Detecting Disinformation in Summer Computer Science REU Program « News @ ODU
[ad_1]
September 8, 2022
Tiffany Whitfield
Have you heard that deer spread COVID? Have you seen the latest screenshots shared that look cool but are far from the truth?
Such fake news was at the center of a disinformation study conducted by students across the country at Old Dominion University for the 2022 National Science Foundation (NSF) Undergraduate Research Experience (REU) in the Department of Computer Science. . Over the next two years from last summer, ODU’s computer science department received $324,000 to conduct research toward a “research experience for undergraduates in disinformation detection and analysis.”
For ten weeks in the summer of 2022, eight students worked with leading computer science faculty on disinformation. Students came from ODU, Christopher Newport University (CNU), Norfolk State University, and the University of California, Berkeley. University of Virginia; and West Virginia University. Delving into disinformation and choosing a research topic was a new experience for most students in the program.
“The misinformation that spreads on the internet and on social media is more than just an annoyance. “There is a consensus that a large amount of false or misleading information is deliberately produced to confuse, influence, harm, mobilize or demobilize target audiences.”
REU students choose topics that align with the expertise of ODU faculty and undertake research projects to advance their skills in STEM areas such as data science, data analysis, information retrieval, applied machine learning, web archiving, and social computing. pursued.
For three of the REU computer science participants, Hailey Bragg, Caleb Bradford, and Ethan Landers, this was their first experience with formal research. Working one-on-one with an ODU expert left an indelible impression on their plans.
Bragg, an up-and-coming senior at CNU, worked on a project called “Finding Traces of Information on Instagram.”
“Instagram has not been as well-studied as Twitter or Facebook because of its many privacy settings,” Bragg said. “We’ve been trying to find trends that characterize disinformation campaigns and posts by health authorities like the CDC.” She found that disinformation campaigns weren’t well-archived on her Instagram. .
Another aspect of her research is to study 12 content creators responsible for more than 65% of anti-vaccine content across all social media platforms, according to a 2021 Center for Countering Digital Hate report. is.
Bragg’s mentor, Associate Professor Michele Weigle, has helped her throughout the research process, from weekly meetings to deep dives into Instagram research.
“I was really impressed with all the students and how much interesting research was done over the summer,” said Weigl. “I was excited to see what impact we could make by providing students with a short research introduction and a graduate atmosphere.”
For Bragg, working with his mentor was a great experience.
“I learned a lot from her,” said Bragg. “She goes from an undergraduate mindset where a mentor knows the answer and just needs to find a solution and check with them to find out that no one might know the answer and work with the mentor to solve the problem.” Helped me move into a research mindset.Work with me to discover something no one else has explored.”
Caleb Bradford, an up-and-coming senior computer science major at ODU, investigated tweet attributes from screenshots. Tweet screenshots can be found on all social media, not just Twitter.
These are “very popular because they’re one of the only ways to cross-share across platforms,” says Bradford.
During the program, he learned that disinformation is “a malicious person trying to gain something by intentionally disseminating information.” It’s an actual tweet that can actually be attributed to that person,” Bradford said. I am skeptical.”
With the help of his mentor, Professor Michael Nelson, Bradford learned how to fact-check screenshots using the Python programming language.
“There are so many hoaxed tweets by politicians, satire or not, but many of them are undoubtedly also intended to be disinformation or malicious,” Bradford said.
In his research, he has seen disinformation spread like wildfire.
“I’ve seen reputable people share screenshots of tweets and think it’s real, but it’s not,” said Bradford.
Another REU participant, Ethan Landers, is an up-and-coming junior in ODU’s Computer Science department. His summer research focused on evaluating models for validating scientific claims.
“Fundamentally, what that means is that there is generally a focus on automation to label scientific claims as containing disinformation or not,” Landers said. .
Since the pandemic, many models have been created to detect disinformation about COVID claims. A model provides a true or false label and an abstract rationale to defend that label.
“My project goal was to be able to test these models with more generalized scientific claims and see how effective they are at detecting COVID-related fake science news.” said Landers. “I hope we can see if these models can detect generalized data.”
More importantly, he said, “Disinformation is the malicious intent of intentionally spreading false information to gain some kind of advantage, and also to target people in favor of themselves or a particular party. I learned that it is upsetting in a way.
He believes it is spreading rapidly.
“It’s good that this program exists to do more research into the problem and hopefully find ways to prevent it,” Landers said.
Working with REU Assistant Professor and Co-Principal Investigator Jian Wu was a game changer for Landers.He is an online student and this is It was his first time not only doing research of this magnitude, but being on campus and fully interacting with peers, graduate students, and computer science faculty.
Working one-on-one with global experts here at ODU has changed the plans of some students. Bragg plans to pursue his master’s degree at ODU after graduating from his CNU in the spring of 2023. Bradford was offered a position as Professor Nelson’s research assistant.
“I am amazed at how the students and mentors have accomplished such an impressive project in an intensive nine weeks,” said Wu. “I could see that they both put a lot of effort into making this program effective and fruitful.”
Related news articles
[ad_2]
Source link