Skip to Main content Skip to Navigation
Master Thesis

Découverte automatique des textes littéraires qui présentent les caractéristiques statistiques d'un texte de qualité

Abstract : The field of natural language processing has witnessed very rapid developments in recent years, particularly with respect to methods used for statistical text analysis. These methods have been brought into focus by several disciplines in particular : the study of texts, linguistics, discours analysis, statistics, computer sciences, and survey processing. This research project develops within the framework of an issue that concerns the publishing company Short Editions. It relies on contributions in a field that employs a vast variety of designations (lexical statistics, statistical linguistics, quantitative linguistics, etcetera). Our work involves the creation of a prototype that allows for the identification of texts that present the characteristics of a quality text and to find appropriate methods of classification of these texts based on data and text mining principles.
Document type :
Master Thesis
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download

https://dumas.ccsd.cnrs.fr/dumas-01066867
Contributor : Uga - Bulles <>
Submitted on : Tuesday, September 23, 2014 - 1:39:15 PM
Last modification on : Tuesday, May 11, 2021 - 11:36:17 AM
Long-term archiving on: : Wednesday, December 24, 2014 - 8:50:44 PM

Identifiers

  • HAL Id : dumas-01066867, version 1

Citation

Hamza Maaouia. Découverte automatique des textes littéraires qui présentent les caractéristiques statistiques d'un texte de qualité. Sciences de l'Homme et Société. 2014. ⟨dumas-01066867⟩

Share

Metrics

Record views

437

Files downloads

1268