social_network_social_media.R

# create reply network
# To create a reply network we need to know the username, and to whom the replies were directed. The username we know, and the information about the replies is stored in the field `replyToSN`

reply_net <- data.frame(sender = "@katerinabohlec", 
                        #receiver = userTl.df[,as.factor(4)] %>% group_by_(as.factor(replyToSN)) %>% summarize(weight = n()),
                        receiver=userTl.df[,c(4)], 
                        type = "reply")
reply_net <- reply_net[-which(is.na(reply_net[,2])),]
dim(reply_net)

reply_net <- data.frame(sender = "@katerinabohlec", 
                        reply_net %>% group_by(receiver) %>% summarize(weight = n()))
reply_net$type <- "reply"

# create mention network
mentioned = 
  lapply(userTl.df$text, function(tx) {
    matches = gregexpr('@[^([:blank:]|[:punct:])]+', tx)[[1]]
    sapply(seq_along(matches), function(i) 
      substr(tx, matches[i] + 1, matches[i] + attr(matches, 'match.length')[i] - 1))
  })

mention_net = 
  lapply(seq_along(userTl.df$text), function(i) {
    if(mentioned[[i]] == '')  
      return(NULL)
    lapply(mentioned[[i]], function(m)
      c(sender = as.character(userTl.df$screenName[i]), receiver = m)) %>%
      do.call(rbind, .) %>% as.data.frame()
  }) %>% 
  do.call(rbind, .) %>%
  count(tolower(sender), tolower(receiver))
mention_net$type = "mentioned"
names(mention_net) <- c("sender", "receiver", "weight", "type")

tw_net <- rbind(reply_net, mention_net)

tw_net_g <- igraph::graph.data.frame(tw_net, directed=T)
# I'n going assume that the networks are very big. Visualizing them will be better in gephi

library(rgexf)
g1.gexf <- igraph.to.gexf(tw_net_g)

# You have to create a file connection.
f <- file("twitter_network.gexf")
writeLines(g1.gexf$graph, con = f)
close(f)