Social Media and Health



Henry Kautz, Jiebo Luo, Eric Portman, Adam Sadilek (Google), Vincent Silzenzio (URMC), Ann Marie White(URMC), Chris Homan (RIT)

Graduate Students: Nabil Hossain, Brian Dickinson, Anis Zaman, Solomon Abiola


Nabil Hossain, Tianran Hu, Roghayeh Feizi, Ann Marie White, Jiebo Luo and Henry Kautz. Precise Localization of Homes and Activities: Detecting Drinking-While-Tweeting Patterns in Communities. 10th International AAAI Conference on Web and Social Media (ICWSM-16), Cologne, Germany.

Adam Sadilek, Henry Kautz, Lauren DiPrete, Brian Labus, Eric Portman, Jack Teitel, and Vincent Silenzio. Deploying nEmesis: Preventing Foodborne Illness by Data Mining Social Media. 28th Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-16), Phoenix, AZ, 2016.

Dawei Zhou, Jiebo Luo, Vincent Silenzio, Yun Zhou, Glenn Currier, and Henry Kautz. Tackling Mental Health by Integrating Unobtrusive Multimodal Sensing. 29th Conference on Artificial Intelligence (AAAI-2015), Austin, TX, 2015.

Danning Zheng, Tianran Hu, Quanzeng You, Henry Kautz, and Jiebo Luo. Inferring Home Location from User's Photo Collections based on Visual Content and Mobility Patterns. ACM Multimedia Conference, Workshop on Geotagging in Multimedia (GeoMM), November 2014.

Adam Sadilek, Christopher Homan, Walter S. Lasecki, Vincent Silenzio, Henry Kautz (2014). Modeling Fine-Grained Dynamics of Mood at ScaleWSDM 2014 Workshop on Diffusion Networks and Cascade Analytics, New York City, Feb 24-28, 2014.

Adam Sadilek, Sean Brennan, Henry Kautz, and Vincent Silenzion (2013). nEmesis: Which Restaurants Should You Avoid Today? First AAAI Conference on Human Computation and Crowdsourcing (HCOMP-2013), Palm Springs, CA, 2013.

Henry Kautz (2013). There's a Fly in My Tweets. New York Times, June 23, 2013, page SR12.

Sean Brennan, Adam Sadilek, and Henry Kautz (2013). Towards Understanding Global Spread of Disease from Everyday Interpersonal Interactions23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, China, 2013.

Adam Sadilek and Henry Kautz (2013). Modeling the Impact of Lifestyle on Health at Scale. Sixth ACM International Conference on Web Search and Data Mining (WSDM 2013). Rome, Italy, 2013.

Adam Sadilek, Henry Kautz, and Vincent Silenzio (2012). Predicting Disease Transmission from Geo-Tagged Micro-Blog Data26th Conference on Artificial Intelligence (AAAI-12), Toronto, Canada, 2012.

Adam Sadilek, Henry Kautz, and Vincent Silenzio (2012) Modeling Spread of Disease from Social InteractionsSixth AAAI International Conference on Weblogs and Social Media (ICWSM-2012), Dublin, Ireland, 2012.


Machine-Learning Algorithm Identifies Tweets Sent Under the Influence of Alcohol

MIT Technology Review - ‎Mar 16, 2016‎
The team began by collecting geotagged tweets sent during the year up to July 2014 from New York City and from Monroe County on the northern border of the state, which includes the city of Rochester. From this set, they filter all the tweets that ...

This algorithm can tell if you're drunk tweeting

CBS News - ‎17 hours ago‎
If you were tweeting and drinking between July 2013 to 2014, your tweets might have been used as part of an experiment by computer science students at the University of Rochester. (Perhaps you don't remember, which might be for the best.) Nabil Hossain ...

How can machine learning algorithms find drunk Twitter users?

Christian Science Monitor - ‎18 hours ago‎
The Rochester analysts came up with a series of three questions they used to determine if a tweetoriginated from a drinking user: Does the tweet mention alcoholic beverages – did they use words such as “drunk,” “beer,” or “alcohol?” Is the tweet about ...

Computers can tell when you've been drunk tweeting

Engadget - ‎Mar 16, 2016‎
In case the rambling string of misspelled words and incoherent thoughts weren't dead giveaways, scientists have developed a method of machine learning to sniff out drunk tweets. Researchers from the University of Rochester collected 11,000 geotagged ...

Machine learning algorithm can identify drunken tweeting

Ars Technica - ‎Mar 17, 2016‎
Researchers have now trained an algorithm to spot alcohol-related tweets, and even to guess if the tweeter was drinking at the time of posting. Nabil Hossain at the University of Rochester, upstate New York, decided to combine Twitter and machine ...

A Computer Can Spot Your Drunk Tweets From a Mile Away

Gizmodo - ‎Mar 16, 2016‎
In a study out this week, a group of computer scientists from the University of Rochester analyzed over 11,000 geotagged drunk tweets posted in New York City and Monroe County in Upstate New York from January to July of 2014. How did they isolate the ...

