uni-ba-socialagenda/issuecomp-analysis.R

require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)

# Create date range
date_start <- as.Date("2014-01-01")
date_end <- as.Date("2014-12-31")
drange <- as.integer(date_end - date_start)
drange <- date_start + days(0:drange)


# MATCH TWEETS ------------------------------------------------------------

issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0

for(d in 1:nrow(issues)) {
  # Go through every day
  curdate <- issues$date[d]
  cat(as.character(curdate),"\n")
  
  # Put all tweets from specific day in a temporary DF
  tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
  
  for(t in 1:nrow(tweets_curday)){
    # Select tweet's text, make it lowercase and remove hashtag indicators (#)
    curtext <- as.character(tweets_curday$text[t])
    curtext <- str_replace_all(curtext, "#", "")
    
    # Now test each single issue (not tag!)
    for(i in 1:length(issuelist)) {
      curtags <- as.character(issuelist[[i]])
      curissue <- names(issuelist)[i]

      # Now test all tags of a single issue
      for(t in 1:length(curtags)) {
        curtag <- str_c("\\W", curtags[t], "\\W")
        curchars <- nchar(curtag, type = "chars") - 4
        
        # Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
        tags_found <- smartPatternMatch(curtext, curtag, curchars)
        if(tags_found == 1) {
          #cat("Matched", curtag, "with", curtext,"\n")
          issues[d,curissue] <- issues[d,curissue] + 1
          break
        }
        else {
          #cat("Nothing found\n")
        }
      } # /for curtags
      
    } # /for issuelist
  } # /for tweets_curday
} # /for drange



# WEEKLY INTERVALS --------------------------------------------------------



## Do not use days but week intervals

wrange <- (as.integer(date_end - date_start) / 7)
wrange <- floor(wrange) - 1
wrange <- date_start + weeks(0:wrange)
issues_week <- data.frame(week = wrange)
issues_week[issueheads] <- 0


for(w in 1:nrow(issues_week)) {
  curweek <- issues_week$week[w]
  currange <- curweek + days(0:6)
  
  day <- 1
  
  
  for(d in 1:nrow(issues)) {
    curday <- issues$date[d]
    
    if(curweek == curday) {
      for(c in 2:ncol(issues)) {
        curissue <- names(issues)[c]
        d2 <- d + 6
        curvalue <- sum(issues[d:d2,curissue])
        issues_week[w, curissue] <- curvalue
        
      } # /for issues columns
    } # /if day matches first day of week
    
  } # /for issues rows
} # /for issues_week




# VISUALS -----------------------------------------------------------------

# Level: days
issues_melt <- melt(issues,id="date")
ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_line(size=1)
ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_smooth(size=1,method="loess",formula = y ~ x, se=FALSE)

# Level: weeks
issues_week_melt <- melt(issues_week,id="week")
ggplot(issues_week_melt,aes(x=week,y=value,colour=variable,group=variable)) + geom_line(size=1)
ggplot(issues_week_melt,aes(x=week,y=value,colour=variable,group=variable)) + geom_smooth(size=1,method="loess",formula = y ~ x, se=FALSE)


# POSSIBLY USEFUL CODE ----------------------------------------------------

# Limits of list
length(issuelist)
length(issuelist[[2]])

# Select all tweets from current day in drange
tweets_curday <- tweets[tweets[, "created_at"] == drange[5], ]
# Is column a issue counting column?
str_detect(names(issues[2]), "^issue")