Stefan Müller

Good idea, we could add exercises to https://tutorials.quanteda.io after each of the (currently) seven main chapters of the tutorial website. I could start working on this in January. @koheiw, is...

@kbenoit: When I wanted to show this example to the participants in Bremen, your website was down and it seems that this is still the case.

Hi @louislegum, you could look into @JBGruber's [LexisNexisTools](https://github.com/JBGruber/LexisNexisTools) R package. It includes functions to import files downloaded from NexisLexis. The package also allows you to extract the relevant meta data...

Thanks, Frederick. Sorry again for the confusing by referring to the wrong issue. I hope my code sets a good basis for implementing the option of two different `alpha`-levels. Delighted...

Sorry, I referred my PR to the wrong issue. It is actually related to #53 (allow multiple argument for alpha).

The **quanteda.classifiers** package contains the functions [`crossval()`](https://github.com/quanteda/quanteda.classifiers/blob/master/R/crossval.R) and [`performance()`](https://github.com/quanteda/quanteda.classifiers/blob/master/R/performance.R) which allow for straightforward k-fold cross-validation of `textmodel_nb()` and `textmodel_svm()`. While these models are included in **quanteda.textmodels**, functions for cross-validation are...

Yes, `textstat_svmlin()` works, but since it can only be used for binary classification tasks it won't fix the problem above (more than two groups). ``` # use 66,000 documents dfmat_66000...

Thanks! I am aware of this, but the original dictionary indicates negations though "not" in the categories `neg_negative` and `neg_positive`. Thus, changing the forms to "nicht" or "keine" would also...

That would be a very elegant solution. I just asked Christian Rauh what he thinks about this idea.

I have the same question as @cgnguyen. The text corpora and documentation are fantastic, but I need help with the XMI format. Do you have instructions on how to load...