On Monday, the Bank of Italy announced that it had produced a collection of experimental indicators from the material of millions of tweets that accurately monitor consumer price moods. As economists and policymakers around the world are increasingly turning to social networks and other unorthodox sources to evaluate consumer behavior, the effort comes as inflation tends to challenge the goals set by many of the leading central financial institutions.
It has offered the potential for a new powerful monetary policy instrument. Researchers found that their metrics, based on millions of tweets, not only matched Italy’s national statistics office, financial markets, and other forecasters with final inflation read-outs and current price expectation measures. Indicators were also in real-time, however, and gave more concentrated detail.
The authors of the 107-page study said, “The results suggest that Twitter can be a new timely source for devising a method to elicit beliefs”. They added that they believed the Italy-focused research could be replicated elsewhere.
According to the authors, Twitter has about 200 million monthly active users worldwide and about 10 million active users in Italy in 2019.
Effect On Inflation:
The research began with the compilation of 11.1 million Italian-language tweets between June 2013 and December 2019, including at least one of a number of terms previously chosen relating to inflation, price, and price dynamics.
“The rationale for focusing on pure raw tweets count is the intuitive notion that the more people talk about something, the larger is the probability it reflects their opinion and that their view can influence other people’s expectations,” it stated.
Then, to delete ads or tweets using the term inflation in an irrelevant way, the dataset was “cleaned”.
Tweets such as “#Draghi: ‘We saved Europe from deflation.’ Do not count your chickens before they are hatched!” were held in this way. While others were flushed out, including “Only at Baby Glamour if you buy three items the least expensive is free. Promotional sales until October 10”
By calculating the regular amount of tweets containing previously chosen word combinations of phrases such as ‘bargain price’ or ‘very high price,’ the remaining dataset was used to create two indexes on assumptions of increasing or decreasing inflation.
“The fact that economic agents talk about expensive bills should reflect expectations of higher inflation. On the other hand, people discussing declining oil prices should correspond to expectations of lower inflation”. The report said.