And the Winner is ...: Bayesian Twitter-based Prediction on 2016 U.S. Presidential Election
This is an incremental improvement for political forecasting, using social media data.
The paper tackles predicting the 2016 U.S. Presidential Election using Twitter data, achieving 95.8% accuracy on cross-validation and predicting Ted Cruz and Bernie Sanders as nominees.
This paper describes a Naive-Bayesian predictive model for 2016 U.S. Presidential Election based on Twitter data. We use 33,708 tweets gathered since December 16, 2015 until February 29, 2016. We introduce a simpler data preprocessing method to label the data and train the model. The model achieves 95.8% accuracy on 10-fold cross validation and predicts Ted Cruz and Bernie Sanders as Republican and Democratic nominee respectively. It achieves a comparable result to those in its competitor methods.