@inbook{a6f51b058af54883a00789982707a196,
title = "Gender Identification in Modern Greek Tweets",
abstract = "The aim of this paper is to analyze tweets written in Modern Greek and develop a robust methodology for identifying the gender of their author. For this reason, we compare three different feature groups (most frequent function words, gender keywords, and Author Multilevel N-gram Profiles) using two different machine learning algorithms (Random Forests and Support Vector Machines) in various text sizes. The best result (0.883 accuracy) was obtained using SVMs trained with the AMNP feature group using 100-word tweet chunks. This methodology can lead to reliable and accurate gender identification results using tweet chunk sizes as small as 50 words each.",
keywords = "author profiling, gender identification, Modern Greek, Multilevel Ngram Profiles, Random Forests, Support Vector Machines, twitter",
author = "Mikros, \{George K.\} and Kostas Perifanos",
note = "Publisher Copyright: {\textcopyright} 2015 Walter de Gruyter GmbH, Berlin/Munich/Boston.",
year = "2015",
doi = "10.1515/9783110420296-008",
language = "English",
series = "Quantitative Linguistics",
publisher = "Walter de Gruyter GmbH",
pages = "75--88",
editor = "Arjuna Tuzzi and Martina Benesov{\'a} and J{\'a}n Macutek",
booktitle = "Quantitative Linguistics",
address = "Germany",
}