When social networks such as Foursquare started to offer people the chance to plot where they were at a particular point in time, it was initially feared that it would offer criminals a great opportunity to scout out potential burglary hot spots.
I’m not sure that those fears have really materialized, but what has happened is the huge amount of data we publish to social networks has been used to plot everything from the spread of flu to the prospects of box office success.
A recent paper has explored how all of this social data could be used to guide urban planning. Of particular focus for the authors was land use at night, with issues such as noise and dirt particularly problematic for residents and planners alike. The belief is that geotagged tweets can be used to improve matters.
“Geolocalized tweets can be a very useful source of information for planning, since it is an activity carried out by a large number of people who provide information on where they are at a specific time and what they are doing,” the authors say.
An increasing number of tweets come with geolocation information attached to them, which if suitably shared could be put to use in improving urban planning.
“You can capture information on urban land use more efficiently and for a much larger number of people than with questionnaires. Moreover, this type of consultation, traditionally used until now in planning activities, are very costly and can cause problems due to the lack of accuracy of the answers,” they continue.
Their method determines land use automatically by pooling together tweets from the same geographical region and analyzing the content published.
The researchers have already explored the land use in areas such as London, Madrid and Manhattan. In Madrid for instance, they identified four core land uses: residential, commercial, daytime leisure and nightlife areas. In London these four were also identified, but an industrial trend was also spotted.
“One of the most interesting contributions of the study is the identification of nightlife areas, since this type of land use in not often specified in urban planning, despite the problems of noise, security and need for cleaning that this creates. Therefore, this information is very relevant,” they suggest.
So for instance, night time tweets in Madrid typically occurred on weekends, but on weekdays in Manhattan.Of course, this isn’t the first project to attempt this kind of analysis. A little while back a project called nEmesis was created to try and use our tweets to create a map of food poisoning in New York.
You might think, or hope at least, that this would be a relatively small number, but over a four month period they found 480 such mentions in New York City alone from a total of 23,000 restaurant visitors. What’s more, the data collected correlated well with public health data on those diners.
“The Twitter reports are not an exact indicator – any individual case could well be due to factors unrelated to the restaurant meal – but in aggregate the numbers are revealing,”said Henry Kautz, chair of the computer science department at the University of Rochester and co-author of the paper. In other words, a“seemingly random collection of online rants becomes an actionable alert,”according to Kautz, which can help detect cases of foodborne illness in a timely manner.
It’s likely that there will be an increasing fertilization of public data with the kind we share willingly on social media. Hopefully it will herald a smarter wave of planning and decision making.