Date of Award

Spring 2023

Document Type

Thesis (Master's)

Department or Program

Computer Science

First Advisor

Soroush Vosoughi

Second Advisor

Lorie Loeb

Third Advisor

Rolando Coto Solano


When deciding on what news stories to cover, traditional journalism determines news values by following several elements of newsworthiness, such as impact, timeliness, and prominence. However, these guidelines do not always seem to correspond with the success of content on social media. As people are increasingly turning to social media for news, our research aims to understand and predict factors that drive user engagement for news on social media. In this study, we analyze news content published on Twitter, and examine a diverse set of characteristics like metrics retrieved from the Twitter API and semantics by natural language processing, including a fine-tuned BERT model for topic classification. Various regression and classification models, such as logistic regression, support vector machine, and random forests, are employed to investigate factors that drive user engagement. Our findings indicate that emotion is the most important factor in determining user engagement, followed by text complexity (e.g., tweet length and average word length of a tweet), whereas the topic of a tweet has a minimal impact. Finally, based on our results, we develop a recommendation system that provides actionable suggestions on how to modify a news tweet for better user engagement. Our results provide insights for news organizations seeking to optimize their content strategies for Twitter and engage their audiences more effectively. It can also contribute to the broader conversation on how to achieve a balance between utilizing emotional appeals and user engagement strategies while maintaining objectivity in news reporting.

Available for download on Monday, May 13, 2024