Date of Completion

Spring 5-3-2024

Thesis Advisor(s)

Suining He

Honors Major

Computer Science and Engineering

Disciplines

Computer and Systems Architecture | Data Storage Systems | Digital Communications and Networking | Other Computer Engineering

Abstract

In today's digital age, social media platforms have become pivotal in influencing public opinion and behavior, with information spreading being both beneficial and detrimental. This rapid spread is typically called an information cascade, and they are important in further understanding social influence, managing misinformation, and even predicting potential trends of public responses. With social media, people are connected so easily to one another like a network, wherein it becomes possible for them to influence each other’s behavior and decisions. Utilizing a dataset from Weibo that spans critical periods of the COVID-19 outbreak, this study integrates machine learning and data analytics to analyze the spread of posts and their impact on public behavior and decision-making. Central to the thesis is the development and application of a Graph Convolutional Network (GCN) model, designed to predict and classify posts as part of significant information cascades. By constructing a graph where nodes represent individual posts and edges depict repost relationships, the model captures how information—both true and false—flows through social networks. This approach allows for a nuanced analysis of connectivity and influence among posts, highlighting how certain information gains prominence.

Download

Share

COinS