Tweets and RT's of #elag2013 plotted on a timeline by Twitter screen name

gistfile1.r

#########################################################
#
# Tweets and RT's of #elag2013 plotted on a timeline by Twitter screen name
#
# Tuija Sonkkila 30.5.2013
#
# The R code and most of the comments are from 
# http://blog.ouseful.info/2012/02/06/visualising-activity-round-a-twitter-hashtag-or-search-term-using-r/
# except when defining my own values etc of course
#
# OAuth help from 
# http://danielgillis.wordpress.com/2012/07/20/twitter-r-twitter/
# and http://dev.twitter.com
#
############################################################

library(twitteR)
library(ROAuth)
library(RCurl) 
library(plyr)
library(stringr)
library(ggplot2)

# Set SSL certs globally
# http://stackoverflow.com/a/16437729
options(RCurlOptions = list(cainfo = system.file("CurlSSL", "cacert.pem", package = "RCurl")))

reqURL <- "https://api.twitter.com/oauth/request_token"
accessURL <- "https://api.twitter.com/oauth/access_token"
authURL <- "https://api.twitter.com/oauth/authorize"
cKey <- "your consumer key here"
cSecret <- "your consumer secret here"

credentials <- OAuthFactory$new(consumerKey=cKey,
                                consumerSecret=cSecret,
                                requestURL=reqURL,
                                accessURL=accessURL,
                                authURL=authURL)
credentials$handshake()
registerTwitterOAuth(credentials)

#Pull in a search around a hashtag.
searchTerm='#elag2013'
rdmTweets <- searchTwitter(searchTerm, n=1000)
# Tuija: got 892

#Plot of tweet behaviour by user over time
#Based on @mediaczar's http://blog.magicbeanlab.com/networkanalysis/how-should-page-admins-deal-with-flame-wars/
#Make use of a handy dataframe creating twitteR helper function
tw.df=twListToDF(rdmTweets)

#@mediaczar's plot uses a list of users ordered by accession to user list
## 1) find earliest tweet in searchlist for each user [ http://stackoverflow.com/a/4189904/454773 ]

tw.dfx=ddply(tw.df, .var = "screenName", .fun = function(x) {return(subset(x, created %in% min(created),select=c(screenName,created)))})

## 2) arrange the users in accession order
tw.dfxa=arrange(tw.dfx,-desc(created))

## 3) Use the username accession order to order the screenName factors in the searchlist
tw.df$screenName=factor(tw.df$screenName, levels = tw.dfxa$screenName)

#ggplot seems to be able to cope with time typed values...
ggplot(tw.df)+geom_point(aes(x=created,y=screenName))

#Identify and colour the RTs...

#A helper function to remove @ symbols from user names...
trim <- function (x) sub('@','',x)

#Identify classic style RTs
tw.df$rt=sapply(tw.df$text,function(tweet) trim(str_match(tweet,"^RT (@[[:alnum:]_]*)")[2]))
tw.df$rtt=sapply(tw.df$rt,function(rt) if (is.na(rt)) 'T' else 'RT')

png("elag2013tweets.png", width=1280,height=800)
ggplot(tw.df)+geom_point(aes(x=created,y=screenName,col=rtt))
dev.off()