[Colloquium] Jenna Cryan Candidacy Exam/Jul 1, 2022

[Megan Woodward]

This is an announcement of Jenna Cryan's Candidacy Exam.
===============================================
Candidate: Jenna Cryan

Date: Friday, July 1, 2022

Time: 11 am CST

Remote Location: https://uchicago.zoom.us/j/92491028233?pwd=Q1RwUXM0T1d5SnBLeXhpTkdudkg2UT09<https://urldefense.com/v3/__https://uchicago.zoom.us/j/92491028233?pwd=Q1RwUXM0T1d5SnBLeXhpTkdudkg2UT09__;!!BpyFHLRN4TMTrA!9OnHAtNviGmhNyjNqJz62etdXlKBMdJP9JhPQlGrXc64JT88PYQB8KeK2ELvwLD5otiKYWc8A8EWOhW6-dPjP_wdHEMNhW6C$> (meeting ID: 924 9102 8233, password: 345294)

Location: JCL 346

Title: Measuring Perceptions and Mitigating Bias in Text and Voice

Abstract: Our ability as humans to effectively communicate depends heavily on the language we use and the way we speak to one another. The values of our society are both reflected in and reinforced by our use of language. Detecting how this language could convey bias needs to remain effective as these values evolve over time. Specifically, gendered language in text often affirms gender stereotypes and often perpetuate bias and discrimination. As we as readers absorb written content, gendered language used settings such as biographies, recommendation letters, and job advertisements can negatively impact the subjects and audiences alike. Gender stereotypes have been studied extensively, however, the current methods used today still rely on word banks from nearly 50 years ago. Since then, societal views have continued to evolve and it’s important to be able to reflect these changes. Additionally, significant advances have been made in developing new methods for analyzing how words are used in text. To address this, the methodology of this work proposes updating existing gender lexicons to reflect modern language use, and applying machine learning to detect gendered language more efficiently. In addition to written text, efficient and unbiased communication depends upon not only the content, but the manner in which it is presented. The tone of voice of a speaker can heavily influence how they are perceived. Particularly, changes in emotional tone of voice can reduce these inherent biases in the listener, thereby providing more effective communication. This work explores ways to improve methods for measuring perceptions of gendered language in text and emotion tone in voice, and ways to mitigate resulting biases.

Advisors: Ben Zhao and Heather Zheng

Committee Members: Ben Zhao, Heather Zheng, Marshini Chetty



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220630/506c6ba3/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: uchi_proposal.pdf
Type: application/pdf
Size: 121677 bytes
Desc: uchi_proposal.pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220630/506c6ba3/attachment-0001.pdf>