How social media can influence the spread of a disease? A new study, conducted by Marcel Salathe, a scientist at Penn State, showed how social birds react and express their thoughts on a new vaccine program. He reasoned that there were some people on social media who looked to a vaccination program positively while there were some who perceived it negatively. And interestingly, all of them influence others in their network in one way or the other.
And he chose Twitter to do the research. But why Twitter?
Salathe reasoned Twitter is a more open channel than Facebook, where everyone can follow and track tweets, coming from anyone. He also told that Twitter keeps a database, which is excellent to learn public’s sentiments. And finally, tweets are short and crux to the point. This is easier to track updates, when hundreds of them are coming in every minute.
Salathe started his study by collecting 4, 77, 768 tweets that contained vaccine related keywords, namely H1N1 vaccine. The study continued from August 2009 to January 2010. After amassing them, he asked his juniors to categorize them according to their inner sentiments (positive, negative, and neutral). Besides, since twitter provides location-related data, the researchers were able to categorize the tweets, depending on the geo-location zones. Based on the initial paperwork to catalog the tweets, Shashank Khandelwal, the co-author of the paper and programmer in the Department of Biology in Penn State created an algorithm to further monitor and track the tweets.
After the entire data passed thought the computer algorithm, only 3, 18, 379 tweets were left as countable for the study.
Now you must be wondering the purpose of the study. According to Salathe, this study can be utilized in public health initiatives. Authorities can design targeted campaigns, depending on the region and their perception towards a vaccination program. The data would be needful to predict how many doses will be necessitated in a particular area. Additionally, Salathe has also built the clusters of like-minded people on the social networking site.
He said, «If anti-vaccination communities cluster in real, geographical space, as well, then this is likely to lead to under-vaccinated communities that are at great risk of local outbreaks.»
After H1N1, he plans to leverage his study for other diseases like heart ailments, obesity, hypertension and other non-infectious diseases. With that, he predicted that people will start worrying about behavior and lifestyle related diseases more than infectious diseases.
He reasoned, «Behavior-influenced diseases always have existed, but, until recently, they were masked: People died of infectious diseases relatively early in their life cycles. So behavior-influenced diseases weren’t really on anyone’s radar. Now that heart disease — a malady caused, at least in part, by lifestyle — is moving to the top of the list of killers, it might be wise to focus on how social media influences behaviors such as poor diet and infrequent exercise. »
The detailed study will be published in the journal PLoS Computational Biology.