Tweet when you’re happy

Nieuws | de redactie
24 juli 2013 | Tracking social media has proven to be effective to track geographical variations in health. Flu trends can be measured easier and far quicker by using Google’s search data than by using the data from Centers of Disease Control. New research shows that also a community’s happiness can be measured using tweets.

Happiness or life satisfaction “goes far beyond the obvious attraction of positive emotion; it contributes to health, productivity and other positive life outcomes”, the researchers from the University of Pennsylvania and Michigan State University explain. The researchers doesn’t aim at just predicting regional variation in happiness, they try to understand it by the use of language in tweets.

“Happiness matters. For example, when a sample of Britons were asked what the prime objective of their government should be – “greatest happiness” or “greatest wealth”, 81% answered with happiness. In a set of other studies conducted around the world, 69% of people on average rate well-being as their more important life outcome. Psychologists still argue about how happiness should be defined, but few would deny that people desire it”, Johannes Eichstaedt and Andrew Schwartz write in their publication.

“We collected a billion tweets from June 2009 to March 2010, mapped as many as possible to the US counties that they were sent from, and correlated the words used in the tweets (in the form of LDA-generated word topics) with life satisfaction, as measured by questionnaires answered in those counties. We also have demographic information (age, sex, and ethnicity) and indicators of socio-economic status (income and education) by county, which we used as controls in a predictive model”, the authors explain.

‘Camping’ and ‘Zumba’ versus ‘Sooooooooo’

Topics that people tweet about say a lot about their well-being. People that tweet about their camping activities, their zumba lessons and the gym are thought to be happy. Social activity in tweets also indicates well-being, but it doesn’t only include restaurants and park visits. Conferences and meetings also suggest engagement. Tweets that mention words like “ideas”, “suggestions” and “advice” indicate strong social networks.

Negative topics are far less diverse; they include less substantive terms and more words relating to attitude, like “boring”. Some of the negative terms are very explicit, like “hate”. Others are more indicative of disengagement, for example “wtf”. The study found that these negative words are more often used by younger people. “This is suggestive of the empirical observation that older people tend, on average, to have higher subjective well-being, referred to by psychologists as the “aging positivity effect.” Or maybe older naggers don’t know how Twitter works yet.

Happiness is contagious

“The fundamental result of this paper is perhaps surprising: we can predict (on average) the happiness of one set of people (those who answered the life satisfaction questionnaires) from the tweets of other people (people in the same county). This is, however, consistent with findings from other methodologies. People in the same county tend to share the same culture and environmental affordances (e.g., hiking, music, or good employment), and attitudes towards them (being excited or bored)”, the scientists conclude.

twitter happiness research

twitter research survey

“Happiness is asserted to be contagious and it has been suggested that although educated people are happier, on average, than less educated ones, there is an even stronger benefit to living in a community of educated people with arts, culture and entertainment. Thus, the tweets of other people can indicate what it’s like to live around them, influencing one’s own happiness.”


«
Schrijf je in voor onze nieuwsbrief
ScienceGuide is bij wet verplicht je toestemming te vragen voor het gebruik van cookies.
Lees hier over ons cookiebeleid en klik op OK om akkoord te gaan
OK