Date: Tuesday, December 12, 2023Time: 12:00pm – 1:00pmLocation: Zoom Abstract: Our project examines media coverage of lynching from 1789 to the current era. Researchers examined metadata of 60,000 pages of news coverage in the Library of Congress’ Chronicling America database and conducted a computational text analysis of a stratified sample. We find that some […]
Soda Seed Grant Series
SoDa Seed Grant Series: Newspapers and the Lynching Story: Discoveries, Distortions, and Erasure, 1789-1963
SoDa Seed Grant Series: Socio-Algorithmic Foundations of Trustworthy Recommendations
Date: February 13, 2024 Time: 12:00pm – 1:00pm Location: Zoom Abstract: Social media newsfeeds shape what people see online but, due to the interplay between human and algorithmic bias, these systems often amplify low-quality information, like misinformation and conspiracy theories. For example, prior work has shown that ranking the news by (either predicted or achieved) […]
SoDa Seed Grant Series: Effective Few-Shot Learning for Constructs in Psychological and Social Science
Date: March 12, 2024 Time: 12:00pm – 1:00pm Location: Zoom Abstract: The idea of a construct is central in the psychological and social sciences: constructs are abstract categories like empathy, misinformation, or benefits of social interaction that are operationalized in order to make them measurable. Social scientists spend an enormous amount of time and care […]
SoDa Seed Grant Series: How Can Data Science Be Used For Racial Equity?
Date: April 9, 2024 Time: 12:00pm – 1:00pm Location: Zoom Abstract: Data science methods are increasingly being applied to large-scale educational data, but there has been less attention on the possibility of algorithmic bias. In this presentation, we present several metrics used for algorithmic bias, discuss how proportions of racial groups impact the presence of […]
SoDa Seed Grant Series: Correlating Population Demographics with Maryland’s County-Level Critical Infrastructure Vulnerabilities
Date: May 7, 2024 Time: 12:00pm – 1:00pm Location: Zoom Abstract: Local government-controlled critical infrastructure relies on computer systems and is increasingly vulnerable to cyber-attacks that can disrupt its operation. This project aims to examine the relationship between cyber vulnerabilities in some critical infrastructure sectors in Maryland counties with available demographic factors to identify potential […]