better matching, now with plural forms and less distance

issuecomp-analysis.R

@@ -29,6 +29,8 @@ issues[issueheads] <- 0
 tweets$issue <- ""
 tweets$tags <- ""
 
+tagexpand <- c("", "s", "n", "en")
+
 for(d in 1:nrow(issues)) {
   # Go through every day
   curdate <- issues$date[d]
@@ -61,10 +63,23 @@ for(d in 1:nrow(issues)) {
         } 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])
+          }
+        }
                  
-        # 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, curacro)
-        if(tags_found == 1) {
+        # Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow also 1 (Levenshtein distance)
+        tags_found <- NULL
+        for(e in 1:length(curtag)) {
+          tags_found[e] <- smartPatternMatch(curtext, curtag[e], curchars, 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
           
@@ -117,6 +132,22 @@ 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 -----------------------------------------------------------------