He said Bank of Italy on Monday: A suite of empirical indicators it has created from the content of millions of tweets on its Twitter platform has accurately tracked consumer sentiment over price, providing room for a powerful new tool for monetary policy.
The effort comes as economists around the world are increasingly turning to social platforms and other unconventional sources to gauge consumer behavior as inflation persists.
The researchers found that the indicators matched final readings of inflation Current metrics for price forecasts from the Italian National Statistical Office and financial markets were also real-time and provided more accurate details.
The authors of the 107-page study said: The findings indicate that Twitter could be a new resource for devising a way to elicit beliefs, and we believe that research focusing on Italy can be replicated elsewhere.
Twitter has nearly 200 million monthly active users worldwide, and it had about 10 million active users in Italy in 2019.
The analysis began by gathering 11.1 million tweets published in Italian between June 2013 and December 2019 containing at least one of the previously selected group of words related to inflation, prices and prices.
The study said: The focus on the number of tweets came from the intuitive idea that the more people talk about something, the more likely it will reflect their opinion, and their point of view can influence the expectations of others.
The dataset was used to build two indicators on expectations of increasing or decreasing inflation by measuring the daily volume of tweets containing pre-defined word combinations.
The final set of indicators was created on the basis of the difference between the two indicators, andThe authors said: The work sheds light on the importance of information received via social networks and its political implications.
They also noted that there have been a small number of cases of a Twitter-based indicator being derailed due to the rapidly spreading events across social platforms, and acknowledged the need for more study to interpret the data.