Border Collie optimisation algorithm for Twitter sentiment classification based on enhanced Elman spike neural network

The sentiment classification field has been increasingly interesting for academic and industrial study due to the widespread development of online reviews. Many sentiment classification approaches are developed to carry out sentiment analysis. Nevertheless, the information retrieval is not carried out precisely, is inefficient, and does not converge as quickly. To overcome these issues, an Enhanced Elman Spike Neural Network optimised with Border Collie Optimisation Algorithm for Twitter sentiment classification (EESNN-BCOA-TSC) is proposed in this paper for classifying the Twitter data. Here, the Twitter data is amassed from Twitter sentiment dataset. Then the input Twitter data is pre-processed. This pre-processed data is fed to the fast discrete curvelet transform with wrapping algorithm (FDCT-WA) for extracting the features. These extracting features are fed to EESNN-BCOA that categorises the Twitter data as positive, negative or neutral. The proposed EESNN-BCOA-TSC technique is activated in Python. From the analysis, it attains better accuracy of 99.7%, sensitivity of 98.8%, and F1-score 98.9%.