Type of Culminating Activity

Graduate Student Project

Graduation Date


Degree Title

Master of Science in Computer Science


Computer Science

Major Advisor

Francesca Spezzano, Ph.D.


The wide availability of user-contributed content in the online social media facilitates aggregation of people around common interests, worldviews, and narratives. But over the years, internet being the source of information also becomes the source of misinformation. As people are generally awash in information, they can sometimes have difficulty discerning misinformation propagated on web platforms from truthful information. They may also lean heavily on information providers or social media platforms to curate information even though such providers do not commonly validate sources. In this project, we primarily focus was on political news and propose a hybrid model to detect misleading news. We use different modalities including news content (headline, body, and associated image), source bias and social network of users who spread the news to detect whether the news is misleading or factual.

We study the relationship between the publisher bias and news stance and show that hyperpartisan news sources are more likely to spread misleading stories than other sources. Also, we demonstrate that it is not necessary to analyze the news content to detect misleading news, but using features such as publisher bias, user engagements, and images related to the news can achieve comparable performances (AUROC of 0.90 vs. 0.88 and average precision of 0.79 vs. 0.78).