Somewhere in the flood of tweets, posts, tags, pokes, likes and shares, a group of statisticians saw opportunity.
At the 2015 Joint Statistical Meetings, researchers presented two examples of how social media could be used for public health purposes. The first example used social media to track foodborne illness. The second used social media to enhance disaster response.
Biostatistician Dr. Elaine Nsoesie, a pediatrics research fellow at Boston Children's Hospital, presented her study on foodborne illness outbreaks and social media.
Traditional activities by public health departments capture a small portion of foodborne illness cases in the US. Dr. Nsoesie and colleagues compared online restaurant reviews on social media with traditional surveillance.
They found foods like lettuce implicated on the popular review site called Yelp. Reports from users who complained on Yelp about illnesses from foods had similar patterns to outbreak reports from the Centers for Disease Control and Prevention.
"Online reviews of food-service businesses offer a unique resource for disease surveillance. Similar to notification or complaint systems, reports of foodborne illness on review sites could serve as early indicators of foodborne disease outbreaks and spur investigation by local health authorities. Information gleaned from such novel data streams could aid traditional surveillance systems in near real-time monitoring of foodborne related illnesses," Dr. Nsoesie said in a press release.
The second presentation analyzed social media traffic when Typhoon Haiyan struck the Philippines in November 2013.
Statistician Dr. Michiko Wolcott and colleagues collaborated with disaster-preparedness organization Humanity Road. The collaboration resulted in a resource booklet: "A Guide to Social Media Emergency Management Analytics."
The purpose of the project was to analyze the use of Twitter for collecting relevant data during disasters.
"Social media can play a critical role in the dissemination of the information, as well as collection of relevant data during natural disasters. The idea of leveraging social media data such as Twitter is intuitively attractive, given their natural ties to mobile devices with obvious disaster response implications," Dr. Wolcott said in a press release.
Using social media presents some unique situations, Dr. Wolcott and team noted. Among these are filtering data — by types of posts, types of posters and keywords.
According to the guidebook these researchers produced, locating posts geographically is also important. Posters in a certain area might report rising flood waters, which could trigger rescue responses, Dr. Wolcott and team noted.
Both research projects were presented Aug. 12. Research presented at conferences may not have been peer-reviewed. Funding and conflict of interest disclosures were not available at the time of publication.
