Memes are one of the most popular types of content used in an online disinformation campaign. They are most effective on social media platforms since they can easily reach a large number of users. Memes in a disinformation campaign achieve their goal of influencing the users through a number of rhetorical and psychological techniques, such as causal oversimplification, name-calling, smear. The goal of the project is to build models for identifying such techniques in the textual content of a meme only and to identify the span(s) of text covered by each technique, and in a multimodal setting in which both the textual and the visual content are to be analyzed together. To achieve my goal, I compared the classic classification models with the state-of-art models.
Ruyuan Wan is a master's student in Data Science and Linguistics. Her research interests are on the intersection of Human-Computer Interaction, Natural Language Processing, and Computational Linguistics. In her free time, she likes practicing boxing with her cat.