Data Science for Suicide Prevention
Data Science for Suicide Prevention

Abstract: 

In late 2019, a group of researchers discovered that not only does media coverage impact national suicide rates, but that coverage which isn’t aligned to the guidelines established in 2001 for reporting on suicide risks increasing national suicide rates by up to 13% (https://www.bmj.com/content/368/bmj.m575). In response, a team of nonprofit and for-profit organizations came together (including the researcher who created the original reporting guidelines, which have been endorsed by the WHO and CDC) to develop a ML-based UI for journalists (similar to Grammarly) to increase the adoption rate of these standards. In this session, we (if approved, a suicide prevention researcher will co-present with me) will demonstrate how this ML will save hundreds of thousands of lives as well as the best practices we’re using to maximize its technical efficacy and social impact. Note that this session will include a live demo.

Bio: 

Annie is a leader in data science with over a decade of industry experience spanning corporate research and startups. Currently, she is the head of the Cisco Data Science Lab in Vancouver. Coming from a research background with a PhD in Computer Science from McGill, Annie is a former Research Scientist at IBM T. J. Watson Research Center in New York and a two-time winner of an ACM Distinguished Paper Award (both in applying data science to software engineering) with five patents (granted and applied). Annie is active in the data science community as a Meetup organizer (Data Science for Social Good), speaker, and mentor.