Sentiment Analysis: Relationship between COVID-19 Twitter Sentiment and Daily Confirmed Cases: A Case Study of New York City.

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Last Modified
  • February 10, 2022
Creator
  • Zinan Bo
    • Affiliation: School of Information and Library Science
Abstract
  • Coronavirus disease 2019 is a new viral disease, named after the year in which it first appeared. On January 30, 2020, the World Health Organization (WHO) declared COVID-19 a pandemic. With the outbreak of the COVID-19 pandemic since the end of 2019, the economy and lives of people around the world have been very severely affected. At the same time, social media has become the main platform for people to express their concerns, opinions and feelings about the pandemic disease. Social media platforms are flooded with a wide variety of information related to COVID-19. As a result, especially during the period of the COVID-19 lockdown, more people were choosing to search for information, express their emotions, and seek peace on social media. Among many social media, Twitter is a popular resource. By analyzing health event data posted on the Twitter platform, researchers can not only get first-hand information about ongoing health events, but they can also get real-time information faster. These can help health professionals and policymakers respond effectively to health-related events. Therefore, this study performs the sentiment analysis of Tweets posted by people in New York from March to December 2020. 20,980 Tweets are collected, along with a daily dataset of confirmed cases in New York City in 2020. The data was cleaned, organized, and merged via Python, and then calculated the correlation values between the two datasets. There is a negative correlation between people's sentiment and daily confirmed cases during COVID-19. This study aims to analyze public sentiment toward the pandemic to better understand how public emotions and views about the pandemic change over time.
Date of publication
Subject
DOI
Resource type
Rights statement
  • In Copyright
Advisor
  • Yue Wang
    • Affiliation: School of Information and Library Science
Degree
  • Master of Science in Information Science
Graduation year
  • 2021
Language

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details zinanbo.pdf 2021-12-06 Public Download