Competitive Author Profiling Using Compression-Based Strategies

Abstract

Author pro ling consists in determining some demographic attributes -such as gender, age, nationality, language, religion, and others- of an author for a given document. This task, which has applications in elds such as forensics, security, or marketing, has been approached from di erent areas, especially from linguistics and natural language process- ing, by extracting di erent types of features from training documents, usually content- and style-based features. In this paper we address the problem by using several compression-inspired strategies that generate diferent models without analyzing or extracting speci c features from the textual content, making them style-oblivious approaches. We analyze the behavior of these techniques, combine them and compare them with other state-of-the-art methods. We show that they can be competitive in terms of accuracy, giving the best predictions for some domains, and they are eficient in time performance.