Podcasts are a rapidly growing medium for information sharing, but their audio and one-way communication format presents unique challenges in addressing misinformation. This thesis explores how to empower podcast listeners to identify and respond to misinformation effectively. Study I investigates listening habits, user trust, confidence, and behavioral responses to misinformation in podcasts through a survey of diverse participants. Key findings highlight gaps in user confidence, the impact of demographic factors, and preferences for incentives to flag misinformation. Study II builds upon these insights to design, implement, and evaluate three interventions—PAUSE, ALERT, and VOLUNTARY—aimed at optimizing user engagement in flagging misinformation. A labeled podcast dataset was created to facilitate this task-based experiment. The findings offer insights into the design of user-centric misinformation detection systems. Interventions have shown potential in empowering users to identify misinformation in podcasts. Although, whether they are able to address misinformation in podcasts effectively remains uncertain and needs further exploration. This work not only addresses a significant gap in the literature but also lays the groundwork for future innovations in combating misinformation in podcasts.

Surgical navigation is a tool that surgeons rely on everyday to perform accurate surgeries all over the world. However, this technology requires good hand-eye coordination and a high level of concentration. HoloNav is a project that inquires to see if using the HoloLens and augmented reality can replace the current surgical navigation methods. To do so, the HoloLens must be able to identify the patient and the location of the surgery instruments, which uses optical reflective spheres. This study focuses on using the grayscale cameras of the HoloLens and a deep learning algorithm YOLOv5 to test if it is possible to precisely detect optical reflective spheres. 3 models were trained with two different data sets, where the results show that the model trained on a data set would perform well on the validation set. However, they would perform far worse when exposed to a data set it was not trained on.