Social and Behavioral Sciences Commons^™

Communicating Uncertain Information From Deep Learning Models To Users, Harishankar Vasudevanallur Subramanian

Masters Theses

“The use of Artificial Intelligence (AI) decision support systems is increasing in high-stakes contexts, such as healthcare, defense, and finance. Uncertainty information may help users better leverage AI predictions, especially when combined with domain knowledge. I conducted two human-subject experiments to examine the effects of uncertainty information with AI recommendations. The experimental stimuli are from an existing image recognition deep learning model, one popular approach to AI. In Paper I, I evaluated the effect of the number of AI recommendations and provision of uncertainty information. For a series of images, participants identified the subject and rated their confidence level. Results …

Airbnbs In The Rural Midwest: Optimizing Listing Content For User’S Decision-Making Processes, Mary Catherine Kosacki

Masters Theses

This research examines the effectiveness of rural Airbnb listing content in influencing user decision-making. The peer-to-peer economy has been rapidly growing over the past decade, providing new opportunities for individuals to offer goods and services to other individuals through corporate platforms. Specifically, the Airbnb platform has rapidly grown, becoming the largest online platform for peer-to-peer property rentals, and one of the largest companies in the peer-to-peer sector of the economy. Previous research on the Airbnb platform has focused primarily on urban areas; however, Airbnbs have a proportionally large impact on local economies in rural areas.

Several methods were employed to …

A Comparative Visual Content Analysis Of The Cdc And Who Covid-19 Infographics, Manushri Pandya

Masters Theses

"In this study, I conducted a comparative visual content analysis of the CDC and WHO COVID-19 infographics. I considered infographics as an important genre of communication during such times because they not only provided sufficient information to the audience but did so in an engaging manner. The goal of my study was to think about the role of infographics in the context of health and risk communication during a pandemic, and to emphasize on the rhetorical elements that constitute the creation of infographics by major health organizations. I specifically focused on three elements: the kinds of information communicated through infographics, …

Communicating With Customers On Social Media In The United States And South Korea: An Analysis Of Four Companies' Practices, Yeonkyung Lee

Masters Theses

"In this study, I analyzed four companies' Facebook and Twitter posts to study the similarities and differences of American and Korean businesses' communication practices on social media. The study used a qualitative research method: each Facebook and Twitter post was assigned as a unit and coded. Southwest Airlines, General Electric, Asiana Airlines, and Samsung Electronics were selected, and a total of 402 Facebook posts and 465 Tweets from July 6 to September 5, 2016, were collected. Each post was coded by two coders under three coding categories: post-content, medium, and Aristotle's pisteis. After the data was coded, I analyzed each …

Yik Yak Posts: A Discourse Analysis, Snehal Ravindra Shirke

Masters Theses

"Anonymity and geolocation create a unique environment for users to communicate with each other. Discourse analysis was conducted to study the posts made on Yik Yak, an anonymous social networking mobile application to understand the communication patterns on an anonymous platform and the posts about taboo topics. The posts were analyzed specifically for patterns on taboo topics and how students interact on the anonymous platform on a particular campus (Missouri S&T campus). Student research assistants coded the collected posts into the pre-defined taboo categories namely sexual activity, non-sexual bodily functions, sexual orientation, mental/emotional health, and "other" taboo topics. I found …