Filtering by
- Creators: Affolter, Jacob
The main objective of this dissertation is to provide a systematic study of misinformation detection in social media. To tackle the challenges of adversarial attacks, I propose adaptive detection algorithms to deal with the active manipulations of misinformation spreaders via content and networks. To facilitate content-based approaches, I analyze the contextual data of misinformation and propose to incorporate the specific contextual patterns of misinformation into a principled detection framework. Considering its rapidly growing nature, I study how misinformation can be detected at an early stage. In particular, I focus on the challenge of data scarcity and propose a novel framework to enable historical data to be utilized for emerging incidents that are seemingly irrelevant. With misinformation being viral, applications that rely on social media data face the challenge of corrupted data. To this end, I present robust statistical relational learning and personalization algorithms to minimize the negative effect of misinformation.
This project offers an argument that isolates several major forces that it contends pose a critical threat to the endurance of modern American democracy. It evaluates modern and classic political philosophy to identify the prerequisites for a stable democracy, identifying and defining voter education and participation as necessary contributors to civic engagement. It provides a socio-legal framework for evaluating four phenomena that have shifted in their impact on politics over the past 20 years: the roles of money and media in politics, as well as disenfranchisement by gerrymandering and by felon voting restrictions. It demonstrates how each has a new and worsening impact on voter education and/or participation, thus threatening the continued existence of modern American democracy.