Home page

This project aims to define the concept of digital self-harm for the HCI community and to understand the diversity and severity of online content associated with self harm behaviors associated with mental health conditions such as eating disorders.

Our goal is to improve the speech perception of individuals with mild cognitive impairment in a therapeutic facility through the design of the sound environment. Discerning speech is complex task that is an interplay between the receiver's cognitive and physical abilities and the quality of the sound signal. By understanding the unique difficulties that individuals with MCI face in discerning speech, we aim to design technologies embedded in the physical environment to improve the quality of the speech signal in the space.

Since its earliest days, flaming, trolling, harassment and abuse have plagued the Internet. Our aim is to computationally model abusive online behavior to build tools that help counter it, with the goal of making the Internet a more welcoming place. In particular, we look at a novel approach to identify online verbal abuse using cross-community linguistic similarities between posts on different communities. This work will enable a transformative new class of automated and semi-automated applications that depend on computationally generated abuse predictions.