Twitter as a Comparable Corpus to build Multilingual Affective Lexicons
Résumé
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).
Domaines
Traitement du texte et du document
Origine : Fichiers produits par l'(les) auteur(s)
Loading...