A big data approach to sentiment analysis using greedy feature selection with cat swarm optimization-based long short-term memory neural networks

Sentiment analysis is crucial in various systems such as opinion mining and predicting. Considerable research has been done to analyze sentiment using various machine learning techniques. However, the high error rates in these studies can reduce the entire system’s efficiency. We introduce a novel big data and machine learning technique for evaluating sentiment analysis processes to overcome this problem. The data are collected from a huge volume of datasets, helpful in the effective analysis of systems. The noise in the data is eliminated using a preprocessing data mining concept. From the cleaned sentiment data, effective features are selected using a greedy approach that selects optimal features processed by an optimal classifier called cat swarm optimization-based long short-term memory neural network (CSO-LSTMNN). The classifiers analyze sentiment-related features according to cat behavior, minimizing error rate while examining features. This technique helps improve system efficiency, analyzed using experimental results of error rate, precision, recall, and accuracy. The results obtained by implementing the greedy feature and CSO-LSTMNN algorithm and the particle swarm optimization (PSO) algorithm are compared; CSO-LSTMNN outperforms PSO in terms of increasing accuracy and decreasing error rate.