Deep Learning Based Sentiment Classification on User-Generated Big Data

Background: Sentiment analysis of big data such as Twitter primarily aids the organizations with the potential of surveying public opinions or emotions for the products and events associated with them. Objective: In this paper, we propose the application of a deep learning architecture namely the Convolution Neural Network. The proposed model is implemented on benchmark Twitter corpus (SemEval 2016 and SemEval 2017) and empirically analyzed with other baseline supervised soft computing techniques. The pragmatics of the work includes modelling the behavior of trained Convolution Neural Network on wellknown Twitter datasets for sentiment classification. The performance efficacy of the proposed model has been compared and contrasted with the existing soft computing techniques like Naïve Bayesian, Support Vector Machines, k-Nearest Neighbor, Multilayer Perceptron and Decision Tree using precision, accuracy, recall, and F-measure as key performance indicators. Methods: Majority of the studies emphasize on the utilization of feature mining using lexical or syntactic feature extraction that are often unequivocally articulated through words, emoticons and exclamation marks. Subsequently, CNN, a deep learning based soft computing technique is used to improve the sentiment classifier’s performance. Results: The empirical analysis validates that the proposed implementation of the CNN model outperforms the baseline supervised learning algorithms with an accuracy of around 87% to 88%. Conclusion: Statistical analysis validates that the proposed CNN model outperforms the existing techniques and thus can enhance the performance of sentiment classification viability and coherency.