Author Profiling using Complementary Second Order Attributes and Stylometric Features. Notebook for PAN at CLEF 2016

Printer-friendly versionSend by email
Conference Proceedings (fully refereed)
5
9
2016
Bougiatiotis
Bougiatiotis, K. & Krithara, A.
In this paper we present an approach for the task of author profiling. We propose a modular framework, extracting two main group of features, combined with appropriate preprocessing, implementing Support Vector Machines for classification. The two main groups we used were stylometric and discriminative, featuring trigrams on one hand and complementary-weighted Second Order Attributes on the other. We address the problem as a profile based problem creating target profiles and also grouping each user’s tweets in the same document.
Software and Knowledge Engineering Laboratory (SKEL)
Conference Short Name: 
PAN 2016, CLEF 2016
Conference Full Name: 
7th Conference & Labs of the Evaluation Forum
Conference Country: 
PT:Portugal
Conference City: 
Evora
Conference Venue: 
"Colégio do Espírito Santo", University of Évora
Conference Date(s): 
Mon, 05/09/2016 - Thu, 08/09/2016
Conference Level: 
International

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