Bloggers and social networks propel billions of emotion-laden words into cyberspace every day. What if you could, day to day, magically rate all these feelings?<\/p>\n
Maybe you\u2019d find that collectively we\u2019re happy on Sunday mornings, after a cup of coffee. Or that we felt downright ecstatic after Barack Obama was elected president. Or that we\u2019re glum on Mondays.<\/p>\n
Chris Danforth \u201901 doesn\u2019t need to muse about this stuff. He really knows when we\u2019re happy or sad. A mathematician at the University of Vermont, Danforth and colleague Peter Dodds have created a high-tech hedonometer \u2014 a way to measure, in real time, the shifting emotions reflected by our vast blog output and, more recently, our Twitter feeds.<\/p>\n They also know who sings happy songs (and unhappy ones), and what president\u2019s rhetoric is more gloom and doom than the others.<\/p>\n The two researchers\u2019 work represents a really cool achievement in what they call \u201csociotechnical data mining\u201d and a potentially novel approach to studying human behavior\u2014 one that goes beyond phone surveys with 500 respondents or psychological studies with a few dozen subjects.<\/p>\n \u201cWe\u2019ve never had the chance to make observations on this scale,\u201d Danforth says during an interview at the Vermont Advanced Computing Center in Burlington.<\/p>\n In the past, what was available to a social science researcher \u201cmight be a college classroom with 20 students beholden to their professor,\u201d he says. \u201cBut if you pay attention to what\u2019s going on online, your experiment can now go from on the order of 100 to the order of 100 million overnight.\u201d<\/p>\n Last summer, Danforth and Dodds announced their work in the Journal of Happiness Studies<\/em>. Their article, \u201cMeasuring the Happiness of Large-Scale Written Expression: Songs, Blogs, and Presidents<\/a>,\u201d got immediate media attention, partly because it included the fact that the national mood, as reflected in blog posts, had briefly soured after Michael Jackson\u2019s death a few weeks earlier.<\/p>\n The<\/em> New York Times<\/em>, <\/a>for example, quoted University of Texas psychologist James Pennebaker, who said the research is \u201ca cross-pollination of computer science, engineering, and psychology. And it\u2019s going to change the social sciences.\u201d<\/p>\n In other words, rather than having to ask a large group of people how they feel \u2014 an approach fraught with error \u2014 \u201cwe are watching conversations,\u201d Danforth says. \u201cWe\u2019re trying to infer someone\u2019s state of mind or well-being from what they say. This changes the game.\u201d<\/p>\n Using supercomputers, the two researchers evaluated 10 million blog sentences that came to them from the website wefeelfine.org<\/em><\/a>, a site that scours blogs for sentences that include \u201cI feel\u201d or \u201cI am feeling\u201d in them. To measure these key sentences\u2019 happiness \u2014 their \u201cemotional valence\u201d \u2014 the researchers turned to a special list of words that have been ranked on a one-to-nine happiness scale. For example, words like \u201ctriumphant\u201d or \u201ctrophy\u201d score happy while \u201chostage\u201d or \u201ccorrupt\u201d score sad.<\/p>\n Thus when Dodds and Danforth looked at \u201cI feel\u201d blog sentences right after the 2008 presidential election \u2014 the happiest day in their dataset \u2014 the word in those sentences that most drove the national smile was \u201cproud.\u201d<\/p>\n The pair made some surprising discoveries, including one that bears on the notion that money can\u2019t buy happiness. \u201cSocial scientists typically find that, provided you have basic food and shelter, ultimately you stay just as happy whether you win the lottery or become disabled,\u201d explains Danforth. \u201cBut we found that individuals do present their happiness differently over their lifetime.\u201d Teenagers are often mad, adults somewhat happier, and older folks increasingly grumpy.<\/p>\n Chip Ross and Bonnie Shulman, along with physics professor George Ruff, helped to show him that he could \u201cuse math to study the world.\u201d<\/p>\n The pair\u2019s hedonometer can assess any big pile of words, so they also looked at the lyrics of 232,574 songs by 20,025 artists released between 1960 and 2007. They found that Luther Vandross\u2019 songs are quite happy while Slayer\u2019s aren\u2019t. And they reviewed the words in State of the Union addresses. Kennedy\u2019s and Reagan\u2019s speeches score happy; Hoover, speaking gloomy words about the Depression, scores low.<\/p>\n Danforth, the nephew of Bates anthropology professor Danny Danforth, came to Bates eager to study math and not much else. Math professors Chip Ross and Bonnie Shulman, along with physics professor George Ruff, helped to show him that he could \u201cuse math to study the world.\u201d<\/p>\n
<\/a><\/p>\n