Author profiling using stylometric and structural feature groupings

Printer-friendly versionSend by email
Conference Proceedings (fully refereed)
8
9
2015
Grivas
A. Grivas, A. Krithara, G. Giannakopoulos
In this paper we present an approach for the task of author profiling. We propose a coherent grouping of features combined with appropriate preprocessing steps for each group. The groups we used were stylometric and structural, featuring among others, trigrams and counts of twitter specific characteristics.We address gender and age prediction as a classification task and personality prediction as a regression problem using Support Vector Machines and Support Vector. Machine Regression respectively on documents created by joining each user’s tweets.
Software and Knowledge Engineering Laboratory (SKEL)
Conference Short Name: 
CLEF 2015
Conference Full Name: 
Sixth Conference and Labs of the Evaluation Forum Experimental IR meets Multilinguality, Multimodality, and Interaction
Conference Country: 
FR:France
Conference City: 
Toulouse
Conference Date(s): 
Tue, 08/09/2015 - Fri, 11/09/2015
Conference Level: 
International
Publisher: 
CLEF 2015
Publication Series: 
CEUR Workshop
Volume: 
1392

© 2018 - Institute of Informatics and Telecommunications | National Centre for Scientific Research "Demokritos"

Terms of Service and Privacy Policy