Date Thesis Awarded


Access Type

Honors Thesis -- Open Access

Degree Name

Bachelors of Science (BS)


Data Science


Alexander C. Nwala

Committee Members

Dan Runfola

Salvatore Saporito


Phishing scams are a billion-dollar problem. According to Threatpost, in 2020, business email compromise phishing attacks cost the US economy $ 1.8 billion. Social media phishing scams are also on the rise with 74% of companies experiencing social media attacks in 2021 according to Proofpoint. Educating users about phishing scams is an effective strategy for reducing phishing attacks. Despite efforts to combat phishing, the number of attacks continues to rise, likely indicative of a reticence of users to change online behaviors. Existing research into predicting vulnerable social media users that are susceptible to phishing mostly focuses on content analysis of their posts or the users they interact with, and not their behaviors. In contrast, in this research, we study the online behaviors of social media users on Twitter to identify those that are susceptible to phishing attacks. Specifically, we analyzed the behaviors of social media users that succumb to phishing scams in comparison to a control group of users that did not, to identify behavioral patterns that distinguish them. Online actions encompass aspects such as liking and sharing habits, the nature of posts, duration of engagement in posting activities, among others. We classified control and susceptible users based on their page metrics with a KNN model (F1: 0.897) and also based on user behavioral metrics with a logistic regression model (F1 score: 0.903).