Impact of Pandemic on Demand for Animal Product assess through natural language processing and Machine Learning

In the wake of the COVID-19 pandemic, understanding consumer sentiments and demand patterns has become paramount for businesses across various industries. This research aims to analyze tweet data to uncover insights into the demand for animal products during the COVID-19 era. Leveraging natural language processing techniques, sentiment analysis, and machine learning classification, we examine the text data to identify relevant mentions, sentiments, and trends related to the consumption or demand for animal products. The methodology involves preprocessing the tweet data to remove noise and irrelevant information, followed by keyword search and sentiment analysis to detect mentions and sentiments related to animal products. Additionally, machine learning classification techniques are employed to categorize tweets into classes relevant to demand, such as high demand, low demand, or neutral. Furthermore, the research explores correlations between mentions of animal products and external factors like COVID-19 case numbers, lockdown measures, or economic indicators. This correlation analysis provides insights into the relationship between consumer sentiments and broader socio-economic factors during the pandemic. The findings of this research contribute to a deeper understanding of consumer behavior and demand dynamics in the context of the COVID-19 era. By uncovering insights from tweet data, businesses can gain valuable intelligence to inform their marketing strategies, product offerings, and supply chain decisions. Ultimately, this research aims to provide actionable insights to businesses seeking to adapt and thrive in the ever-changing landscape of consumer demand.