BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Blending Social Media and Machine Learning to Impro
 ve Mental Health: Harnessing the Potentials and Avoiding the Pitfalls
DTSTART:20191216T161500
DTEND:20191216T171500
DTSTAMP:20260610T113908Z
UID:1afb4b075948e617d441fbb7cc85fb034996109a707dfdfb47633ac4
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Munmun De Choudhury - Georgia Tech\nVideo of her talk\n\nA
 bstract:\nSocial media data is being increasingly used to computationally 
 learn about and infer the mental health states of individuals and populati
 ons. Despite being touted as a powerful means to shape interventions and i
 mpact mental health recovery\, little do we understand about the theoretic
 al\, domain\, and psychometric validity of this novel information source\,
  or its underlying biases\, when appropriated to augment conventionally ga
 thered data\, such as clinical assessments and verbal self-reports. This t
 alk presents a critical analytic perspective on the pitfalls of social med
 ia signals of mental health\, especially when they are derived from “pro
 xy” diagnostic indicators\, often removed from the real-world context in
  which they are likely to be used. Then\, to overcome these pitfalls\, thi
 s talk presents results from two case studies\, where computational algori
 thms to glean mental health insights from social media were developed in a
  context-centered way\, in collaboration with domain experts and stakehold
 ers. The first of these case studies\, a collaboration with Northwell Heal
 th\, focuses on the individual-perspective\, and reveals the ability and i
 mplications of using social media data of consented schizophrenia patients
  to forecast relapse and support clinical decision-making. Scaling up to p
 opulations\, in collaboration with the Centers for Disease Control and Pre
 vention and towards influencing public health policy\, the second case stu
 dy seeks to forecast nationwide rates of suicide fatalities using social m
 edia signals\, in conjunction with health services data. The talk conclude
 s with discussions of the path forward\, emphasizing the need for a collab
 orative\, multi-disciplinary research agenda\, that incorporates methodolo
 gical rigor\, ethics\, and accountability.\n\nBio:\nMunmun De Choudhury is
  an assistant professor of Interactive Computing at Georgia Tech where she
  directs the Social Dynamics and Wellbeing Lab. Dr. De Choudhury is best k
 nown for laying the foundation of a new line of research focusing on asses
 sing and improving personal and societal mental health from online social 
 interactions. In her relatively short academic career\, Dr. De Choudhury h
 as been recognized with the Complex Systems Society – Junior Scientific 
 Award in 2019\, the James D. Lester III Family Award in 2018\, the James E
 denfield Faculty Fellowship in 2015\, multiple best paper and honorable me
 ntion awards from the ACM and AAAI\, and extensive coverage in popular pre
 ss like the New York Times\, the NPR\, and the BBC. Earlier\, Dr. De Choud
 hury was a faculty associate with the Berkman Klein Center for Internet an
 d Society at Harvard\, a postdoc at Microsoft Research\, and obtained her 
 PhD in Computer Science from Arizona State University.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR