My goal is to classify users to see if they live in USA.
For each user, I have a string that contains their BIO and contains their location.
It can be:
Father, Marketer, Lives in New York.
Or
Agency owner, US
Or
Artist from NY,US.
etc...
Now I want to analyze this text and see if the person actually lives in the US.
But as you can see in the examples not all users claim that they live in US.
Some mentioned USA some only mentioned the city or the state.
What I tried is creating an Excel in which each row contains a city or a state from the US and I've also added two cells one contains the string United States of America and the other one USA.
My next step was to loop in all the Excel cells and see if they appear in the bio of the user.
I wasn't able to get this to work.
I also tried using a dedicated Python script for this but I had many false positive false negative issue.
I don't want to go the nested if route I think it's not efficient.
I'm probably missing something with regard to use of "contain" in the condition or leveraging regex.
But, I don't know what I don't know.
Would love some advice about this.