My master thesis focuses on crowdfunding project description, where I used Computer-Aided-Text-Analysis (CATA) to match the words in these to a predefined dictionary. The output is a quantity of matches from the project description and the dictionary.

I only use the three sub dimension "Innovativeness", "Proactiveness" and "Risk-Taking".

I was wondering how I can create a score that can be used for the regression looking at a relationship of "Entrepreneurial oriented" project descriptions and the continuous variable project success (measured in percentage)?