I'm a fifth-year PhD student working at the University of Maryland's Computational Linguistics and Information Processing lab, where I'm advised by Philip Resnik.
My research is oriented around the development and evaluation of methods for computational social science. My basic contention is that the field of NLP is well-served served by grounding it in the needs of social science—giving direction to concepts like interpretability and generalization. On the methods side, I'm interested in identifying latent constructs (perhaps call it "very abstractive summarization"): topic models, ideal points models, NLG for annotation. In terms of evaluation, I like to think about validity: are we really measuring what we want to measure? Topically, I'm drawn to work on bias & fairness and political science; more recently, I've started work on constructs in mental health, specifically those relating to suicidality.
Last summer I was an intern in the FATE group at Microsoft Research. In the past I have interned with AllenNLP at AI2. Previously, I completed my master's in computational statistics and machine learning at University College London, where my thesis advisors were Sebastian Riedel and Jeff Mitchell at the UCL NLP group.
After undergrad, I was a Research Analyst at The Brattle Group in Cambridge, Massachusetts, where I built econometric models, developed a document retrieval platform, and did additional work that could be classified as data science. In a key project, I helped conduct research on New York City public housing for the U.S. Department of Justice; these efforts eventually led to a $2.2 billion settlement to improve conditions.
You can reach me at hoyle [at] umd [dot] edu. I use masculine pronouns.