Design and Testing of a Sentiment Analysis Model for Digital Data

Abstract

This study analyzed sentiments on social media regarding American airlines during COVID 19 and IMDb reviews of "Tenet" using the BERT model for sentiment analysis. Results showed Delta Airlines received more positive sentiments than American and United Airlines, which faced consistent negative sentiments. Similarly, "Tenet" reviews exhibited a mix of positive and negative opinions. The BERT model demonstrated high accuracy in sentiment prediction, capturing nuanced opinions. Limitations included potential dataset bias and challenges in encompassing all factors influencing sentiment. Nonetheless, the study highlighted sentiment analysis' potential in understanding evolving public perceptions on social media and beyond. Key Terms − Data Analysis, Public Opinion, Sentiment Analysis, Social Media.