Twitter Inc (NYSE:TWTR) can be used to replace costly methods to determine regional unemployment, a new study asserts.
A recent study from Alejandro Llorente, Manuel Garcia-Herranz, Manuel Cebrian, Esteban Moro published by Cornell University shows that data analysis of Twitter activity can determine how many people in a given geographic region are unemployed.
This Tiger Cub Giant Is Betting On Banks And Tech Stocks In The Recovery
The first two months of the third quarter were the best months for D1 Capital Partners' public portfolio since inception, that's according to a copy of the firm's August update, which ValueWalk has been able to review. Q2 2020 hedge fund letters, conferences and more According to the update, D1's public portfolio returned 20.1% gross Read More
Twitter can determine socio-economic status
The group set out to study universal patterns of behavior on Twitter to determine if they could uncover socio-economic status of various geographic regions. They attempted to quantify the extent to which deviations in patterns of behavior that follow day and night cycles, mobility patterns, and communication styles across regions relate to the geographic region’s unemployment incidence.
The researchers examined social media data in Spain and quantified individual behavioral features from over 145 million messages spanning more than 340 different Spanish economic regions. The results showed several clear differences in night and day Tweeting behavior and patterns could be discerned between high and low unemployment regions.
The study found that geographic regions exhibiting more diverse mobility, earlier diurnal rhythms, and more correct grammatical usage also displayed lower unemployment rates. For example, the rate of tweeting between 9am and midday on weekdays is significantly higher in areas of high unemployment. Tweets in high unemployment areas are more likely to contain words such as job or unemployment, while the messages themselves are more likely to contain spelling mistakes.
From this information the researchers built a model that approximated unemployment in each region. This is significant as the analysis, once set up in a template, can be quick, easy and cost effective. Certain countries are considering abandoning unemployment surveys due to the cost, and this could be a potential solution, the report noted, allowing governments and policy makers to monitor changes in the population, more or less in real time.
“The immediacy of social media may also allow governments to better measure and understand the effect of policies, social changes, natural or man-made disasters in the economical status of cities in almost real-time,” said Llorente, noting that their methodology could be applied to any location in the world.