# Text wrangling before classification

**URL:** <https://discuss.huggingface.co/t/text-wrangling-before-classification/6069>\
**Category:** 🤗Transformers\
**Created:** [May 7, 2021, 5:45pm UTC](https://discuss.huggingface.co/t/text-wrangling-before-classification/6069 "2021-05-07T17:45:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![DanDanDan](https://avatars.discourse-cdn.com/v4/letter/d/eada6e/32.png) [@DanDanDan](https://discuss.huggingface.co/u/DanDanDan)\
**Post date:** [May 7, 2021, 5:45pm UTC](https://discuss.huggingface.co/t/text-wrangling-before-classification/6069/1 "2021-05-07T17:45:32Z")

</div>

Hi!  
I’m performing sentiment classification on some sentences.  
What I do is I fine-tune RoBERTa on a subset of my data.  
My question is what text wrangling I should perform?  
Should I lowercase, stem, remove punctuation?  
With a simpler model (logistic regression, tree, etc.), I would definitely do all of these things, but I’m not sure what to do when I use a transformer.