Instagram offers unfiltered look at teen drinking

"This new method could be a useful complement to more traditional methods of measuring youth drinking," says Elizabeth Handley. (Credit: bo$$man/Flickr, Abitha Pallett/Flickr, Mark Miller/Flickr)

Instagram offers a new way to monitor the drinking habits of teenagers, say researchers.

Using photos and text from Instagram, a team of researchers shows 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 favored alcohol brands or types among different demographic groups.

As Jiebo Luo, professor of computer science at the University of Rochester, and his colleagues describe in a new paper, underage drinkers “are willing to share their alcohol consumption experience” on social media.

Do not disturb

Studying the social media behavior of this group allows the researchers to observe it passively in an “undisturbed state.”

Traditional methods of monitoring underage alcohol consumption have disadvantages. For example, teenagers might not be honest when they respond to an administered survey about alcohol use, e.g., the “Monitoring the Future” survey by the federal government.

In addition, the teens who choose to respond to such a survey might not be a representative sample and the sample size might be too small to draw conclusions.

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.

[Drunk people, not hangovers, are popular on YouTube]

Luo 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.

Having selected a group of underage users to study, the researchers monitored drinking related activities via their Instagram photos by analyzing the social media tags associated with these photos using a constructed internet slang dictionary and also any alcohol brands the users follow.

Alcohol brands on Instagram

In their study, the researchers found that underage alcohol consumption, like with adults, happens more on weekends and holidays and at the end of the day. There also wasn’t a strong bias toward one gender for alcohol consumption – it matched the gender ratio of Instagram users.

The researchers did find that different alcohol brands are followed in varying degrees by teenagers, and that different genders follow different brands. The researchers highlight that this could point out brands that are attracting younger audiences in social media, information that could be useful to people working with underage drinkers.

[What #diabetes tells us about public health]

“There are several ways we can go about doing that,” says Luo. “We can keep government agencies or schools better informed and help them design interventions. We could also use social media to incorporate targeted intervention and to measure the effect of any intervention. And perhaps other things we haven’t thought about.”

Checking their work

The researchers acknowledge, however, that research like this could also be used by brands to target their products to those users most likely to follow them.

Luo explains that an important next step is to check the results of their approach with surveys, to ensure their methodology is robust before applying it to extract even more information from Instagram. They hope to collaborate with people working on addressing other youth problems, such as tobacco, drugs, teen pregnancy, stress, or depression.

“This new method could be a useful complement to more traditional methods of measuring youth drinking,” says Elizabeth Handley, clinical psychologist and research associate at the university’s Mount Hope Family Center. “It could provide important new insights into the contexts of youth drinking and be a valuable tool for evaluating the effectiveness of school or community-based preventive interventions.”

The team presents their work this week at the 2015 IEEE International Conference on Big Data in Santa Clara, California.

Source: University of Rochester