Glen Coppersmith and Mark Dredze join #SPSM Sunday 3/8/15, 9pCST to discuss how social media can be used to track various indices of mental health, such as prevalence of depression, bipolar disorder, or PTSD. Follow the hashtag, and also join us LIVE here:
The Tweets for this chat will be archived on Storify.
“Twitter is, apparently, the quiet therapist to whom we reveal much more that we realize. As such, it could be a valuable public-health tool. More work needs to be done in considering how such information could be used while still preserving privacy, but it’s an inquiry worth pursuing,” according to a Boston Globe editorial.
Increasingly, a person’s social media feed can provide additional diagnostic information about their mental health, predicting (albeit with some error) the likelihood that someone has or will develop depression. Could this same kind of technology be used to predict a person’s risk of suicide, or need for support/assistance? If it could, what would that mean for people at risk, or for the system that serves them?
“Researchers are beginning to link to mental health certain types of data that people can’t track or identify in themselves. Just as an EKG is a more effective tool to diagnose cardiac disease than asking a patient how his or her heart feels, these new data sources could radically change our ability to track mental health,” according to Stav Ziv in his Newsweek article, referring to the Johns Hopkins project our guest experts will be discussing with #SPSM.
Chat with our panel of experts about this innovative use of social media, and share your thoughts/opinions, 3/8/15, 9pCST.
Glen Coppersmith is an independent consultant addressing a range of data science challenges — currently working with the leadership of DARPA’s XData program, founder of Qntfy, affiliate of the Data Guild, and a part-time research scientist at the Human Language Technology Center of Excellence at Johns Hopkins University. He joined the HLTCOE in 2008 as its first full-time researcher, staying on full time there until the end of 2014. He also maintains assistant research scientist positions within two departments at Johns Hopkins: Applied Math and Statistics and Electrical and Computer Engineering. His graduate work was at Northeastern University, using computational techniques to explore psychology problems (in linguistics, neuroscience, and clinical psychology). His work spans a number of disciplines: computer science, graph theory, statistics, natural language processing, machine learning, and psychology. He tends to shy away from curated and cared-for datasets, instead preferring the wild-west of real world data. He suspects this is in part due to his keen appreciation for the outdoors — an avid rock climber, kayaker, photographer, hiker, and SCUBA diver.
Mark Dredze is an Assistant Research Professor in Computer Science at Johns Hopkins University and a research scientist at the Human Language Technology Center of Excellence. He is also affiliated with the Center for Language and Speech Processing and the Center for Population Health Information Technology. His research in natural language processing and machine learning has focused on graphical models, semi-supervised learning, information extraction, large-scale learning, and speech processing. His recent work includes health information applications, including information extraction from social media, biomedical and clinical texts. He obtained his PhD from the
University of Pennsylvania in 2009.