Extraction of Opposite Sentiments in Classified Free Format Text Reviews

Haoyuan Li (1, 2) , Anne Laurent (3) , Mathieu Roche (4) , Pascal Poncelet (3)

1 LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
2 LGI2P - Laboratoire de Génie Informatique et Ingénierie de Production
3 TATOO - Fouille de données environnementales
4 TEXTE - Exploration et exploitation de données textuelles

Most of the previous approaches in opinion mining focus on the classifications of opinion polarities, positive or negative, expressed in customer reviews. In this paper, we present the problem of extracting contextual opposite sentiments in classified free format text reviews. We adapt the sequence data model to text mining with Part-of-Speech tags, and then we propose a belief-driven approach for extracting contextual opposite sentiments as unexpected sequences with respect to the opinion polarity of reviews. We conclude by detailing our experimental results on free format text movie review data.

Domaines: Traitement du texte et du document

Haoyuan Li, Anne Laurent, Mathieu Roche, Pascal Poncelet. Extraction of Opposite Sentiments in Classified Free Format Text Reviews. DEXA 2008 - 19th International Conference on Database and Expert Systems Applications, Sep 2008, Turin, Italy. pp.710-717, ⟨10.1007/978-3-540-85654-2_62⟩. ⟨lirmm-00324582⟩