Technology.am (July 26, 2009) — Scientists have created a tool that “knows” to measure the “happiness” levels of millions of people at any given point in time with a reasonable degree of certainty.
Peter Dodds and Chris Danforth, a mathematician and computer scientist working in the Advanced Computing Center at the University of Vermont, say they have created a remote-sensing mechanism that can record how millions of people around the world are feeling on any particular day — without their knowing it.
Their methods say that the 2008 US Election Day was one of the happiest days for Americans, with a huge spike in words like “proud,” while the day of Michael Jackson’s death were among the unhappiest day.
They started with a site, wefeelfine.org, which scours the Internet looking for certain phrases. After gathering almost 10 million sentences they applied the findings of a previous study, Affective Norms for English Words (ANEW), which gave common English words a “psychological valence,” to determine the happiness score of every sentence.
The ANEW study asked participants to assign words on an unhappy to happy scale. The software searches some 2.3 million web sites looking for sentences beginning with “I feel” or “I am feeling.
In the ANEW study, a large pool of participants graded their reaction to 1,034 words, forming a kind of “happy-unhappy” scale from 1 to 9. For example, “triumphant” averaged 8.87, “paradise” 8.72, “pancakes” 6.08, “vanity” 4.30, “hostage” 2.20, and “suicide” 1.25. For example, the sentence “I feel lazy” would receive a score of 4.38.
The scale of the study and the size of the texts they analyzed and believed that the findings give an accurate measurement of the general state of happiness of a large group of people. Their method is only reasonable for large-scale texts available on the Web.