Skip to Main content Skip to Navigation
Conference papers

Fusion probabiliste appliquée à la détection et classification d'opinions

Abstract : We present probabilistic learning models applied to sentiment classification task as defined in the DEFT'08 challenge. In this task, the texts must be classified following theirs opinions. We have used a mix of several classifiers. A comparison between the results and validation tests shows a remarkable coincidence and highlight the robustness and performance of our mixture algorithm. Our results, (precision, recall and F-score) on the test corpus, enabled us to win the challenge.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01433913
Contributor : Sylvain Meignier <>
Submitted on : Wednesday, April 22, 2020 - 1:33:50 PM
Last modification on : Saturday, May 9, 2020 - 1:00:38 AM

File

7_torres-moreno-1.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01433913, version 1

Collections

Citation

Juan-Manuel Torres-Moreno, Marc El Bèze, Frédéric Béchet, Nathalie Camelin. Fusion probabiliste appliquée à la détection et classification d'opinions. Défi Fouille de Texte (DEFT'09), 2009, Paris, France. ⟨hal-01433913⟩

Share

Metrics

Record views

97

Files downloads

13