I can’t resist a word cloud: now using R!

Top 1000 words in FriendFeed comments, ISMB 2008-2011

The wordcloud package is word clouds for R with a difference: they look great.

Of course, having just analysed online coverage of the ISMB conference, I had to run all 6 906 comments from the 2008-2011 meetings through some code. If you followed along via the Sweave code, I went as far as generating the data frame of comments, ismb.comments, then pulled the comment text into a new data frame using:

data.frame(ismb.comments$body)

It was then simply a case of following along with the excellent example code from the post Word Cloud in R, over at One R Tip A Day, limiting myself to the 1000 most-used words. Watch out, the TermDocumentMatrix() function from the tm package uses quite a lot of memory.

Result shown at right: click image for full-size version. I think that word in the centre says it all.

Analysis of ISMB coverage at FriendFeed: 2008 – 2011

ISMB/ECCB 2011 was held between July 15-19 this year and as in previous years, FriendFeed was used to cover the meeting.

Last year, I wrote a post about how to use R to analyse the coverage. I was planning something similar for 2011 when I thought: we have 4 years of ISMB at FriendFeed now – why not look at all of them?

So I did. Read on for the details.