Sentiment analysis using an ensemble approach of BiGRU model: A case study of AMIS tweets

Abstract

This paper presents a comparably simpler yet effective deep learning approach for sentiment analysis of Twitter topics. We automatically collected positive and negative tweets and labeled them manually, and thus created a new dataset. We then leveraged BiGRU model with an ensemble approach for the binary classification of tweets. Our finalized BiGRU model offered an accuracy of 84.8% as well as an averaged F1-measure of 84.8%(±0.3). Moreover, the ensemble approach, using an averaged prediction of 5-fold strategy, provided the accuracy of 86.3% along with the averaged F1-measure of 86.3%(±0.05). Consequently, the ensemble approach offered better performance even on a smaller dataset used in this study.