Researchers: Twitter Could Help Accurately Predict True Unemployment Rate
SACRAMENTO (CBS Sacramento) – Twitter could help predict the U.S. jobs report more accurately, researchers found.
A report published by the National Bureau of Economic Research found that unemployment numbers released by the government suffer from a lack of response.
The researchers found that people who are unemployed and who are surveyed more than once will most likely only respond to the survey the first time.
“It is possible that unemployed respondents who have already been interviewed are more likely to change their response to the labor force question, for example, if they want to minimize the length of the interview (now that they know the interview questions) or because they don’t want to admit that they are still unemployed,” the report, which was obtained by CBSNews, noted.
The researchers believe that this can end up skewing the unemployment rate downward.
Researchers at the University of Michigan believe that they have found a more accurate way of measuring the unemployment rate with Twitter. Researchers at the university searched for words and phrases which people use when talking about unemployment.
“’Lost work’ was one of the first phrases we chose,” Matthew Shapiro, a professor at the University of Michigan, said in a press release. “But it didn’t take long to figure out that it usually referred to a computer hard disk crashing. When we looked at the results, we saw that the word ‘computer’ showed up often.”
He, along with his colleagues, was able to test the results to makes sure the terms were indeed about unemployment.
The findings have not yet been published.