To start, scientists collected tweets containing words relating to alcohol, like “hammered,” “drunk,” and “party,” that were posted by users in New York City or Monroe County over the course of one year. They then determined whether the tweeter was the one drinking, and whether the tweet was posted while drinking.
After collecting tweets with home-related keywords, like "sofa" and "bath," they used Amazon's Mechanical Turk crowdsourcing service to find more details on whether the tweets were posted from the user’s residence, Newser explained.
This data helped them develop an algorithm to identify "patterns of alcohol-related behavior in unprecedented detail," including a link between the number of liquor stores and bars in a specific area and the number of tweets in that same area relating to alcohol consumption.
“We can explore the social network of drinkers to find out how social interactions and peer pressure in social media influence the tendency to reference drinking,” the researchers explained.
“One possible explanation is that a crowded city such as NYC with highly dense alcohol outlets and many people socializing is likely to have a higher rate of drinking,” the study explained.
The findings have opened up an interesting drinking debate about correlation and causation, though the data does not prove either side.
“Does a high density of alcohol outlets cause people to drink more? Or do drinkers flock to areas with a high density of alcohol outlets?” Technology Review asked.
