Abstract: Surveys show that the vast majority of Internet users seek information online when they have a medical concern. Behavioral data generated during these searches can thus serve to provide unprecedented insights into the health of large populations of users. However, mining these data poses several challenges, including making sense of large-scale unstructured information, unbiasing the sampled population, linking the findings to established medical research, and preserving the privacy of users. In this talk I will discuss both the promise and the challenge in using online behavioral information for medical research. I will exemplify with recent research on identifying adverse reactions to medical drugs, finding risk factors to disease, and validating the usefulness of public health campaigns.
Bio: Elad Yom-Tov is a Senior Researcher at Microsoft Research Israel. Before joining Microsoft he was with Yahoo Research, IBM Research, and Rafael. Dr. Yom-Tov studied at Tel-Aviv University and the Technion, Israel. He has published two books, over 80 papers (of which 3 were awarded prizes), and filed more than 30 patents (18 of which have been granted so far). His primary research interests are in large-scale Machine Learning, Information Retrieval, and Social Analysis. The results of his work have flown at four times the speed of sound, enabled people to communicate with computers using only their brain-waves, and analyzed the cellphone records of a significant portion of the worlds' population. He is a Senior Member of IEEE and held the title of Master Inventor while at IBM.
Abstract: By making new types of information easily accessible on an unprecedented scale and in real-time, social media has triggered an information revolution perhaps only comparable with the advent of the Web itself in the early 1990s. Still, the methods to retrieve, organize and organize social media content are in their infancy. I will discuss the trajectory of research we have done in this area since 2005, in particular as it relates to news and media, how it is inspired by the idea (and a set of algorithms) of AttentionRank, and how it led to the creation of Seen.co, a New York City startup created to make the world's stories "watchable".
Bio: Mor Naaman is an associate professor at Cornell Tech, and co-founder and Chief Scientist at Seen.co. Mor's research applies multidisciplinary methods to gain new insights about people and society from social media data, and to develop novel tools to make this data more accessible and usable in various settings. Previously, Mor worked as a research scientist at Yahoo! Research Berkeley, and received a Ph.D. in Computer Science from Stanford University. He is a recipient of a NSF Early Faculty CAREER Award, research awards from Google, Yahoo!, and Nokia, and three best paper awards. Find out more about Mor at http://mornaaman.com.