Text mining of crowdfunding data, including numerical metadata
I'm trying to analyze crowdfunding datasets for a study project.
The dataset shows in each row -amongst others-, a descriptions of the campaigns and how much money was raised for that campaign.
The goal is now to analyze the total occurence of certain terms in the dataset by using text mining.
The basic text mining process is not the problem. So as an example, I found out that the term "android" exists in 150 crowdfunding campaigns.
Now it would be interesting to find out how much money was spent on the campaigns that contain this word.
So, in theory, adding up the numbers from the raised money cell of every campaign that contains the word "android".
The goal is then to get a result like this, (so an additional column that shows the totalmone raised)
|word||attribute name||document occurences||total money raised|
Is this possible with text mining?
Thank you in advance!