R code for analyzing tweets relating to #AAA2011 (text mining, topic modelling, network analysis, clustering and sentiment analysis)
Switch branches/tags
Nothing to show
Latest commit 938f822 Nov 19, 2013
benmarwick Update AAA2011.R
Edits in preparation for publication of book chapter
Failed to load latest commit information.
AAA2011.R Update AAA2011.R Nov 20, 2013
README Update README Dec 29, 2012


R code for obtaining and analysing tweets from the 2011 meeting of the American Anthropological Association

The code details ten steps in the analysis and visualisation of the tweets:

1.  acquiring the raw Twitter data
2.  calculating some basic statistics with the raw Twitter data
3.  calculating  some basic retweet statistics
4.  calculating the ratio of retweets to tweets
5.  calculating some basic statistics about URLs in tweets
6.  basic text mining for token frequency and token association analysis
7.  calculating senitment scores of tweets, including on subsets containing tokens of interest
8.  hierarchical clustering of tokens based on multiscale bootstrap resampling
9.  topic modelling the tweet corpus using latent Dirichlet allocation
10. network analysis of tweeters based on retweets

Author: Ben Marwick
Contact: http://faculty.washington.edu/bmarwick/how-contact-me
Licence: http://creativecommons.org/licenses/by-nc-sa/2.0/
Date: Dec 2011