I am a MIDAS Fellow at the University of Michigan, where I work with the LIT Lab to develop NLP systems that can adapt to different social situations and provide better feedback to writers.

As of Fall 2021 I am on the job market! I am interested in positions in government, non-profit, and industry labs that have a focus on technology for public good. You can read my full research statement here.

My current research focuses on (1) social ramifications of writing interventions and (2) assessing social bias in text. For (1), I am currently interested in audience-oriented systems that can preempt possible information gaps among the readers of a particular piece of writing, e.g. missing information in advice-seeking posts online. More broadly, I’m investigating the role of automated writing interventions in helping writers understand their readers, and themselves, better. For (2), I am working on several projects related to understanding bias in NLP systems, such as negative stereotypes about people of different races.

In 2020 I earned my PhD from the Interactive School of Computing (in the Human-Centered Computing program) at the Georgia Institute of the Technology. During my PhD, my research explored how sociolinguistic variation reflects communication goals in online discussions, including: (1) how people choose their language to address a partly-known audience; (2) how people adopt new words online; and (3) how social attitudes can explain language choices among multilingual people. You can read the full thesis here.

You can reach me at ianbstew at umich dot edu. In my free time, you’ll find me making music and baking cookies.