U.S. Senator Networks on Twitter
Kagen Lim
2021-04-08
Network Analysis of U.S. Senate Tweets
Overview
Twitter is a great tool to analyze the public interactions of political actors. For this assignment, I want you to use the information about who follows whom on Twitter as well as past tweets of the current U.S. Senate members to analyze how they interact and what they tweet about.
Data
Twitter Handles of Senators
Twitter does not allow us to search for past tweets (beyond about a week back) based on keywords, location, or topics (hashtags). However, we are able to obtain the past tweets of users if we specify their Twitter handle. The file senators_twitter.csv contains the Twitter handles of the current U.S. Senate members (obtained from UCSD library). We will focus on the Senators’ official Twitter accounts (as opposed to campaign or staff members). The data also contains information on the party affiliation of the Senators.
Followers
The file senators_follow.csv contains an edge list of connections between each pair of senators who are connected through a follower relationship (this information was obtained using the function rtweet::lookup_friendships). The file is encoded such that the source is a follower of the target. You will need to use the subset of following = TRUE to identify the connections for which the source follows the target.
Tweets by Senators
Helper Code for Twitter Data:
library(tidyverse)
library(lubridate)
library(rtweet)
# Read in the Tweets
senator_tweets <- readRDS("senator_tweets.RDS")
# How limiting is the API limit?
senator_tweets %>%
group_by(screen_name) %>%
summarize(n_tweet = n(),
oldest_tweet = min(created_at)) %>%
arrange(desc(oldest_tweet))The data contains about 280k tweets and about 90 variables. Please note, that the API limit of 3,200 tweets per twitter handle actually cuts down the time period we can observe the most prolific Twitter users in the Senate down to only about one year into the past.
Tasks for the Assignment
1. Who follows whom?
a) Network of Followers
Read in the edgelist of follower relationships from the file senators_follow.csv.
Create a directed network graph. Identify the three senators who are followed by the most of their colleagues (i.e. the highest “in-degree”) and the three senators who follow the most of their colleagues (i.e. the highest “out-degree”). [Hint: You can get this information simply from the data frame or use igraph to calculate the number of in and out connections: indegree = igraph::degree(g, mode = "in").]
Visualize the network of senators. In the visualization, highlight the party ID of the senator nodes with an appropriate color (blue = Democrat, red = Republican) and size the nodes by the centrality of the nodes to the network. Briefly comment.
library(ggraph)## Warning: package 'ggraph' was built under R version 4.0.2## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.0.2## Warning: replacing previous import 'vctrs::data_frame' by 'tibble::data_frame'
## when loading 'dplyr'library(igraph)## Warning: package 'igraph' was built under R version 4.0.2##
## Attaching package: 'igraph'## The following objects are masked from 'package:stats':
##
## decompose, spectrum## The following object is masked from 'package:base':
##
## unionlibrary(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:igraph':
##
## as_data_frame, groups, union## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionsenator_edgelist <- readr::read_csv("senators_follow.csv")## Parsed with column specification:
## cols(
## source = col_character(),
## target = col_character(),
## following = col_logical(),
## followed_by = col_logical()
## )senator_following_edgelist = senator_edgelist %>%
select(source, target, following) %>%
filter(following == T)
following = graph_from_data_frame(senator_following_edgelist, directed=T)
indegree = igraph::degree(following, mode = "in")
head(sort(indegree, decreasing = T), 3) #most followed by other senators## SenRonJohnson SenatorRomney SenatorLankford
## 93 92 91outdegree = igraph::degree(following, mode = "out")
head(sort(outdegree, decreasing = T), 3) #follows most other senators## SenatorCollins lisamurkowski ChuckGrassley
## 83 80 76#merge senate with the edgelist
# Read in the Senator Data
senate <- readr::read_csv("senators_twitter.csv")## Parsed with column specification:
