The Bank of Italy said Monday that a set of experimental indicators it created from the content of millions of tweets accurately tracked consumer sentiment about price, offering the possibility of a powerful new monetary policy tool. .
The effort comes as economists and policy makers around the world increasingly turn to social media and other unconventional sources to measure consumer behavior and as inflation continues to challenge the targets set by many of the major central banks. .
The researchers found that their indicators, based on millions of tweets, not only featured final inflation readings and existing measures of price expectations by Italy’s national statistics office, financial markets and other forecasters, but also they were also in real time and provided more granular detail.
“The results suggest that Twitter may be a timely new source for devising a method for generating belief,” the authors of the 107-page study said, adding that they believed the research focused on Italy could be replicated elsewhere.
Twitter has roughly 200 million monthly active users worldwide and had around 10 million active users in Italy in 2019, the authors said.
The analysis began with the compilation of 11.1 million tweets published in Italian between June 2013 and December 2019 that contain at least one of a set of previously selected words related to inflation, prices and price dynamics.
“The reason for focusing on pure tweet counting is the intuitive notion that the more people talk about something, the more likely it is to reflect their opinion and that your point of view can influence other people’s expectations,” He said.
The dataset was then “cleaned up” to remove ads or tweets that use the word inflation in an unrelated context.
In this way, tweets like “#Draghi: ‘We saved Europe from deflation.’ Don’t count your chickens before they hatch! “remained, while others, such as” Only in Baby Glamor if you buy three items, the least expensive is free. Promotional sales through October 10 “were leaked.
The remaining data set was used to construct two indices on expectations of rising or falling inflation by measuring the daily volume of tweets containing previously selected combinations of words, such as “sale price” or “very high price.”
“The fact that economic agents talk about expensive bills should reflect expectations of higher inflation,” the report said. “On the other hand, people who discuss falling oil prices should correspond to expectations of lower inflation.”
The final set of indicators was then created based on the divergence between the two indices.
The authors said their work underscored the importance and political implications of information on social media, but acknowledged that more studies are needed to interpret the data.
They also pointed out that there were some instances of a Twitter-based indicator being derailed by a viral event on social media, for example when the sale of an apartment for a record $ 236 million (roughly Rs. 1.7 billion) rupees) in 2014 resulted in a series of tweets containing variants of the phrase “most expensive”.
© Thomson Reuters 2021
Can Realme X7 Pro take on OnePlus Nord? We talked about this on Orbital, our weekly tech podcast, which you can subscribe to via Apple podcasts, Google podcasts, or RSS, download episode, or just press the play button below.
.
She is a freelance blogger, writer, and speaker, and writes for various entertainment magazines.