Corrent status

2015-03-04 11:36:31 +01:00
parent a388110551
commit 9bbf1b4f56
16 changed files with 2713 additions and 494 deletions
@@ -0,0 +1,138 @@
+require(lubridate)
+require(XML)
+require(stringr)
+require(foreach)
+require(doParallel)
+
+source("issuecomp-functions.R")
+setwd("~/Dokumente/Uni/Aktuell/BA-Arbeit/uni-ba-issuecomp")
+
+
+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)
+
+# Import issues and prepare everything
+# Will only be filled after the large categorisation loop
+issues <- data.frame(date = drange)
+issuelist <- readLines("issues-v2.xml")
+issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
+issuelist <- xmlToList(issuelist)
+issueheads <- names(issuelist)
+issues[issueheads] <- 0
+tweets$issue <- ""
+tweets$tags <- ""
+
+
+# MATCH TWEETS ------------------------------------------------------------
+
+# Create folder where all results will be saved (saver for backup and import)
+id_folder <- "matched-ids"
+unlink(id_folder, recursive = TRUE)
+dir.create(id_folder)
+
+# Tag expansion for plural, genetiv etc
+tagexpand <- c("", "s", "n", "en", "er", "e")
+
+# Parameters for parallelisation
+writeLines(c(""), "issuecomp-analysis.log")  
+cl<-makeCluster(7)
+registerDoParallel(cl)
+
+# START CAT LOOP
+foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
+  # 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
+        curacro <- checkAcronym(string = curtag)
+        # Check if tag is some kind of specific hashtag. If so, do not handle as acronym, but don't expand it either
+        if(str_detect(curtag, "^#")) {
+          curacro <- FALSE   # hashtags like #WM2014 are also written as #wm2014, so we need case-insensitivity
+          curhash <- TRUE    # But we need to mark it as hashtag, so it doesn't get extended or Levenshtein distance > 0
+          curtag <- str_replace(curtag, "#", "")
+          curchars <- curchars - 1
+        } else {
+          curhash <- FALSE
+        }
+        
+        # Now expand the current tag by possible suffixes that may be plural forms
+        # Only do if it isn't an acronym or specific hastag
+        if(!curacro && !curhash) {
+          for(e in 1:length(tagexpand)) {
+            curtag[e] <- str_c(curtag[1], tagexpand[e])
+          }
+        }
+        
+        # Set Levenshtein distance depending on char length, acronym and hashtag status
+        if(curchars <= 6 || curacro || curhash) { # Distance = 1 if 7 chars or longer
+          curdistance <- 0
+        } else {
+          curdistance <- 1
+        }
+        
+        # Match current tweet with tag. 
+          # Allow 1 Levenshtein distance if tag is >= 5 letters and no hashtag or acronym
+          # Make is case-sensitiv if tag is an acronym
+        
+        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)