sigir 13'.R

library(tm)

## read from txt file
path = 'd:/sigir_full.txt'
f <- file(path,open='rt')
con <- readLines(f)
close(f)

## get the tile from the content
paperTitles <- con[grepl("^Title: ",con)]
paperTitles <- lapply(paperTitles,function(x) strsplit(x,':')[[1]][2])

##TermDocMatrix
paperTitlesCorpus <- Corpus(VectorSource(paperTitles))
ptTermMatrix <- TermDocumentMatrix(paperTitlesCorpus, 
                                   control=list(
                                     stopwords=T,
                                     removePunctuation=T,
                                     removeNumbers=T))
print(findFreqTerms(ptTermMatrix,4))

##word clound
m <- as.matrix(ptTermMatrix)
v <- sort(rowSums(m), decreasing=TRUE)
myNames <- names(v)
d <- data.frame(word=myNames, freq=v)
par(mar = rep(2, 4))

png(paste(getwd(), "/sigir13",  ".png", sep = ''), 
    width=10, height=10, 
    units="in", res=700)

pal2 <- brewer.pal(8,"Dark2")
wordcloud(d$word,d$freq, scale=c(5,.2), min.freq=mean(d$freq),
          max.words=80, random.order=FALSE, rot.per=.15, colors=pal2)
dev.off()