This Algorithm Tells If You're Drunk Or Not By What You Tweet

Tech Times - ‎21 hours ago‎
Headed by lead author and graduate research assistant Nabil Hossain, scientists at the University of Rochester developed the algorithm to differentiate drunk tweets from sober ones, all in the name of, among other things, averting alcohol-related ...

A new algorithm can tell when you're tweeting while drunk, and may help save lives

Digital Trends - ‎16 hours ago‎
... Twitter contribution was made in a drunken stupor. In truly monumental research, Nabil Hossain at the University of Rochester took Twitter and machine learning, and smashed them together to determine drinking habits across specific geographic ...

This Algorithm Knows If You're Drunk Tweeting

PC Magazine - ‎21 hours ago‎
Using social media while intoxicated may be hazardous to your personal life. But there may be an upside. A team of researchers at the University of Rochester have trained a computer to spot alcohol-related tweets and use that data to monitor localized ...

Computer Algorithm Can Spot a Drunken Tweeter

Discover Magazine (blog) - ‎16 hours ago‎
Drunk tweets, long considered an unfortunate, yet ubiquitous, byproduct of the social media age, have finally been put to good use. With the help of a machine-learning algorithm, researchers from the University of Rochester cross-referenced tweets ...

Researchers tracked drunken New Yorkers' tweets -- for science

The Next Web - ‎Mar 16, 2016‎
A study published this week by a group of computer scientists from the University of Rochesteranalyzed over 11,000 geotagged drunk tweets from January to July of 2014 — this means the image you tweeted in an American flag mankini on Independence ...

New algorithm identifies when someone tweets being drunk

Pulse Headlines - ‎15 hours ago‎
Rochester, New York – A group of researchers at the University of Rochester introduced a machine-learning algorithm they developed. This machine can spot tweets posted under the influence of alcohol. This technology, they said, could be used to better ...

These Researchers Know When and Where You're Drunk Tweeting

Entrepreneur - ‎22 hours ago‎
And now for a brief St. Patrick's Day PSA: If you're planning any celebratory outings today, drink responsibly and do your level best to not drunk tweet or text. It may seem like a good idea at the time, but the Internet is forever. Thanks to context ...

Algorithm Can Spot If You're Tweeting While Drinking

Newser - ‎45 minutes ago‎
(Newser) – Think last night's drunk tweets were pretty coherent? You won't fool University ofRochester researchers, who have developed a machine-learning algorithm that can tell when a tweeter is drinking. To do so, they started with humans ...

Drunk Tweeting? This Algorithm Will Find You Out

ValueWalk - ‎21 hours ago‎
Researchers have now come up with an algorithm that can detect drunk tweeting and guess whether the tweeter was drunk at the time of the post. Nabil Hossain at the University ofRochester, upstate New York, used Twitter and machine learning in order to ...

Drunk on Twitter: Scientists develop algorithm to detect alcohol inducedtweets

International Business Times UK - ‎Mar 17, 2016‎
While, some may have participated or bore the brunt of drunken tweets, many have denied being under the influence. But now, scientists at the University of Rochester have developed an algorithm that identifies tweets that were posted when a user was ...

An Algorithm Can Tell If You're Drunk Tweeting

Gizmodo India - ‎Mar 16, 2016‎
If you were at a bar with your phone in New York City during 2014, your whiskey-laced illegibletweets may have been used for important scientific research. In a study out this week, a group of computer scientists from the University of Rochester ...

Tweet Machine Knows When You're Drunk

Regal Tribune - ‎Mar 17, 2016‎
... stuff on Twitter or Facebook. Apparently, the machine is so far off, that it can predict with an 80 percent accuracy you're location and how drunk you are based on your text. Leaving the joke aside, a team of scientists from the University of ...

Researchers create algorithm to detect drunk tweeting

TechSpot - ‎15 hours ago‎
It's this type of behavior that inspired researchers at the University of Rochester in New York do a study on the matter. Specifically, they set out to create an algorithm that could detect tweets that were likely published by someone under the ...

Machine-Learning Algorithm Can Determine If You're Drunk Tweeting

Headlines & Global News - ‎Mar 16, 2016‎
It's safe to assume that most people agree that alcohol and tweeting is probably not a good combination, but researchers at the University of Rochester have examined this practice even further and created a machine-learning algorithm that can spot ...

Machine Learning Can Tell Which Tweets Are Sent While Drunk

Ubergizmo - ‎Mar 17, 2016‎
Sure, sometimes it's a dead giveaway with typos and exaggerated punctuation, but sometimes it's not, which is why Nabil Hossain and his friends at the University of Rochester decided to train a machine to identify tweets that were sent out while the ...

Twitter Knows When You've Had One Too Many

Gadget Gestures - ‎Mar 17, 2016‎
While it's not Twitter as an entity that can tell and instead it's an algorithm that Twitter owns which knows when you drink, the point is – it can guess how drunk you are and where you have been drinking. Typing is hard, especially when ... The ...

Scientists Track Sloshed Tweeters in Real Time

TECHNEWS WORLD - ‎Mar 21, 2016‎
Applied machine learning techniques can identify tweeters' behaviors in real time and locate them to within 100 meters, according to a paper Rochester University computer scientists published earlier this month...