I have a PhD in Linguistics from the University of Washington. I study computational sociolinguistics, or how our social identity affects the way we use language in computational contexts. I'm currently a Data Preparation Analyst at Kaggle, where I'm working to increase the breadth & depth of the data available on their public data platform.
I moderate the LingStatsChat Slack channel, a place for friendly discussion & help on linguistic and statistical topics.
If you're interested, you can join at this link.
Some current research projects:
- Investigating how Twitter users with different political affiliations use punctuation and capitalization.
- I, along with Leo Stewart, Amandalynne Paullada and Emma Spiro have a paper, “Non-lexical Features Encode Political Affiliation on Twitter”, at the Workshop on Natural Language Processing and Computational Social Science at ACL
- I also had a poster, along with my co-author Amandalynne Paullada, at the 33rd Northwest Linguistics Conference: “Social Identity and Punctuation Variation in the #BlueLivesMatter and #BlackLivesMatter Twitter Communities”.
- In my dissertation, I showed the ways in which automatic speech recognition falls short when dealing with sociolinguistic variation (like dialects), looked at how human listeners use acoustic and social information when learning a new dialect and computationally modelled that learning to provide a roadmap to help improve automatic speech recognition.
- I was interviewed about sociolinguistic bias in automatic speech recognition for this article by New Scientist.
- My research on dialect and gender bias in Youtube's automatic captions was covered in depth by the Daily Dot, San Francisco Chronicle and L'Atelier (in French). It was also mentioned in this article about prejudice in machine learning and this article by the Atlantic.
- My research on deictic and semantic influences on emoji ordering was featured in New York Magazine's The Science of Us as well as in Supertext Magazine.
Education and Outreach:
- Instructing for Software Carpentry, a volunteer organization which offers free introductory courses in scientific computing (Unix shell, Python, R, Git, SQL).
- Writing a blog to introduce linguistics concepts to a lay audience.
- Volunteering at outreach events such as Paws On Science at the Pacific Science Center.