Leveraging Tweets for Artificial Intelligence Driven Sentiment Analysis on the COVID-19 Pandemic

Area of Science:

• Computational Social Science
• Natural Language Processing
• Artificial Intelligence

Background:

• The COVID-19 pandemic exacerbated psychological issues and increased interest in understanding public sentiment during crises.
• Social media platforms like Twitter serve as a rich source for analyzing user-generated content and public emotional responses.
• Advancements in Natural Language Processing (NLP) and Deep Learning (DL) offer powerful tools for sentiment analysis.

Purpose of the Study:

• To develop and evaluate a novel deep learning model for sentiment analysis of COVID-19 related tweets.
• To identify and classify public sentiments expressed on social media during the pandemic.
• To aid in the development of public health interventions and awareness campaigns.

Main Methods:

• A new Sunflower Optimization with Deep-Learning-driven Sentiment Analysis and Classification (SFODLD-SAC) model was proposed.
• Tweet preprocessing involved stemming, stopword removal, and elimination of usernames, links, punctuation, and numerals.
• TF-IDF was used for feature extraction, followed by a Cascaded Recurrent Neural Network (CRNN) for sentiment analysis and classification.
• The Sunflower Optimization (SFO) algorithm was employed to fine-tune CRNN hyperparameters.

Main Results:

• The SFODLD-SAC model demonstrated high performance in sentiment analysis on a benchmark COVID-19 tweet dataset.
• Comparative analysis showed the SFODLD-SAC model outperformed existing state-of-the-art methods.
• The model achieved a maximum classification accuracy of 99.65%.

Conclusions:

• The SFODLD-SAC model, integrating SFO for hyperparameter optimization, is a novel and effective approach for analyzing public sentiment on COVID-19.
• The model's high accuracy indicates its potential for real-world applications in public health monitoring and policy-making.
• This study highlights the utility of advanced NLP and DL techniques in understanding societal responses to global health crises.