Document Type


Date of Award


Degree Name

Doctor of Philosophy in Computing Sciences - (Ph.D.)


Computer Science

First Advisor

James Geller

Second Advisor

Soon Ae Chun

Third Advisor

Vincent Oria

Fourth Advisor

Dimitri Theodoratos

Fifth Advisor

Usman W. Roshan


Social media platforms have created virtual space for sharing user generated information, connecting, and interacting among users. However, there are research and societal challenges: 1) The users are generating and sharing the disinformation 2) It is difficult to understand citizens' perceptions or opinions expressed on wide variety of topics; and 3) There are overloaded information and echo chamber problems without overall understanding of the different perspectives taken by different people or groups.

This dissertation addresses these three research challenges with advanced AI and Machine Learning approaches. To address the fake news, as deceptions on the facts, this dissertation presents Machine Learning approaches for fake news detection models, and a hybrid method for topic identification, whether they are fake or real.

To understand the user's perceptions or attitude toward some topics, this study analyzes the sentiments expressed in social media text. The sentiment analysis of posts can be used as an indicator to measure how topics are perceived by the users and how their perceptions as a whole can affect decision makers in government and industry, especially during the COVID-19 pandemic. It is difficult to measure the public perception of government policies issued during the pandemic. The citizen responses to the government policies are diverse, ranging from security or goodwill to confusion, fear, or anger. This dissertation provides a near real-time approach to track and monitor public reactions toward government policies by continuously collecting and analyzing Twitter posts about the COVID-19 pandemic.

To address the social media's overwhelming number of posts, content echo-chamber, and information isolation issue, this dissertation provides a multiple view-based summarization framework where the same contents can be summarized according to different perspectives. This framework includes components of choosing the perspectives, and advanced text summarization approaches.

The proposed approaches in this dissertation are demonstrated with a prototype system to continuously collect Twitter data about COVID-19 government health policies and provide analysis of citizen concerns toward the policies, and the data is analyzed for fake news detection and for generating multiple-view summaries.



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.