Leveraging Signals from the Crowd in Studies of Health and Well-Being
I will describe how anonymized behavioral data drawn from online services can be harnessed to perform large-scale sensing about health and well-being. I will highlight opportunities for garnering insights and performing inferences and predictions about health via analyses of signals expressed in social media, web searching and browsing, and interpersonal communications. I will frame directions by presenting studies that consider different types of data, and show how behavioral signals can complement more traditional studies performed in medicine, public health, and psychology. Finally, I will reflect about challenges and directions on privacy and ethics that may come to the fore with efforts to leverage behavioral data in studies of health and well-being.
Eric Horvitz is a distinguished scientist at Microsoft Research where he serves as the managing director of Microsoft Research at Redmond. His interests span theoretical and practical challenges with machine perception, learning, and inference. He has been elected a fellow of AAAI, ACM, AAAS, the American Academy of Arts and Sciences, and the National Academy of Engineering, and has been inducted into the CHI Academy. He has served as president of the AAAI, chair of the AAAS Section on Information, Computing, and Communications, and on the NSF CISE Advisory Committee. He received PhD and MD degrees at Stanford University. Information on publications, collaborations, and activities can be found at http://research.microsoft.com/~horvitz.
7:15am to 8:30am