Electronic Theses and Dissertations

Date of Award


Document Type


Degree Name

M.S. in Engineering Science

First Advisor

Dawn E. Wilkins

Second Advisor

Dawn E. Wilkins

Third Advisor

Yixin Chen

Relational Format



The COVID-19 pandemic has dramatically affected peoples’ daily lives all over theworld - physically, economically, and emotionally. Due to the virus, many people have died, and many hospitalized. A record number of people have lost their job, and many businesses have closed. The global economy is at risk. People are facing new realities of their lives. Studies have shown that the level of depression is three times higher than before this pandemic. Previous studies have shown that people use social media to express their emotions and feelings. The purpose of this study is to understand the depression during this COVID-19 pandemic using social media data. To study the depression-related tweets, I have used a COVID-19 related dataset that is made available by IEEE. Regarding methods,I have employed unsupervised techniques such as clustering and topic modeling. Besides, I have used sentiment analysis to understand the emotions and subjectivity in the clusters.The result from the analysis shows the change of depression related discussions during this pandemic over a five and a half months period of time. It also shows the characteristics of the overall discussion around depression. The findings may be useful for future depression studies.


Computer Science



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.