How Do You Feel? Twitter Knows

Researchers have created an index to measure how happy everyone is and put it online.

This global mood index resembles a stock-market style measurement of several feelings.

Mathematicians at the University of Vermont developed the index by collecting about 50 million tweets a day from all around the world. These tweets were the analyzed for "happy", "sad" and "neutral" word content.

The project at www.hedonometer.org, has been collecting data for five years and went live Tuesday. It shows the ups and downs people express on the messaging platform about occurrences in their environment.

"Reporters, policymakers, academics - anyone - can come to the site and see population-level responses to major events," Dr. Chris Danforth, from the University of Vermont, one of two mathematicians who developed the hedonometer told Agence-France Presse.

Researchers found that April 15, the day of the Boston Marathon bombings, marked saddest day in the U.S. measured since their project began. That day ranked only slightly worse than the day of the Newtown, Conn. school shooting.

"Our instrument reflects a kind of quantitative macro-story, one that journalists can use to bring big data into an article attempting to characterize the public response to the incident," Danforth said.

The happiest days were typically Christmas or Thanksgiving. The scientists measured the tweets by ranking each word with a score. For example, the word happy got a score of 8.30 while the word War had a much lower score of 1.80 on the scale. The tweets were then averaged to paint a picture of the mood that day.

The researchers say they are trying to improve the tool to get information from two-word expressions, as opposed to single words. Using the two-word method could provide more context clues.

"It's the relative context that is so important: which is why the sudden drop from the Boston Marathon bombings jumps out at you. The hedonometer shows the pulse of a society," Danforth added.

Researchers say the hedonometer will be improved to utilize data from other online sources, including Google Trends, online blogs, and bit.ly links.

© 2024 iTech Post All rights reserved. Do not reproduce without permission.

Company from iTechPost

More from iTechPost