Home > Research > Publications & Outputs > Evaluation and Sociolinguistic Analysis of Text...

Electronic data

  • ajeassp.2016.868.876

    Rights statement: © 2016 Vasiliki Simaki, Iosif Mporas and Vasileios Megalooikonomou. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

    Final published version, 199 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Evaluation and Sociolinguistic Analysis of Text Features for Gender and Age Identification

Research output: Contribution to journalJournal articlepeer-review

Published
Close
<mark>Journal publication date</mark>25/09/2016
<mark>Journal</mark>American Journal of Engineering and Applied Sciences
Issue number4
Volume9
Number of pages9
Pages (from-to)868-876
Publication StatusPublished
<mark>Original language</mark>English

Abstract

The paper presents an interdisciplinary study in the field of automatic gender and age identification, under the scope of sociolinguistic knowledge on gendered and age linguistic choices that social media users make. The authors investigated and gathered standard and novel text features used in text mining approaches on the author's demographic information and profiling and they examined their efficacy in gender and age detection tasks on a corpus consisted of social media texts. An analysis of the most informative features is attempted according to the nature of each feature and the information derived after the characteristics' score of importance is discussed.

Bibliographic note

© 2016 Vasiliki Simaki, Iosif Mporas and Vasileios Megalooikonomou. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.