Social media platforms have been growing at a rapid pace, attracting users' engagement with the online content due to their convenience facilitated by many useful features. Such platforms provide users with interactive options such as likes, dislikes as well as a way of expressing their opinions in the form of text (i.e., comments). As more people engage in different social media platforms, such platforms will increase in both size and importance. This growth in social media data is becoming a vital new area for scholars and researchers to explore this new form of communication. The huge data from social media has been a massive aid to researchers in the mission of exploring the public's behavior and opinion pursuing different venues in social media research. In recent years, social media platforms have facilitated the way people communicate and interact with each other. The recent approach in analyzing the human language in social media has been mostly powered by the use of Natural Language Processing (NLP) and deep learning techniques. NLP techniques are some of the most promising methods used in social media analyses, including content categorization, topic discovery and modeling, sentiment analysis. Such powerful methods have boosted the process of understanding human language by enabling researchers to aggregate data relating to certain events addressing several social issues. The ability of posting comments on these online platforms has allowed some users to post racist and obscene contents, and to spread hate on these platforms. In some cases, this kind of toxic behavior might turn the comment section from a space where users can share their views to a place where hate and profanity are spread. Such issues are observed across various social media platforms and many users are often exposed to these kinds of behaviors which requires comment moderators to spend a lot of time filtering out these inappropriate comments. Moreover, such textual "inappropriate contents" can be targeted towards users irrespective of age, concerning a variety of topics not only controversial, and triggered by various events. Our work is primarily focused on studying, detecting and analyzing users' exposure to this kind of toxicity on different social media platforms utilizing state-of-art techniques in both deep learning and natural language processing areas, and facilitated by exclusively collected and curated datasets that address various domains. The different domains, or applications, benefit from a unified and versatile pipeline that could be applied to various scenarios. Those applications we target in this dissertation are: (1) the detection and measurement of kids' exposure to inappropriate comments posted on YouTube videos targeting young users, (2) the association between topics of contents cover by mainstream news media and the toxicity of the comments and interactions by users, (3) the user interaction with, sentiment, and general behavior towards different topics discussed in social media platforms in light of major events (i.e., the outbreak of the COVID-19 pandemic). Our technical contribution is not limited to only the integration of the various techniques borrowed from the deep learning and natural language processing literature to those new and emerging problem spaces, for socially relevant computing problems, but also in comprehensively studying various approaches to determine their feasibility and relevant to the discussed problems, coupled with insights on the integration, as well as a rich set of conclusions supported with systematic measurements and in-depth analyses towards making the online space safer.


If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu.

Graduation Date





Mohaisen, David


Doctor of Philosophy (Ph.D.)


College of Engineering and Computer Science


Computer Science

Degree Program

Computer Science







Release Date

December 2021

Length of Campus-only Access


Access Status

Doctoral Dissertation (Open Access)