1

I am searching urgent for a software that I can use to analyse corpora. In short, I would like to have a look at collocations, ellipsis, frequencies, concordances etc. I also want to search for themes and then accordingly to be able to assign the data different categories, so that I am able to work further on these. For overview of the data I tried to upload it in AntConc, but it is not working (though that the data is less than 400MB). I read about QDAMiner, didn’t understand however if WordStat is part of it or it can run separately (or what I need in general). Do you have any comments or suggestions about a program I can use? I am grateful for every information

EDIT: I would like to carry out mostly qualitative analysis, so the program doesn't have to do all analysis automatically, but to offer tools/features which can help me analyze the data.

1 Answer 1

1

You are asking for a software that can do quite a lot. Many of the tasks you are asking for can be done with Python NLTK, for pointers to some tutorial see TeLeMaCo hosted by the CLARIN-D centra at Saarland University. For themes, a topic model can be of help, see here for tutorials on topic modelling.

I am not aware of any software that can annotate ellipsis automatically (in any language).

EDIT: In response to the comment, there is another relevant software, namely the Corpus Query Processor and its web fontend CQPweb. Again, there are some tutorials linked from TeLeMaCo.

1
  • I forgot to mention that I plan to carry out the analysis mostly manually. I have just edited my question, thank you for the information. Basically, except the trivial features -to be able to produce collocations, frequencies, concordances etc., the program should allow me to assign (manually) categories to segments of the corpus and then be able to work with them structured.
    – Cathe
    Sep 7, 2019 at 21:23

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.