Hello fellow researchers,

I am looking for a preferably free text mining/ text analysis software with especially the following feature:

I have answers to open ended questions e.g. those three answers from three different persons:

- ban on pesticide

- it would be good to ban fertilizer and pesticides

- pesticides should be banned

I would like a software that realizes that ban/ banned and pesticide(s) are always in the same sentence, although they are not directly after each other. The best would be if the software could give me the count of these word combinations. It would be good if it also had a lemmatizing function so that ban and banned or pesticide and pesticides would be recognized as the same.

At the moment I am working with MAXQDA but there I have to input the word combinations myself and I would need a software that recognizes them automatically.

Thanks a lot!