MonitoringMediaR.r

mediapart<-userTimeline(user="mediapart",
                        n=500,cainfo="cacert.pem")
lemonde<-userTimeline(user="lemondefr",
                      n=500,cainfo="cacert.pem")
lefigaro<-userTimeline(user="Le_Figaro",
                       n=500,cainfo="cacert.pem")
leparisien<-userTimeline(user="le_Parisien",
                         n=500,cainfo="cacert.pem")
#Concaténation
Media.df<-rbind(mediapart.df,
                lemonde.df,
                lefigaro.df,
                leparisien.df)

# Les mots les plus utilisés

mots <- strsplit(mediapart.df$text, " ")
numb = as.character(seq(1,1000,1))
sw<- c("a",stopwords("fr"),numb)
mots <- lapply(mots, function(x) x[grep("^[A-Za-z0-9]+$", x)])
mots <- unlist(mots)
mots <- tolower(mots)

# Réaliser son wordcloud
mots <- mots[!mots %in% sw]
mots.t <- as.data.frame(table(mots))
mots.t <- mots.t[sort.list(mots.t$Freq, decreasing = T),]
pal <- brewer.pal(8, "Dark2")
par(bg = "black")
wordcloud(mots.t$mots,mots.t$Freq, scale=c(6,0.7), min.freq=1, max.words=Inf,
  random.order=F, rot.per=0.25, colors=pal, vfont=c("sans serif","plain"))