How to read the data of all-vv document

medianeuroscience / emfdscore

Fast, flexible extraction of moral information from textual input data.

GNU General Public License v3.0

102 stars 28 forks source link

How to read the data of all-vv document #10

Closed Emma123295 closed 3 years ago

Emma123295 commented 3 years ago

Hello, I have some problems when interpreting the data of all vice-virtue documents. The vice-virtue split is accomplished by considering the average sentiment of each foundation of each word, but I found all virtue and vice values are positive. Would you please show me how to read these values? Should I compare the size of virtue and vice value to decide if the text uses virtue or vice foundation?

fhopp commented 3 years ago

Hi @Emma123295 , yes, when you use the vice-virtue scoring option, then higher values in either a virtue or a vice column mean that the text uses a higher representation of either vices or virtues in a particular foundation. Say an article returns care.virtue .4 and care.vice .6, then you know that there is slightly more "harm" (care.vice) than "care" (care.virtue) represented.