R语言推特twitter转发可视化分析

28次阅读

共计 2365 个字符,预计需要花费 6 分钟才能阅读完成。

原文链接:http://tecdat.cn/?p=5124

包含术语“生物信息学”的推文示例

第 1 步:加载所需的软件包

# load packages

library(twitteR)

library(igraph)

library(stringr)

第 2 步:收集关于“生物信息学”的推文

# tweets in english containing "bioinformatics"

dm_tweets = searchTwitter("bioinformatics", n=500,)

# get text

dm_txt = sapply(dm_tweets, function(x) x$getText())

第 3 步:识别转发

# regular expressions to find retweets

grep("(RT|via)((?:\\b\\W*@\\w+)+)", dm_tweets,

ignore.case=TRUE, value=TRUE)

# which tweets are retweets

rt_patterns = grep("(RT|via)((?:\\b\\W*@\\w+)+)",

dm_txt, ignore.case=TRUE)

# show retweets (these are the ones we want to focus on)

dm_txt[rt_patterns]

第 4 步:收集谁转发和谁发布

我们将使用这些结果来形成边缘列表以创建图形

# create list to store user names

who_retweet = as.list(1:length(rt_patterns))

who_post = as.list(1:length(rt_patterns))

# for loop

for (i in 1:length(rt_patterns))

{

# get tweet with retweet entity

twit = dm_tweets[[rt_patterns[i]]]

# get retweet source

poster = str_extract_all(twit$getText(),

"(RT|via)((?:\\b\\W*@\\w+)+)")

#remove ':'

poster = gsub(":", "", unlist(poster))

# name of retweeted user

who_post[[i]] = gsub("(RT @|via @)", "", poster, ignore.case=TRUE)

# name of retweeting user

who_retweet[[i]] = rep(twit$getScreenName(), length(poster))

}

# unlist

who_post = unlist(who_post)

who_retweet = unlist(who_retweet)

第 5 步:从编辑清单创建图形

# two column matrix of edges

retweeter_poster = cbind(who_retweet, who_post)

# generate graph

rt_graph = graph.edgelist(retweeter_poster)

# get vertex names

ver_labs = get.vertex.attribute(rt_graph, "name", index=V(rt_graph))

第 6 步:让我们绘制图

# choose some layout

glay = layout.fruchterman.reingold(rt_graph)

# plot

par(bg="gray15", mar=c(1,1,1,1))

plot(rt_graph, layout=glay,

vertex.color="gray25",

vertex.size=10,

vertex.label=ver_labs,

vertex.label.family="sans",

vertex.shape="none",

vertex.label.color=hsv(h=0, s=0, v=.95, alpha=0.5),

vertex.label.cex=0.85,

edge.arrow.size=0.8,

edge.arrow.width=0.5,

edge.width=3,

edge.color=hsv(h=.95, s=1, v=.7, alpha=0.5))

# add title

title("\nTweets with'bioinformatics': Who retweets whom",

cex.main=1, col.main="gray95")

第 7 步:让我们试着给它一个更生物信息学的外观

# another plot

par(bg="gray15", mar=c(1,1,1,1))

plot(rt_graph, layout=glay,

vertex.color=hsv(h=.35, s=1, v=.7, alpha=0.1),

vertex.frame.color=hsv(h=.35, s=1, v=.7, alpha=0.1),

vertex.size=5,

vertex.label=ver_labs,

vertex.label.family="mono",

vertex.label.color=hsv(h=0, s=0, v=.95, alpha=0.5),

vertex.label.cex=0.85,

edge.arrow.size=0.8,

edge.arrow.width=0.5,

edge.width=3,

edge.color=hsv(h=.35, s=1, v=.7, alpha=0.4))

# add title

title("\nTweets with'bioinformatics': Who retweets whom",

cex.main=1, col.main="gray95", family="mono")

正文完
 0