Automatic political profiling in heterogeneous corpora

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings
EditorsStephane Loiseau, Joaquim Filipe, Joaquim Filipe, Beatrice Duval, Jaap van den Herik
PublisherSciTePress
Pages476-481
Number of pages6
ISBN (Electronic)9789897580741
DOIs
StatePublished - 2015
Event7th International Conference on Agents and Artificial Intelligence, ICAART 2015 - Lisbon, Portugal
Duration: 10 Jan 201512 Jan 2015

Publication series

NameICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings
Volume2

Conference

Conference7th International Conference on Agents and Artificial Intelligence, ICAART 2015
Country/TerritoryPortugal
CityLisbon
Period10/01/1512/01/15

Keywords

  • Automatic profiling
  • Facebook
  • Machine learning
  • Politics classifying
  • Text classification

Fingerprint

Dive into the research topics of 'Automatic political profiling in heterogeneous corpora'. Together they form a unique fingerprint.

Cite this