Gender Classification of Web Authors Using Feature Selection and Language Models

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Abstract

In the present article, we address the problem of automatic gender classification of web blog authors. More specifically, we employ eight widely used machine learning algorithms, in order to study the effectiveness of feature selection on improving the accuracy of gender classification. The feature ranking is performed over a set of statistical, part-of-speech tagging and language model features. In the experiments, we employed classification models based on decision trees, support vector machines and lazy-learning algorithms. The experimental evaluation performed on blog author gender classification data demonstrated the importance of language model features for this task and that feature selection significantly improves the accuracy of gender classification, regardless of the type of the machine learning algorithm used.

Detaljer

Författare
Externa organisationer
  • University of Patras
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Jämförande språkvetenskap och lingvistik

Nyckelord

Originalspråkengelska
Titel på värdpublikationSpeech and Computer
Undertitel på gästpublikation17th International Conference, SPECOM 2015, Athens, Greece, September 20-24, 2015, Proceedings
RedaktörerAndrey Ronzhin, Rodmonga Potapova, Nikos Fakotakis
FörlagSpringer
Sidor226-233
ISBN (elektroniskt)978-3-319-23132-7
ISBN (tryckt)978-3-319-23131-0
StatusPublished - 2015
PublikationskategoriForskning
Peer review utfördJa
Externt publiceradJa

Publikationsserier

NamnLecture Notes in Computer Science
Volym9319
ISSN (elektroniskt)0302-9743