Sentiment classification of movie reviews using GA and NeuroGA

Views or comments expressed in favor or against of any item, a product or a movie, etc. are often available in the form of sentiments of users. These reviews are analyzed with an aim to provide meaningful information to the provider of the product and help in guiding the future users in a more meaningful way. In this manuscript, two different machine learning algorithms are considered for classification of movie reviews. Firstly, Genetic Algorithm (GA), where the movie reviews under analysis are transformed into chromosomes and these chromosomes are then classified using proper technique. Secondly, a combination of GA and Artificial Neural Network (ANN) is considered for the classification purpose. The best fit chromosomes obtained from GA is considered as input for ANN and further processing is carried out by changing the hidden nodes in ANN. The performance of these classifiers are then evaluated using different parameters like recall, precision, f-measure and accuracy.