使用 R 语言挖掘 QQ 群聊天记录

每天活跃人数统计

#根据flat.day数据观察每天活跃用户变化# numday为每天发言人数numday <- apply(flat.mat,2,sum)
tempdf <- data.frame(time=ymd(names(numday)),numday)
qplot(x=time,y=numday,ymax=numday,geom='linerange')

• 十强选手的日内情况

# 再观察十强选手的日内情况

flat.hour <- dcast(newdata,id~hour,value.var='hour',subset=.(id %in% topuser))# 平行坐标图

hour.melt <- melt(flat.hour)
p <- ggplot(data=hour.melt,aes(x=variable,y=value))
p + geom_line(aes(group=id,color=id))+theme_bw()+theme(legend.position = "none")

• 连续对话的次数，以三十分钟为间隔

# 连续对话的次数，以三十分钟为间隔

newdata$realtime <- strptime(newdata$time,'%Y-%m-%d %H:%M')# 时间排序有问题，按时间重排数据

newdata2 <- newdata[order(newdata$realtime),]# 将数据按讨论来分组

group <- rep(1,dim(newdata2)[1])for (i in 2:dim(newdata2)[1]) {
 ? 
?d <- as.numeric(difftime(newdata2$realtime[i],
 ? ? ? ? ? ? ? ? ? ? ? ? ? ? newdata2$realtime[i-1],
 ? ? ? ? ? ? ? ? ? ? ? ? ? ? units='mins')) ? ?

if ( d < 30) {
 ? ? ? ?group[i] <- group[i-1]
 ? ?} 
 ? ?else {group[i] <- group[i-1]+1}
}
barplot(table(group))

• 画社交网络图

# 得到 93 多组对话newdata2$group <- group# igraph进行十强之间的网络分析# 建立关系矩阵，如果两个用户同时在一次群讨论中出现，则计数+1newdata3 <- dcast(newdata2,id~group,sum,value.var='group',subset=.(id %in% user[1:10,]$Var1))#newdata4 <- ifelse(newdata3[,-1] > 0,0)
rownames(newdata4) <- newdata3[,1]
relmatrix <- newdata4 %*% t(newdata4)# 很容易看出哪两个人聊得最多

deldiag <- relmatrix-diag(diag(relmatrix))
which(deldiag==max(deldiag),arr.ind=T)# 根据关系矩阵画社交网络画

g <- graph.adjacency(deldiag,weighted=T,mode='undirected')
g <-simplify(g)
V(g)$label<-rownames(relmatrix)
V(g)$degree<- degree(g)
layout1 <- layout.fruchterman.reingold(g)#egam <- 10*E(g)$weight/max(E(g)$weight)egam <- (log(E(g)$weight)+1) / max(log(E(g)$weight)+1)#V(g)$label.cex <- V(g)$degree / max(V(g)$degree)+ .2V(g)$label.color <- rgb(0,.2,.8)
V(g)$frame.color <- NA
E(g)$width <- egam
E(g)$color <- rgb(0,0,1,egam)
plot(g,layout=layout1)

• 找到配对

#找到配对pairlist=data.frame(pair=1:length(attributes(deldiag)$dimnames[[1]]))
rownames(pairlist)<-attributes(deldiag)$dimnames[[1]]for(i in(1:length(deldiag[1,])))
{
pairlist[i,1]<-attributes(which(deldiag[i,]==max(deldiag[i,]),arr.ind=T))$names[1]
}
pairlist

pairmatrix=data.frame(pairA=1:length(attributes(deldiag)$dimnames[[1]]),pairB=1:length(attributes(deldiag)$dimnames[[1]]))
pairmatrix=data.frame(pair=1:length(attributes(deldiag)$dimnames[[1]]))for(i in (1:dim(deldiag)[1]))
{
deldiag[i,] <- ifelse(deldiag[i,] == max(deldiag[i,0)
}
deldiag