Text-Based Gender Classification of Twitter Data using Naive Bayes and SVM Algorithm

This paper presents the development of the gender classification system on Twitter tweets. Three feature extraction techniques are explored: Bag of words and 2 variations of meta-attributes extraction. Feature sets are fed to Multinomial Naive Bayes and Support Vector Machine, and results were compared to see which algorithm can produce the best results in the classification task. Experiments show that the SVM outperformed the Naïve Bayes algorithm, obtaining a performance of 56.31%.