Detecting Misinformation During the REU Summer Computing Program « News @ ODU
September 08, 2022
By Tiffany Whitfield
Have you heard that deer spread COVID? Have you seen the latest shared screenshot that looks cool but is far from factual?
Fake news like this was at the heart of disinformation research conducted by students across the country at Old Dominion University for the 2022 National Science Foundation (NSF) Research Experiments for Undergraduates (REU) from the Computer Science Department. Beginning last summer and running for the next two years, ODU’s Computer Science faculty has been awarded $324,000 to conduct research on “Research Experiments for Undergraduate Students in Detection and Analysis of disinformation”.
For 10 weeks in the summer of 2022, eight students worked with leading computer science professors on misinformation. The students came from ODU, Christopher Newport University (CNU), Norfolk State University, University of California at Berkeley; the University of Virginia; and West Virginia University. For most students in the program, delving into misinformation — and choosing their research topic — was a new experience.
“The misinformation that spreads on the internet and social media is not just a nuisance. It is causing real harm,” said Sampath Jayarathna, assistant professor at ODU, principal investigator of the NSF grant. “There is consensus that a significant amount of false or misleading information is deliberately produced to confuse, influence, harm, mobilize or demobilize a target audience.”
REU students chose topics relevant to the expertise of ODU faculty and pursued research projects to advance their skills in STEM fields such as data science, data analytics, information retrieval, applied machine learning, web archiving and social computing.
For three of REU’s computer science participants – Hailey Bragg, Caleb Bradford and Ethan Landers – this was their first formal research experience. Working one-on-one with ODU experts left an indelible impression on their plans.
Bragg, a rising senior at CNU, has been working on a project called “Finding Instagram’s Information Trails.”
“Instagram is under-researched compared to Twitter and Facebook because it has more privacy settings,” Bragg said. “We tried to find patterns that characterize misinformation campaigns versus messages from health authorities like the CDC.” She discovered that misinformation campaigns are not well archived by Instagram.
Another aspect of her research led her to study the 12 content creators who, according to a report by the Center for Countering Digital Hate in 2021, are responsible for more than 65% of anti-vaccine content on all social media platforms. .
Bragg’s mentor, Assistant Professor Michele Weigle, helped her through the research process, from weekly meetings to deep-dive into Instagram research.
“I was really impressed with all of the students and the amount of interesting work that was done over the summer,” Weigle said. “I was excited to see the impact we could have by giving students even a short-term introduction to research and a taste of what graduate school could be like.”
For Bragg, working with his mentor was a great experience.
“I learned so much from her,” Bragg said. “She helped me move from an undergraduate mindset, where your mentor knows the answers and you just have to find the solution and check with them, to this research mindset where maybe no one knows the answer and you are collaborating with your mentors to work together to discover something no one has ever studied.”
Caleb Bradford, a rising senior majoring in computer science at ODU, researched tweet attributions from screenshots. Screenshots of tweets can be found not only on Twitter, but on all social networks.
They “are extremely prevalent because it’s one of the only ways to share sharing across platforms,” Bradford said.
In the program, he learned that misinformation is “someone with malicious intent trying to gain something by intentionally spreading information. Tweets can very easily be fabricated or altered, so this project is about, from a screenshot of a tweet, how can we verify that it’s a real tweet that can be attributed to this person,” Bradford said. “We are not investigating whether the tweet in question is true or not. We are wondering whether it was made or not.”
With the help of his mentor, Professor Michael Nelson, Bradford learned to check screenshots using the Python programming language.
“There are so many tweets from politicians that are fabricated, whether it’s for satire or not, but certainly a lot of them are also misinformation, malicious intent,” Bradford said.
In his research, he saw misinformation spread like wildfire.
“I’ve seen reputable people share screenshots of a tweet thinking it was real, but it’s not,” Bradford said.
Another REU participant, Ethan Landers, is a rising junior in ODU’s IT department. His summer research focused on an evaluation of scientific models for verifying claims.
“Fundamentally, that means the focus is on automating the labeling of scientific claims in general, whether or not they contain misinformation,” Landers said.
Since the pandemic, many models have been created to detect misinformation regarding COVID claims. Models provide a true or false label and an abstract justification that defends the label.
“The goal of my project was to be able to test these models with more general scientific claims and see how effective they are at detecting fake news science related to COVID,” Landers said. “We hope to see if these models can detect generalized data.”
More importantly, he learned that “misinformation is bad intention, deliberately spreading false information to gain some type of advantage and also to influence people in some way, in favor of oneself or a party” .
He thinks it is spreading fast.
“It’s good that this program exists to conduct further research on the subject and hopefully find ways to prevent it,” Landers said.
Working alongside Jian Wu, Assistant Professor and Co-Principal Investigator for REU, was a game-changer for Landers. He is an online student, and it was his first time not only doing research of this magnitude, but also being on campus and fully interacting with his peers, graduate students, and faculty of computer science.
Working one-on-one with global experts here at ODU has changed some students’ plans. After Bragg graduates from CNU in the spring of 2023, she plans to pursue a master’s degree at ODU. Bradford was offered a position as a research assistant to Professor Nelson.
“I am amazed that the students and mentors have accomplished such impressive projects during the intensive nine weeks,” Assistant Professor Wu said. this effective and successful program.”