SWAT-CMW: Classification of Twitter Emotional Polarity using a Multiple-Classifier Decision Schema and Enhanced Emotion Tagging

In this paper, we describe our approach to Semeval 2015 task 10 subtask B, message level sentiment detection. Our system implements a variety of classifiers and data preparation techniques from previous work. The set of features and classifiers used in the final system produced consistently strong results using crossvalidation on the provided training data. Our final system achieved an F-score of 57.60 on the provided test data. The overall best performing system had an F-score of 64.84.