Methodological proposal to identify the nationality of twitter users through random-forests

HIGHLIGHTS

SUMMARY

    The list of possible combinations with the columns on mentions is shown below. menciones= Below are the list groupings for retweets, replies, and quotes. retweets= replicas= rquotes= Fig 10 shows the results comparing the percentage of nationals in the user samples from the UsersCountry_D2 tables (79.48%, 76.88% and 75.84%, average 77.40%) with the percentage of nationals in the user samples from the UsersCountry_class1 tables (94.03%, 91.17% and 89.61%, average 91.60%) that were automatically labeled. When averaging the proportions inferred from the national samples in each country . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?