A Hybrid Approach to Analyse the Public Sentiment on Covid-19 Tweets

Abstract

Objectives: The objective of this study is to introduce a hybrid model for analyzing the people sentiment on covid-19 tweets. Methods: We used a total no. of 27,500 datasets, 70% of the data sets for training and reserved the other 30% for testing. Due to this separation 19,250 samples are used for training, the remaining 8,250 were used to evaluate the accuracy of the test. This paper proposes a technique for sentiment analysis that integrates deep learning, genetic algorithms (GA), and social media sentiment. For more accuracy and performance, we here suggested a hybrid genetic algorithm-based model. A hybrid model is created by assembling the LSTM model and providing it to the genetic algorithm architecture. Findings: LSTM with a genetic model better than LSTM without genetic model. The accuracy of our suggested model is 96.40%. Novelty : The accuracy of the LSTM model for sentiment analysis is 91%. The accuracy of the proposed model is 96.40%. The proposed model is more accurate for sentiment prediction. Keywords: Social network perception, Crossover, Mutation, LSTM, NLP, GA