A visual approach for age and gender identification on Twitter

Issue title: Intelligent and Fuzzy Systems applied to Language & Knowledge Engineering

Guest editors: David Pinto, Vivek Kumar Singh, Aline Villavicencio, Philipp Mayr-Schlegel and Efstathios Stamatatos

Article type: Research Article

Authors: Álvarez-Carmona, Miguel A.^{a; *} | Pellegrin, Luis^a | Montes-y-Gómez, Manuel^a | Sánchez-Vega, Fernando^a | Escalante, Hugo Jair^a | López-Monroy, A. Pastor^b | Villaseñor-Pineda, Luis^a | Villatoro-Tello, Esaú^c

Affiliations: [a] Department of Computer Science, Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro 1, Puebla, México | [b] Research in Text Understanding and Analysis of Language Lab, University of Houston, Houston, TX, USA | [c] Language and Reasoning Research Group, Department of Information Technologies, Universidad Autónoma Metropolitana, Unidad Cuajimalpa (UAM-C), Ciudad de México, México

Correspondence: [*] Corresponding author. Miguel A. Álvarez-Carmona, Department of Computer Science, Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro 1, Puebla 72840, México. E-mail: [email protected].

Abstract: The goal of Author Profiling (AP) is to identify demographic aspects (e.g., age, gender) from a given set of authors by analyzing their written texts. Recently, the AP task has gained interest in many problems related to computer forensics, psychology, marketing, but specially in those related with social media exploitation. As known, social media data is shared through a wide range of modalities (e.g., text, images and audio), representing valuable information to be exploited for extracting valuable insights from users. Nevertheless, most of the current work in AP using social media data has been devoted to analyze textual information only, and there are very few works that have started exploring the gender identification using visual information. Contrastingly, this paper focuses in exploiting the visual modality to perform both age and gender identification in social media, specifically in Twitter. Our goal is to evaluate the pertinence of using visual information in solving the AP task. Accordingly, we have extended the Twitter corpus from PAN 2014, incorporating posted images from all the users, making a distinction between tweeted and retweeted images. Performed experiments provide interesting evidence on the usefulness of visual information in comparison with traditional textual representations for the AP task.

Keywords: Visual author profiling, age identification, gender identification, social media, Twitter, CNN representation

DOI: 10.3233/JIFS-169497

Journal: Journal of Intelligent & Fuzzy Systems, vol. 34, no. 5, pp. 3133-3145, 2018