I focus on computational analysis, modeling, and prediction of complex phenomena, namely human behavior exhibited both off-line and on-line. I am interested in developing scalable machine learning techniques that help us understand and predict emergent global processes, such as disease epidemics, from day-to-day interactions of individuals. I work with Professor Henry Kautz in the Computer Science department at the University of Rochester.
We develop systems that reason about people's activities, health, plans, intentions, and strategies that occur in their everyday lives, on-line interactions, as well as in the games they play. Our models leverage a wide variety of raw data (e.g., location, text, video) and large datasets mined from online social media. The key applications of our research lie in areas where computers need to understand people—particularly in augmented cognition, context-aware reasoning, computational epidemiology, and human-computer interaction.
Along with my studies, I have been doing research & development work at eBay Research Labs, Google, and Microsoft Research.
Take a look at our mobile health web app GermTracker.
|
Predicting Spread of Disease from Social Media |
|
Given that three of your friends have flu-like symptoms, and that you have recently met eight people, possibly strangers, who complained about having runny noses and headaches, what is the probability that you will soon become ill as well? Our models enable you to see the spread of infectious diseases, such as flu, throughout a real-life population observed through online social media. We apply machine learning and natural language understanding techniques to determine the health state of Twitter users at any given time. Since a large fraction of tweets is geo-tagged, we can plot them on a map, and observe how sick and healthy people interact. Our model then predicts if and when an individual will fall ill with high accuracy, thereby improving our understanding of the emergence of global epidemics from people's day-to-day interactions. This video interview provides a quick overview of our work in the health space: The following video shows a heatmap visualization of the prevalence of flu in New York City, as observed through public Twitter data. The more red an area is, the more people are afflicted by flu at that location. We show emergent aggregate patterns in real-time, with second-by-second resolution. By contrast, previous state-of-the-art methods (including Google Flu Trends and government data) entail time lags from days to weeks. You can explore health patterns with our web application at Fount.in. The fine-grained epidemiological models we show here are just one instance of the general class of problems that our system solves. Other domains include understanding public sentiment, the diffusion of information throughout a population, and predicting customer behavior. By augmenting existing datasets with real-time insights and cues from social media, we are able to connect the dots, visualize patterns, and refine models based on user feedback. |
|
|
Learning about Human Behavior from Social Media |
|
|
|
Location-Based Modeling of Complex Multi-Agent Activities |
|
|
|
|
|
Adam Sadilek, John Krumm, and Eric Horvitz Crowdphysics: Planned and Opportunistic Crowdsourcing for Physical Tasks Seventh AAAI International Conference on Weblogs and Social Media (ICWSM), 2013 |
|
|
Adam Sadilek, Henry Kautz, and
Jeffrey Bigham Modeling The Interplay of People’s Location, Interactions, and Social Ties Twenty-Third International Conference on Artificial Intelligence (IJCAI), 2013 |
|
|
Sean Brennan, Adam Sadilek, and Henry Kautz Towards Understanding Global Spread of Disease from Everyday Interpersonal Interactions Twenty-Third International Conference on Artificial Intelligence (IJCAI), 2013 |
|
|
Adam Sadilek and Henry Kautz Modeling the Impact of Lifestyle on Health at Scale Sixth ACM International Conference on Web Search and Data Mining (WSDM), 2013 |
|
![]() |
|
Walter Lasecki,
Christopher Miller, Adam Sadilek,
Andrew Abumoussa,
Donato Borrello,
Raja Kushalnagar,
and
Jeffrey Bigham Real-Time Captioning by Groups of Non-Experts in 25th ACM Symposium on User Interface Software and Technology (UIST), 2012 News Coverage: New Scientist, Gizmodo |
Best Paper
Nomination |
|
|
|
Adam Sadilek Modeling Human Behavior at a Large Scale Ph.D. Thesis, University of Rochester, 2012 |
|
|
|
Adam Sadilek and John Krumm Far Out: Predicting Long-Term Human Mobility Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012 News Coverage: IEEE Spectrum |
|
|
|
Adam Sadilek, Henry Kautz, and Vincent Silenzio Predicting Disease Transmission from Geo-Tagged Micro-Blog Data Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012 News Coverage: Gizmodo, New Scientist, NPR's "Wait Wait ... Don't Tell Me!", Information Week, Discovery News, Medical Daily, San Francisco Chronicle, Daily Mail, Business Insider Democrat and Chronicle |
Outstanding Paper
Honorable Mention |
|
|
|
Adam Sadilek, Henry Kautz, and Vincent Silenzio Modeling Spread of Disease from Social Interactions Sixth AAAI International Conference on Weblogs and Social Media (ICWSM), 2012 Video of the talk News Coverage: CNN, NY Post, The Guardian |
Best Paper
Nomination |
|
|
|
Adam Sadilek and Henry Kautz Modeling Success, Failure, and Intent of Multi-Agent Activities Under Severe Noise in Mobile Context Awareness, Springer, 2012 |
|
|
|
Adam Sadilek, Henry Kautz, and Jeffrey Bigham Finding Your Friends and Following Them to Where You Are Fifth ACM International Conference on Web Search and Data Mining (WSDM), 2012 Presentation slides, Poster, Video of the talk News Coverage: New Scientist, Gizmodo, Science Daily, O'Reilly, UPI, NDTV, Yahoo! News, ACM TechNews, TG Daily, Science Codex |
Best Paper Award
![]() |
|
![]() |
|
Adam Sadilek and Henry Kautz Location-Based Reasoning about Complex Multi-Agent Behavior Journal of Artificial Intelligence Research, 2012 |
|
|
|
Adam Sadilek and Henry Kautz Modeling and Reasoning about Success, Failure, and Intent of Multi-Agent Activities Mobile Context-Awareness Workshop, Twelfth ACM International Conference on Ubiquitous Computing, 2010 |
|
|
|
Adam Sadilek and Henry Kautz Recognizing Multi-Agent Activities from GPS Data Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010 |
|
|