Big Data, Sep 2016, Cusco, Peru. Second Annual International Symposium, SIMBig 2015, Cusco, Peru, September 2-4, 2015, and Third Annual International Symposium, SIMBig 2016, Cusco, Peru, September 1-3, 2016, Revised Selected Papers, pp.57-68, 2017, Information Management and Big Data. 〈https://simbig.org/SIMBig2016/〉. 〈10.1007/978-3-319-55209-5_5〉
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01910683
Contributeur : Pascal Poncelet <>
Soumis le : jeudi 1 novembre 2018 - 17:52:11
Dernière modification le : lundi 19 novembre 2018 - 19:56:53

Fichier

37.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Laura Cruz, José Ochoa, Mathieu Roche, Pascal Poncelet. Dictionary-Based Sentiment Analysis Applied to a Specific Domain. SIMBIg: Symposium on Information Management and Big Data, Sep 2016, Cusco, Peru. Second Annual International Symposium, SIMBig 2015, Cusco, Peru, September 2-4, 2015, and Third Annual International Symposium, SIMBig 2016, Cusco, Peru, September 1-3, 2016, Revised Selected Papers, pp.57-68, 2017, Information Management and Big Data. 〈https://simbig.org/SIMBig2016/〉. 〈10.1007/978-3-319-55209-5_5〉. 〈lirmm-01910683〉

Partager

Métriques

Consultations de la notice

55

Téléchargements de fichiers

7