PANcakes team

A composite system of genre-Agnostic features for author profiling

Pepa Gencheva, Martin Boyanov, Elena Deneva, Preslav Nakov, Yasen Kiprov, Ivan Koychev, Georgi Georgiev

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

We present the system we built for participating in the PAN-2016 Author Profiling Task [9]. The task asked to predict the gender and the age group of a person given several samples of his/her writing, and it was offered for three different languages: English, Spanish, and Dutch. We participated in both subtasks, for all three languages. Our approach focused on extracting genre-Agnostic features such as bag-of-words, sentiment and topic derivation, and stylistic features. We then used these features to train SVM-based classifiers, as implemented in LIBLINEAR for the gender classification sub-Task, and in LIBSVM for the age classification sub-Task.

Original languageEnglish
Pages (from-to)874-880
Number of pages7
JournalCEUR Workshop Proceedings
Volume1609
Publication statusPublished - 1 Jan 2016

Fingerprint

Large scale systems
Classifiers

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Gencheva, P., Boyanov, M., Deneva, E., Nakov, P., Kiprov, Y., Koychev, I., & Georgiev, G. (2016). PANcakes team: A composite system of genre-Agnostic features for author profiling. CEUR Workshop Proceedings, 1609, 874-880.

PANcakes team : A composite system of genre-Agnostic features for author profiling. / Gencheva, Pepa; Boyanov, Martin; Deneva, Elena; Nakov, Preslav; Kiprov, Yasen; Koychev, Ivan; Georgiev, Georgi.

In: CEUR Workshop Proceedings, Vol. 1609, 01.01.2016, p. 874-880.

Research output: Contribution to journalConference article

Gencheva, P, Boyanov, M, Deneva, E, Nakov, P, Kiprov, Y, Koychev, I & Georgiev, G 2016, 'PANcakes team: A composite system of genre-Agnostic features for author profiling', CEUR Workshop Proceedings, vol. 1609, pp. 874-880.
Gencheva P, Boyanov M, Deneva E, Nakov P, Kiprov Y, Koychev I et al. PANcakes team: A composite system of genre-Agnostic features for author profiling. CEUR Workshop Proceedings. 2016 Jan 1;1609:874-880.
Gencheva, Pepa ; Boyanov, Martin ; Deneva, Elena ; Nakov, Preslav ; Kiprov, Yasen ; Koychev, Ivan ; Georgiev, Georgi. / PANcakes team : A composite system of genre-Agnostic features for author profiling. In: CEUR Workshop Proceedings. 2016 ; Vol. 1609. pp. 874-880.
@article{cf5cd38819fe4db4ace0b1b960bdba0c,
title = "PANcakes team: A composite system of genre-Agnostic features for author profiling",
abstract = "We present the system we built for participating in the PAN-2016 Author Profiling Task [9]. The task asked to predict the gender and the age group of a person given several samples of his/her writing, and it was offered for three different languages: English, Spanish, and Dutch. We participated in both subtasks, for all three languages. Our approach focused on extracting genre-Agnostic features such as bag-of-words, sentiment and topic derivation, and stylistic features. We then used these features to train SVM-based classifiers, as implemented in LIBLINEAR for the gender classification sub-Task, and in LIBSVM for the age classification sub-Task.",
author = "Pepa Gencheva and Martin Boyanov and Elena Deneva and Preslav Nakov and Yasen Kiprov and Ivan Koychev and Georgi Georgiev",
year = "2016",
month = "1",
day = "1",
language = "English",
volume = "1609",
pages = "874--880",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - PANcakes team

T2 - A composite system of genre-Agnostic features for author profiling

AU - Gencheva, Pepa

AU - Boyanov, Martin

AU - Deneva, Elena

AU - Nakov, Preslav

AU - Kiprov, Yasen

AU - Koychev, Ivan

AU - Georgiev, Georgi

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We present the system we built for participating in the PAN-2016 Author Profiling Task [9]. The task asked to predict the gender and the age group of a person given several samples of his/her writing, and it was offered for three different languages: English, Spanish, and Dutch. We participated in both subtasks, for all three languages. Our approach focused on extracting genre-Agnostic features such as bag-of-words, sentiment and topic derivation, and stylistic features. We then used these features to train SVM-based classifiers, as implemented in LIBLINEAR for the gender classification sub-Task, and in LIBSVM for the age classification sub-Task.

AB - We present the system we built for participating in the PAN-2016 Author Profiling Task [9]. The task asked to predict the gender and the age group of a person given several samples of his/her writing, and it was offered for three different languages: English, Spanish, and Dutch. We participated in both subtasks, for all three languages. Our approach focused on extracting genre-Agnostic features such as bag-of-words, sentiment and topic derivation, and stylistic features. We then used these features to train SVM-based classifiers, as implemented in LIBLINEAR for the gender classification sub-Task, and in LIBSVM for the age classification sub-Task.

UR - http://www.scopus.com/inward/record.url?scp=85019620799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019620799&partnerID=8YFLogxK

M3 - Conference article

VL - 1609

SP - 874

EP - 880

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -