JANUARY 29, 2020
Elad Yom-Tov, PhD
About the Presentation: The majority of Internet users turn to the web for information when they have a medical concern. The data they generate in the process can help understand conditions which are difficult to monitor using more traditional medical data sources. However, accessing these data in order to learn about the conditions of interest and conducting interventions in an online environment is often challenging.
In my talk I will present our work which aims to learn about issues of mental health using novel collection of online data and innovative intervention methods. First, I will discuss studies where crowdsourced users contributed their browsing histories, which we used to identify eating disorders, depression, and barriers to treatment. The models constructed using these data can now be applied to the browsing data of users across the web to predict the prevalence of mental conditions at a population level.
In the second part of my talk I will show how advertising in search engines can be used to intervene in online behavior. I will present our work demonstrating the use of online ads to estimate the effect of a specific pro-anorexia website on future behaviors of users and to nudge users to less harmful behaviors and to earlier diagnosis
About the Presenter: Elad Yom-Tov is a Principal Researcher at Microsoft Research. Before joining Microsoft he was with Yahoo Research, IBM Research, and Rafael. His primary research interests are in applying large-scale Machine Learning and Information Retrieval methods to medicine. Dr. Yom-Tov studied at Tel-Aviv University and the Technion, Israel. He has published four books, over 100 papers (of which 3 were awarded prizes), and was awarded more than 20 patents. His latest book is “Crowdsourced Health: How What You Do on the Internet Will Improve Medicine” (MIT Press, 2016).