require(lubridate) require(XML) require(ggplot2) require(reshape2) require(stringr) library(foreach) library(doParallel) source("issuecomp-functions.R") load(file = "tweets_untagged.RData") # 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 ------------------------------------------------------------ id_folder <- "matched-ids" unlink(id_folder, recursive = TRUE) dir.create(id_folder) issues <- data.frame(date = drange) issuelist <- readLines("issues.xml") issuelist <- str_replace_all(string = issuelist, pattern = ".*", "") issuelist <- xmlToList(issuelist) issueheads <- names(issuelist) issues[issueheads] <- 0 tweets$issue <- "" tweets$tags <- "" tagexpand <- c("", "s", "n", "en", "er", "e") # Parallelisation writeLines(c(""), "issuecomp-analysis.log") cl<-makeCluster(4) registerDoParallel(cl) df<-foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% { #for(d in 1:nrow(issues)) { # Go through every day curdate <- issues$date[d] cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE) # Put all tweets from specific day in a temporary DF tweets_curday <- tweets[tweets[, "created_at"] == curdate, ] for(t in 1:nrow(tweets_curday)){ cat(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE) # Select tweet's text, make it lowercase and remove hashtag indicators (#) curtext <- as.character(tweets_curday$text[t]) curtext <- str_replace_all(curtext, "#", "") curid <- as.character(tweets_curday$id_str[t]) # Now test each single issue (not tag!) for(i in 1:length(issueheads)) { curissue <- issueheads[i] curtags <- as.character(issuelist[[curissue]]) curfile <- str_c(id_folder,"/",curissue,".csv") # Now test all tags of a single issue for(s in 1:length(curtags)) { curtag <- curtags[s] curchars <- nchar(curtag, type = "chars") # Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch if(curchars <= 4) { curacro <- checkAcronym(string = curtag, chars = curchars) } else { curacro <- FALSE } # Now expand the current tag by possible suffixes that may be plural forms if(!curacro) { for(e in 1:length(tagexpand)) { curtag[e] <- str_c(curtag[1], tagexpand[e]) } } # Set Levenshtein distance depending on char length if(curchars <= 4) { curdistance <- 0 } else { curdistance <- 1 } # Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow also 1 (Levenshtein distance) tags_found <- NULL # Match the tweet with each variation of tagexpand for(e in 1:length(curtag)) { tags_found[e] <- smartPatternMatch(curtext, curtag[e], curdistance, curacro) } tags_found <- any(tags_found) curtag <- curtag[1] if(tags_found == TRUE) { # # Raise number of findings on this day for this issue by 1 # issues[d,curissue] <- issues[d,curissue] + 1 # # # Add issue and first matched tag of tweet to tweets-DF # oldissue <- tweets[tweets[, "id_str"] == curid, "issue"] # tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";") # oldtag <- tweets[tweets[, "id_str"] == curid, "tags"] # tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";") # Add information to file for function viewPatternMatching write(str_c(curdate,";\"",curid,"\";",curissue,";",curtag), curfile, append = TRUE) cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE) # data.frame(date=curdate, issue=curissue) break # next issue, no more tags from same issue } else { #cat("Nothing found\n") } } # /for curtags } # /for issuelist } # /for tweets_curday } # /for drange #rm(tweets_curday,curacro, curchars, curdate,curfile,curid,curissue,curtag,curtags,curtext,d,date_end,date_start,i,id_folder,oldissue,oldtag,s,t,tags_found) stopCluster(cl) # SAVING ------------------------------------------------------------------ row.names(tweets) <- NULL write.csv(tweets, "tweets.csv") save(tweets, file="tweets.RData") # SOME TESTS -------------------------------------------------------------- stats <- data.frame(date=drange) stats$tpd <- 0 # Total number of tweets per day over time for(r in 1:length(drange)) { stats$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"]) } stats_melt <- melt(stats, id="date") g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) + geom_line() + geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) g1 rm(g1, r) # Show party percentage of twitter users acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene")) acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats acc_parties$twitter <- 0 for(p in 1:nrow(acc_parties)) { acc_parties$twitter[p] <- round(nrow(acc_df[acc_df$party == as.character(acc_parties$party[p]), ]) / 280 * 100) } pie(acc_parties$btw13, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T, main = "Seats of parties in the parliament") pie(acc_parties$twitter, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T, main = "Percentage of parties' MdBs of all Twitter accounts") rm(acc_parties, p) # 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) # 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")