Text Classification Using Hybridization of Meta-Heuristic Algorithm with Neural Network

Sentiment analysis is one of the important applications of text mining which categorized the text into sentiments. This research work presents the sentiment categorization of text which consists of pre-processing, feature vector extraction, feature selection, and classification steps. The grey wolf technique is used in this work for feature selection to extract the prominent text features from the feature vector. Further, deep learning neural network is used to classify the text into positive and negative sentiments. The validation of the proposed model is done on publicly available Tweeter and movie review datasets namely sentiment140 and Imdb, respectively. The highest 94.16%, 95.81%, 92.87%, and 95.22% of precision, accuracy, recall, and f-measures have achieved, respectively.