Ensemble Hybrid Model for COVID-19 Sentiment Analysis with Cuckoo Search Optimization Algorithm

Abstract

The COVID-19 pandemic has caused anxiety and fear worldwide, affecting people's physical and mental health. This research work proposes a sentiment analysis approach to better understand the public's perception of COVID-19 in India. Two datasets are created by collecting tweets regarding COVID-19 in India. Pre-processing and analysis of datasets are performed by using natural language processing (NLP) techniques. Various features are extracted from collected tweets using three-word embeddings GloVe, fastText, Elmo. The optimal features are selected by cuckoo search optimization algorithm. Finally, the proposed hybrid model of Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (BiLSTM) is used to categorize the tweets into three sentiment categories. Proposed model achieved 94.44% accuracy, 90.34% precision, 88.53% sensitivity, and 89.53% F1 score. It significantly improved over previous approaches, which achieved 80% accuracy.