A mathematician and computer scientist working in the Advanced Computing Center at the University of Vermont have created a remote-sensing mechanism that examines the content of blogs to measure the emotional levels of millions of people. The result is the ‘We Feel Fine’ system, which purports to give an indication of how people around the world are feeling.
The ‘We Feel Fine’ system works by searching newly posed blog entries for occurrences of the phrases “I feel” and “I am feeling.” It records the full sentence and identifies the “feeling” expressed in that sentence. Each sentence then receives a happiness score based on a standardized “psychological valence’ of words established by the Affective Norms for English Words (ANEW) study. For example, “triumphant” scores 8.87 on the happiness-unhappy scale, while “suicide” scores 1.25.
And because blogs are structured in largely standard ways, the age, gender, and geographical location of the author can often also be extracted, as can the local weather conditions at the time the sentence was written. The resulting database of several million human feelings, which increases by 15,000 to 20,000 new feelings per day, can then be searched and sorted across a number of demographic parameters to offer insight into specific questions.
For example the system showed that Election Day, November 4, 2008, was the happiest day in four years showing a spike in the word “proud”, while the day of Michael Jackson’s death and the two following were some of the unhappiest. Each year, September 11 gets a dip, as does September 10, in apparent anticipation of the anniversary.
The system’s creators, Peter Dodds and Chris Danforth, say that, although bloggers tend to be younger and more educated than average, they are broadly representative of the US population, writing from most everywhere with an even split between genders and high racial diversity. And although the system generally focuses on how the writings are received rather than what and author may have intended to convey, they say their method does allow an estimation of the emotional state of the blog authors.
Their method drew conclusions that are contrary to recent social science data that suggests that people basically feel the same at all ages of life. Instead, Dodds and Danforth's method shows young teenagers are unhappiest with a disproportionate use of "sick," "hate," "stupid," "sad," "depressed," "bored," "lonely," "mad," and, not surprisingly, "fat." After the teenage years people get happier, until they are old when happiness drops off according to the results.
Dodds and Danforth also apply their method to song lyrics, presidential speeches, and, recently, to Twitter messages. For example they found that the happiness of song lyrics trends downward from the 1960s to the mid 1990s while remaining stable within genres.
Anyone wanting to see how their own emotional state compares to others around the globe can visit the We Feel Fine site, while the study by Dodds and Danforth, Measuring the Happiness of Large-Scale Written Expression: Songs, Blogs, and Presidents, will be permanently available in an open-access edition of the Journal of Happiness Studies.