Supervised text classifiers need to learn from many labeled examples to achieve a high accuracy. However, in a real context, sufficient labeled examples are not always available because human labeling is enormously time-consuming. For this reason, there has been recent interest in methods that are capable of obtaining a high accuracy when the size of the training set is small. In this paper we introduce a new single label text classification method that performs better than baseline methods when the number of labeled examples is small. Differently from most of the existing methods that usually make use of a vector of features composed of weighted words, the proposed approach uses a structured vector of features, composed of weighted pairs of words. The proposed vector of features is automatically learned, given a set of documents, using a global method for term extraction based on the Latent Dirichlet Allocation implemented as the Probabilistic Topic Model. Experiments performed using a small percentage of the original training set (about 1%) confirmed our theories. © 2013 Elsevier Ltd. All rights reserved.

Colace, F., De Santo, M., Greco, L., & Napoletano, P. (2014). Text classification using a few labeled examples. COMPUTERS IN HUMAN BEHAVIOR, 30, 689-697 [10.1016/j.chb.2013.07.043].

Text classification using a few labeled examples

NAPOLETANO, PAOLO
Ultimo
2014

Abstract

Supervised text classifiers need to learn from many labeled examples to achieve a high accuracy. However, in a real context, sufficient labeled examples are not always available because human labeling is enormously time-consuming. For this reason, there has been recent interest in methods that are capable of obtaining a high accuracy when the size of the training set is small. In this paper we introduce a new single label text classification method that performs better than baseline methods when the number of labeled examples is small. Differently from most of the existing methods that usually make use of a vector of features composed of weighted words, the proposed approach uses a structured vector of features, composed of weighted pairs of words. The proposed vector of features is automatically learned, given a set of documents, using a global method for term extraction based on the Latent Dirichlet Allocation implemented as the Probabilistic Topic Model. Experiments performed using a small percentage of the original training set (about 1%) confirmed our theories. © 2013 Elsevier Ltd. All rights reserved.
Articolo in rivista - Articolo scientifico
Data mining; Model; Probabilistic topic; Term extraction; Text classification; Text mining; Human-Computer Interaction; Psychology (all); Arts and Humanities (miscellaneous)
English
689
697
9
Colace, F., De Santo, M., Greco, L., & Napoletano, P. (2014). Text classification using a few labeled examples. COMPUTERS IN HUMAN BEHAVIOR, 30, 689-697 [10.1016/j.chb.2013.07.043].
Colace, F; De Santo, M; Greco, L; Napoletano, P
File in questo prodotto:
File Dimensione Formato  
10.pdf

Solo gestori archivio

Descrizione: Articolo principale
Dimensione 889.75 kB
Formato Adobe PDF
889.75 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/56730
Citazioni
  • Scopus 38
  • ???jsp.display-item.citation.isi??? 33
Social impact