amy-langley / tracking-trans-hate-bills

2 stars 1 forks source link

Word frequency analysis of hate emails #7

Open amy-langley opened 1 year ago

amy-langley commented 1 year ago

datasets/Emails.pdf is a leaked trove of emails relating to past anti-trans legislation. It should be easy enough to generate a word frequency analysis of this dataset similar to visualize/word_freq.ipynb, but we will need to develop a new stopword list to exclude names (since they are not very interesting) and other artifacts of the email format