Corrent status

issuecomp-2-analysis.R

@@ -3,8 +3,8 @@ require(XML)
 require(ggplot2)
 require(reshape2)
 require(stringr)
-library(foreach)
-library(doParallel)
+require(foreach)
+require(doParallel)
 
 source("issuecomp-functions.R")
 setwd("~/Dokumente/Uni/Aktuell/BA-Arbeit/uni-ba-issuecomp")
@@ -94,7 +94,7 @@ foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
         }
         
         # Set Levenshtein distance depending on char length, acronym and hashtag status
-        if(curchars <= 4 || curacro || curhash) {
+        if(curchars <= 6 || curacro || curhash) { # Distance = 1 if 7 chars or longer
           curdistance <- 0
         } else {
           curdistance <- 1
@@ -191,6 +191,7 @@ for(r in 1:nrow(results)) {
 # SAVING ------------------------------------------------------------------
 
 save(tweets, file="tweets_tagged.RData")
+write.csv(tweets, file="tweets.csv")
 save(issues, file="issues.RData")