Including Dialects and Language Varieties in Author Profiling

TL;DR

This paper introduces an ensemble SVM-based method for author profiling that considers gender and language variety, achieving high accuracy on multilingual Twitter data.

Contribution

It presents a novel ensemble approach incorporating character and word n-grams for gender and language variety identification in social media texts.

Findings

75% accuracy in gender identification on tweets

97% accuracy in Portuguese language variety classification

Effective use of ensemble SVMs on multilingual datasets

Abstract

This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese.