Résumé automatique de textes d'opinion

Aurélien Bossard (1) , Michel Généreux (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord

There is currently a growing need concerning the analysis of texts expressing opinions or judgements. In this paper, we present a summarization system that is specifically designed to process blog posts, where factual information is mixed with opinions. We show that a classical approach based on surface cues is efficient to summarize this kind of texts. The system is evaluated through a participation to TAC (Text Analysis Conference), an international evaluation framework for automatic summarization, in which our system obtained good results.

Mots clés: Résumé automatique; Analyse d'opinion; Extraction d'information; Traitement automatique du langage

Domaines: Traitement du texte et du document

Aurélien Bossard, Michel Généreux. Résumé automatique de textes d'opinion. 2009. ⟨hal-00527586⟩