Full Text Available

Access Repository Access Repository
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Cover Image

Stock markets performance during a pandemic: How contagious is COVID-19?

Background and Motivation: The coronavirus (“COVID-19”) pandemic, the subsequent policies and lockdowns have unarguably led to an unprecedented fluid circumstance worldwide. The panic and fluctuations in the stock markets were unparalleled. It is inarguable that real-time availability of news and so...

Full description

Saved in:
Main Author: Abushahba, Yara
Format: Thesis
Published: AUC Knowledge Fountain 2021
Subjects:
Sentiment Analysis Twitter Affective Computing Covid-19 pandemic volatility global indices
Applied Mathematics
Artificial Intelligence and Robotics
Business Analytics
Business and Corporate Communications
Business Intelligence
Computational Engineering
Corporate Finance
Data Science
Digital Communications and Networking
Finance and Financial Management
Longitudinal Data Analysis and Time Series
Multivariate Analysis
Programming Languages and Compilers
Risk Analysis
Statistics and Probability
Tags: Add Tag
No Tags, Be the first to tag this record!
Summary:Background and Motivation: The coronavirus (“COVID-19”) pandemic, the subsequent policies and lockdowns have unarguably led to an unprecedented fluid circumstance worldwide. The panic and fluctuations in the stock markets were unparalleled. It is inarguable that real-time availability of news and social media platforms like Twitter played a vital role in driving the investors’ sentiment during such global shock. Purpose:The purpose of this thesis is to study how the investor sentiment in relation to COVID-19 pandemic influenced stock markets globally and how stock markets globally are integrated and contagious. We analyze COVID-19 sentiment through the Twitter posts and investigate its effect on financial securities movements. Methodology: In order to determine investor sentiment, we used text mining and Natural Language Processing (NLP) to conduct sentiment analysis on COVID-19 related tweets during the year of 2020 and got the daily polarity of those tweets. We employed a GARCH (1,1) model to study the impact of the investor sentiment, assessed by the COVID-19 related tweets, on the stock markets movements globally, in the conditional heteroscedasticity equation. The thesis uses six global stock market indices from developed markets. Duration of the study: 4th of January 2020 - 21st of December 2020 Conclusion: Our results from the GARCH (1,1) models suggest that the investors’ sentiment based on the COVID-19 tweets shows significant impact on the conditional heteroscedasticity of the developed markets indices, indicating an impact on volatility and trading volumes of the six developed market indices.

Similar Items