Sentiment classification of Hinglish text

Abstract

In order to determine the sentiment polarity of Hinglish text written in Roman script, we experimented with different combinations of feature selection methods and a host of classifiers using term frequency-inverse document frequency feature representation. We carried out in total 840 experiments in order to determine the best classifiers for sentiment expressed in the news and Facebook comments written in Hinglish. We concluded that a triumvirate of term frequency-inverse document frequency-based feature representation, gain ratio based feature selection, and Radial Basis Function Neural Network as the best combination to classify sentiment expressed in the Hinglish text.