Automatic Political Profiling in Heterogeneous Corpora

Hodaya Uzan, Esther David, Moshe Koppel, Maayan Geffet-Zhitomirsky

2015

Abstract

In this paper we consider automatic political tendency recognition in a variety of genres. To this end, four different types of texts in Hebrew with varying levels of political content (manifestly political, semipolitical, non-political) are examined. It is found that in each case, training and testing in the same genre yields strong results. More significantly, training on political texts yields classifiers sufficiently strong to classify non-political personal Facebook pages with fair accuracy. This suggests that individuals’ political tendencies can be identified without recourse to any tagged personal data.

Paper Citation

in Harvard Style

Uzan H., David E., Koppel M. and Geffet-Zhitomirsky M. (2015). Automatic Political Profiling in Heterogeneous Corpora . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-074-1, pages 476-481. DOI: 10.5220/0005270104760481

in Bibtex Style

@conference{icaart15,
author={Hodaya Uzan and Esther David and Moshe Koppel and Maayan Geffet-Zhitomirsky},
title={Automatic Political Profiling in Heterogeneous Corpora},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2015},
pages={476-481},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005270104760481},
isbn={978-989-758-074-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Automatic Political Profiling in Heterogeneous Corpora
SN - 978-989-758-074-1
AU - Uzan H.
AU - David E.
AU - Koppel M.
AU - Geffet-Zhitomirsky M.
PY - 2015
SP - 476
EP - 481
DO - 10.5220/0005270104760481