We describe the approach that we submitted to the 2015 PAN competition for the author profiling task. The task consists in predicting some attributes of an author analyzing a set of his/her Twitter tweets. We consider several sets of stylometric and content features, and different decision algorithms: we use a different combination of features and decision algorithm for each language-attribute pair, hence treating it as an individual problem.



Titolo: An Author Profiling Approach Based on Language-dependent Content and Stylometric Features
Autori: 
BARTOLI, Alberto
DE LORENZO, ANDREA
LADERCHI, ALESSANDRA
MEDVET, Eric
TARLAO, FABIANO
Data di pubblicazione: 2015
Serie: 
CEUR WORKSHOP PROCEEDINGS  
Abstract: We describe the approach that we submitted to the 2015 PAN competition for the author profiling task. The task consists in predicting some attributes of an author analyzing a set of his/her Twitter tweets. We consider several sets of stylometric and content features, and different decision algorithms: we use a different combination of features and decision algorithm for each language-attribute pair, hence treating it as an individual problem.
Handle: http://hdl.handle.net/11368/2846876
URL: http://ceur-ws.org/Vol-1391/
Appare nelle tipologie:4.1 Contributo in Atti Convegno (Proceeding)

File in questo prodotto:
FileDescrizioneTipologiaLicenza 
106-CR.pdf pdf editorialePost-printDigital Rights Management non definitoOpen Access Visualizza/Apri
Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/11368/2846876
  • Citazioni
  • ND
  • ND

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
 
 
 
©2014 University of Trieste dove siamo Privacy
Piazzale Europa,1 34127 Trieste, Italia - Tel. +39 040.558.7111 - P.IVA 00211830328 - C.F. 80013890324 - P.E.C.: ateneo@pec.units.it
 Copyright © 2020