If you know the word hedonism, you might know what a hedonometer might measure. Researchers have developed one, and the project, at www.hedonometer.org, went live on Tuesday. The service munches Twitter data to determine the happiness index of those tweeting.
The project has been collecting data for about five years. It analyzes approximately 10 percent of all English language tweets, and measures the mood of the Internet community. Being that it examines only English language tweets, it is admittedly heavily weighted toward the United States.
The researchers might have made a mistake with this weighting. The U.S. is almost never among the top of countries in happy country surveys, and if one uses the Happy Planet Index, the U.S. is in 114th place at the time of this writing.
Still, what’s done is done.
According to the hedonometer, the day of the Boston Marathon bombings, April 15, 2013, was the saddest day measured in five years. It was slightly worse than the another horribly memorable date, the day of the Newtown, Conn., school massacre.
The happiest days measured were usually on holidays such as Christmas or Thanksgiving.
The day of the U.S. raid which killed Osama bin Laden — although possibly an upbeat one among Americans — was ranked as a sadder-than-average day because of the negative words expressed in tweets. “It happened to a negative person, and the texture of that day is talking about death, a negative event,” said lead researcher Peter Dodds.
Dodds said that the hedonometer uses the “psychological valence” of about 10,000 words that are compared against the tweets. As examples, on a scale of one to nine, the word “happy” is ranked 8.30, “hahaha” 7.94, “cherry” 7.04. At the bottom of the valence, “crash” is rated 2.60, “war” 1.80, and “jail” 1.76.
Some 50 million tweets are collected from around the world daily. Dodds said that “then we basically toss all the words into a huge bucket,” to calculate a happiness score, saying “It gives us some great insight and it works in real time.”
Although the hedonometer’s current calculations use only English-language tweets, the researchers said the hedonometer will later draw data from other streams of information, such as Google Trends, The New York Times, blogs, CNN transcripts, and text captured by the link-shortening service Bitly. It will eventually mine data in 12 languages.
The hedonometer project was led by Dodds and Chris Danforth at the Computational Story Lab at the University of Vermont with Mitre, a non-profit group that operates federal research centers and has expertise in the analytics of large amounts of data.
The researchers themselves did not come up with the term hedonometer. That word was first coined by Irish-born economist and philosopher Francis Edgeworth in the late 19th century, who spoke of “an ideally perfect instrument … continually registering the height of pleasure experienced by an individual.”