Author gender identification from Arabic text

The Gender Identification (GI) problem is concerned with determining the gender of a given text's author. It has a wide range of academic/commercial applications in various fields including literature, security, forensics, electronic markets and trading, etc. To address this problem, researchers have proposed that the writing styles of authors of the same gender share certain aspects, which can be captured by certain stylometric features (SF). Another approach to address this problem focuses mainly on keywords occurrences in each document. This is known as the Bag-Of-Words (BOW) approach. In this work, we study and compare both approaches and focus on the Arabic language for which this problem is still largely understudied despite its importance. To the best of our knowledge, no previous work has considered these approaches for the GI problem of Arabic text. The comparison is carried out under different settings and the results show that the SF approach, which is much cheaper to train, can generate more accurate results under most settings. In fact, the best accuracy levels obtained by the SF and BOW approaches on our in-house dataset are 80.4% and 73.9%, respectively. (C) 2017 Elsevier Ltd. All rights reserved.