Multi-Language Neural Network Model with Advance Preprocessor for Gender Classification over Social Media

Abstract

This paper describes approaches for the Author Profiling Shared Task at PAN 2018. The goal was to classify the gender of a Twitter user solely by their tweets. Paper explores a simple and efficient Multi-Language model for gender classification. The approach consists of tweet preprocessing, text representation and classification model construction. The model achieved the best results on the English language with an accuracy of 72.79%; for the Spanish and Arabic languages the accuracy was 72.20% and 64.36%, respectively.