High Resolution Sentiment Analysis by Ensemble Classification

This study proposes an approach to ensemble sentiment classification of a text to a score in the range of 1–5 of negative-positive scoring. A high-performing model is produced from TripAdvisor restaurant reviews via a generated dataset of 684 word-stems, gathered by information gain attribute selection from the entire corpus. The best performing classification was an ensemble classifier of RandomForest, Naive Bayes Multinomial and Multilayer Perceptron (Neural Network) methods ensembled via a Vote on Average Probabilities approach. The best ensemble produced a classification accuracy of 91.02% which scored higher than the best single classifier, a Random Tree model with an accuracy of 78.6%. Other ensembles through Adaptive Boosting, Random Forests and Voting are explored with ten-fold cross-validation. All ensemble methods far outperformed the best single classifier methods. Even though extremely high results are achieved, analysis documents the few mis-classified instances as almost entirely being close to their real class via the model’s given error matrix.