Twitter as a Comparable Corpus to build Multilingual Affective Lexicons

Fraisse, Amel; Paroubek, Patrick

Document type :

Communication dans un congrès avec actes

Title :

Twitter as a Comparable Corpus to build Multilingual Affective Lexicons

Author(s) :

Fraisse, Amel [Auteur]

Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur [LIMSI]
Paroubek, Patrick [Auteur]
Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur [LIMSI]

Conference title :

The 7th Workshop on Building and Using Comparable Corpora

City :

Reykjavik

Country :

Islande

Start date of the conference :

2014-05-26

Book title :

The 7th Workshop on Building and Using Comparable Corpora Proceedings

English keyword(s) :

Affective Lexicon
Comparable Corpus
Sentiment Analysis

HAL domain(s) :

Informatique [cs]/Traitement du texte et du document

English abstract : [en]

The main issue of any lexicon-based sentiment analysis system is the lack of affective lexicons. Such lexicons contain lists of words annotated with their affective classes. There exist some number of such resources but ...
Show more >The main issue of any lexicon-based sentiment analysis system is the lack of affective lexicons. Such lexicons contain lists of words annotated with their affective classes. There exist some number of such resources but only for few languages and often for a small number of affective classes, generally restricted to two classes (positive and negative). In this paper we propose to use Twitter as a comparable corpus to generate a fine-grained and multilingual affective lexicons. Our approach is based in the co-occurence between English and target affective words in the same emotional corpus. And it can be applied to any number of target languages. In this paper we describe the building of affective lexicons for seven languages (en, fr, de, it, es, pt, ru).Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :