Twitter could be used to predict coronary heart disease, according to a new study from researchers at the University of Pennsylvania. By studying tweets announcing marriages and divorces, struggles and accomplishments, it may be possible to predict the psychological well-being of a community, and foretell cardiac disease.
Stress, smoking, and low incomes can all add to the risk of heart disease, and Twitter provides a wealth of information about these lifestyle factors. An overall psychological feeling of individual communities can be developed through the examination of tweets from a particular region. Researchers have long suspected that the prevailing psychological atmosphere of a community had a profound effect on heart disease risk. However, quantifying that local zeitgeist at a given time and location proved challenging. Twitter could provide a means of expressing that public feeling in health models.
Tweets expressing hope and optimism were found to be associated with lower risks of heart disease within the communities examined. Stress, fatigue, and anger correlated with higher rates of coronary heart disease.
"Psychological states have long been thought to have an effect on coronary heart disease. For example, hostility and depression have been linked with heart disease at the individual level through biological effects. But negative emotions can also trigger behavioral and social responses; you are also more likely to drink, eat poorly and be isolated from other people which can indirectly lead to heart disease," Margaret Kern of the University of Melbourne in Australia said.
Traditionally, the mental well-being of communities is judged through the use of surveys conducted of residents. However, this method has several flaws, which could be addressed though the analysis of Twitter postings. Not only are surveys expensive and time-consuming, but data is limited to the questions on the list. Instead, researchers studied Tweets looking for words such as "learning," "conference," and "management" which express positive feelings. These were compared to words expressing boredom, fatigue, and swears, associated with negative feelings.
"Imagine you go through a town that you don't know and you get a recording of all the traffic signs, the road signs, the menus, and then you start getting conversations between people, even though you might not know anything about the town. It would tell you a lot. Any single tweet probably has close to zero information, but that times a billion is a lot," Johannes Eichstaedt, a graduate student at the University of Pennsylvania, said.
Further research is examining depression in individuals and how it relates to Facebook status updates. Eichstaedt and his team are also comparing Twitter postings to incidents of the top 15 causes of death in the United States.
Investigation of the role Twitter could play in the prediction of heart disease was detailed in the journal Psychological Science.