Researchers Using GPUs to Monitor Underage Drinking on Instagram

Instagram could offer a novel way of monitoring the drinking habits of teenagers.
Using photos and text from Instagram, a team of researchers from the University of Rochester has shown that this data can not only expose patterns of underage drinking more cheaply and faster than conventional surveys, but also find new patterns, such as what alcohol brands or types are favored by different demographic groups. The researchers say they hope exposing these patterns could help develop effective intervention.

Instagram does not offer a way of selecting users by age, but the research team was able to select users that fit the profile they were looking for by applying computer vision techniques using TITAN GPUs and the deep learning framework Caffe. Jiebo Luo, professor of computer science at the University of Rochester, and his team have been pioneering techniques that teach computers to extract information from images on the Internet, something that is much more complex than just extracting information from text. They were able to use computers to analyze the profile faces of Instagram users to get sufficiently accurate guesses for their age, gender, and race.
The paper mentions several features of Instagram make it a good choice for monitoring adolescent alcohol use. Today there are more than 300 million Instagram users among which around 41% are aged between 16 and 24. Instagram has become the most important social platform for teenagers, who start to migrate from their former accounts of Facebook and Twitter, especially those with upper-income and coming from urban areas. Also, teenagers find in Instagram a safe place to post potentially incriminating information about underage alcohol use, without fear that it will be seen their parents or teachers.
Read the entire research paper >>