A Comparative Analysis of the Spanish Flu and COVID-19 Pandemics: Economic Impacts and Sentiment Analysis through Historical Data and First-Person Accounts

This study presents an advanced methodological framework for analyzing the economic impacts of pandemics by integrating sentiment analysis with both historical and contemporary economic data. We utilize a comprehensive dataset of firstperson narratives from the 1918-1919 Spanish Flu pandemic, applying Natural Language Processing (NLP) techniques to perform sentiment extraction and temporal sentiment analysis. This qualitative data is paired with quantitative economic indicators from the COVID-19 pandemic era (2014-2024), including Gross Domestic Product (GDP) growth, Consumer Confidence Indices (CCI), inflation rates, and unemployment metrics. Our approach employs sophisticated statistical methods such as vector autoregression (VAR) and structural equation modeling (SEM) to analyze and predict the economic impacts of the Spanish Flu based on contemporary data trends. Using machine learning algorithms, including random forests and gradient boosting machines, we extrapolate economic indicators such as real GDP, wage changes, and trade balances, creating a robust econometric model to compare and contrast the effects of the two pandemics. This integrated analysis combines advanced econometric techniques with sentiment quantification to offer new insights into the economic repercussions of pandemics. By merging historical sentiment data with modern economic metrics, our study provides a comprehensive framework for understanding pandemic-induced economic shifts and informs policy development with empirical evidence on resilience and economic recovery strategies.