Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier


Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded


Month Degree Awarded


First Advisor

James Allan

Second Advisor

W. Bruce Croft

Third Advisor

Brendan O'Connor

Fourth Advisor

Weiai Wayne Xu

Subject Categories

Artificial Intelligence and Robotics | Computer Sciences | Databases and Information Systems | Social Influence and Political Communication | Social Media


Navigating controversial topics on the Web encourages social awareness, supports civil discourse, and promotes critical literacy. While search of controversial topics particularly requires users to use their critical literacy skills on the content, educating people to be more critical readers is known to be a complex and long-term process. Therefore, we are in need of search engines that are equipped with techniques to help users to understand controversial topics by identifying them and explaining why they are controversial. A few approaches for identifying controversy have worked reasonably well in practice, but they are narrow in scope and exhibit limited performance.

In this thesis, we first focus on understanding the theoretical grounding of the state-of-the-art algorithm. We derive an underlying probabilistic model that explains the state-of-the-art controversy detection algorithm. We revisit the properties and assumptions from the derived model, and propose new methods to identify controversy on Webpages. We then point out that the current approaches for controversy detection do not consider time while controversy is a dynamically changing phenomenon. This causes current methods to have delays in recognizing emerging controversial topics or exaggerated effects on outdated controversies. We address time-adaptable controversy detection by estimating the dynamically-changing controversy trend of topic by interpolating the observed level of contention and the public interest over time on the topic. Finally, we offer a method that explains controversy by generating a summary of each stance. Our method ranks social media postings using a score of how likely it is that the given post can be a representative summary of controversy.