Words, counting words and visualisations.

I went to a seminar today discussing how to analyse comments on a news Website.  I went primary as I want to engage in analysing comments myself, and thought that it would help with my research.

The researchers had over 45 million comments that they had collected, which made me feel that 30,000 or so lines of comment was a bit pathetic, but  I can’t really complain if people are not using revenge pornography Websites enough.

The talk was interesting as the researchers had used regex queries in order to analyse the data and categorise the comments as to whether they were insulting to other contributors.  The idea of using queries to help with the qualitative analysis is intriguing to me, but I don’t think I would be able to trust my programming enough to allow this to happen.  With datasets running into the millions this would be the only way to do it.

After the talk I went back to my office and spent five minutes (honestly supervisors) making a word cloud of the most popular words found in the titles posted to a revenge pornography Website, seen below.

Post Titles Word Cloud

These are the words that are used to describe the person in the post.  Many of these are sexually denigrating words likes whore, slut bitch as well as words used to describe body parts.

Just a visual reminder of the type of language directed towards those who find themselves on a revenge pornography Website.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s