Bouillot Flavien, Poncelet Pascal, Roche Mathieu.
2014. Classification of small datasets: why using class-based weighting measures?.
In : Proceedings of the 21st International Symposium on Methologies for Intelligent Systems (ISMIS 2014), Roskilde, Denmark, June 25-27, 2014. Troels Andreasen, Henning Christiansen, Juan-Carlos Cubero, Zbigniew W. Ras (eds.)
![[img]](http://agritrop.cirad.fr/style/images/fileicons/application_pdf.png) |
Version publiée
- Anglais
Accès réservé aux personnels Cirad Utilisation soumise à autorisation de l'auteur ou du Cirad. document_574194.pdf Télécharger (289kB) |
Résumé : In text classification, providing an efficient classifier even if the number of documents involved in the learning step is small remains an important issue. In this paper we evaluate the performance of traditional classification methods to better evaluate their limitation in the learning phase when dealing with small amount of documents. We thus propose a new way for weighting features which are used for classifying. These features have been integrated in two well known classifiers: Class-Feature-Centroid and Naïve Bayes, and evaluations have been performed on two real datasets. We have also investigated the influence on parameters such as number of classes, documents or words in the classification. Experiments have shown the efficiency of our proposal relatively to state of the art classification methods. Either with a very few amount of data or with a small number of features that can be extracted from poor content documents, we show that our approach performs well.
Classification Agris : C30 - Documentation et information
U10 - Informatique, mathématiques et statistiques
Auteurs et affiliations
- Bouillot Flavien, ITESOFT (FRA)
- Poncelet Pascal, LIRMM (FRA)
-
Roche Mathieu, CIRAD-ES-UMR TETIS (FRA)
ORCID: 0000-0003-3272-8568
Source : Cirad - Agritrop (https://agritrop.cirad.fr/574194/)
[ Page générée et mise en cache le 2023-03-20 ]