## cols(
## senator = col_character(),
## twitter_handle = col_character(),
## state = col_character(),
## party = col_character()
## )head(senate)## # A tibble: 6 x 4
## senator twitter_handle state party
## <chr> <chr> <chr> <chr>
## 1 Baldwin, Tammy SenatorBaldwin WI D
## 2 Barrasso, John SenJohnBarrasso WY R
## 3 Bennet, Michael F. SenatorBennet CO D
## 4 Blackburn, Marsha MarshaBlackburn TN R
## 5 Blumenthal, Richard SenBlumenthal CT D
## 6 Blunt, Roy RoyBlunt MO Rsenate_tomerge = senate %>%
rename(
source = twitter_handle
)
senate_toplot = left_join(senator_following_edgelist, senate_tomerge, by = 'source')
head(senate_toplot)## # A tibble: 6 x 6
## source target following senator state party
## <chr> <chr> <lgl> <chr> <chr> <chr>
## 1 SenatorBaldwin SenatorBennet TRUE Baldwin, Tammy WI D
## 2 SenatorBaldwin SenBlumenthal TRUE Baldwin, Tammy WI D
## 3 SenatorBaldwin CoryBooker TRUE Baldwin, Tammy WI D
## 4 SenatorBaldwin SenSherrodBrown TRUE Baldwin, Tammy WI D
## 5 SenatorBaldwin SenatorBurr TRUE Baldwin, Tammy WI D
## 6 SenatorBaldwin SenatorCantwell TRUE Baldwin, Tammy WI Dunique(senate_toplot$party) #expect three different colors## [1] "D" "R" "I"#to get edge colors correct
senate_toplot$party <- ifelse(senate_toplot$party == "D", "blue", senate_toplot$party )
senate_toplot$party <- ifelse(senate_toplot$party == "R", "red", senate_toplot$party)
senate_toplot$party <- ifelse(senate_toplot$party == "I", "green", senate_toplot$party)
senate_toplot$party <- factor(senate_toplot$party)
unique(senate_toplot$party) #expect three different colors## [1] blue red green
## Levels: blue green red#now to get the nodes in the correct color
following_party = graph_from_data_frame(senate_toplot, directed=T)
library(tidygraph)## Warning: package 'tidygraph' was built under R version 4.0.2##
## Attaching package: 'tidygraph'## The following object is masked from 'package:igraph':
##
## groups## The following object is masked from 'package:stats':
##
## filtergraph_tbl <- following_party %>%
as_tbl_graph() %>%
activate(nodes) %>%
mutate(size = centrality_degree())
layout <- create_layout(graph_tbl, layout = 'igraph', algorithm = 'kk')
#need to re-merge because this new layour object does not have party any longer
senate_tomerge = senate %>%
rename(
name = twitter_handle
)
layout_toplot = left_join(layout, senate_tomerge, by = 'name')
cols = c("D" = "dodgerblue", "R" = "red4", "I" = "springgreen")
#now to plot
ggraph(layout_toplot) +
geom_edge_fan(aes(color = party, alpha = 0.001), show.legend = F) +
scale_edge_color_identity(guide = "legend") +
geom_node_point(aes(size = size, color = as.factor(party)), show.legend = F) +
scale_color_manual(
values = cols
) +
theme_graph(fg_text_colour = 'white') +
labs(
title = "US Senator Accounts Following Each Other on Twitter",
subtitle = "Red = Rep.; Blue = Dem.; Green = Indp."
)
This graph seems to suggest some degree of polarization, as senators often follow senators from their own party, but less so senators from another party. Independent senators more closely associated with democratic senators.
b) Communities
Now let’s see whether party identification is also recovered by an automated mechanism of cluster identification. Use the cluster_walktrap command in the igraph package to find densely connected subgraphs.
Based on the results, visualize how well this automated community detection mechanism recovers the party affiliation of senators. This visualization need not be a network graph. Comment briefly.
following_party## IGRAPH 9b7af73 DN-- 99 5674 --
## + attr: name (v/c), following (e/l), senator (e/c), state (e/c), party
## | (e/c)
## + edges from 9b7af73 (vertex names):
## [1] SenatorBaldwin->SenatorBennet SenatorBaldwin->SenBlumenthal
## [3] SenatorBaldwin->CoryBooker SenatorBaldwin->SenSherrodBrown
## [5] SenatorBaldwin->SenatorBurr SenatorBaldwin->SenatorCantwell
## [7] SenatorBaldwin->SenCapito SenatorBaldwin->SenatorCardin
## [9] SenatorBaldwin->SenatorCarper SenatorBaldwin->SenBobCasey
## [11] SenatorBaldwin->SenatorCollins SenatorBaldwin->ChrisCoons
## [13] SenatorBaldwin->JohnCornyn SenatorBaldwin->SenCortezMasto
## + ... omitted several edgeslibrary(igraph)
wc <- cluster_walktrap(following_party) # find "communities"
community_id <- wc$membership
twitter_handle <- as_ids(V(following_party))
vcom <- data.frame(twitter_handle,community_id)
senator_communities = left_join(vcom, senate, by = 'twitter_handle')
senator_communities_party <- senator_communities %>%
group_by(community_id) %>%
count(party)ggplot(senator_communities_party) +
geom_tile(aes(x = as.factor(community_id), y = party, fill=n)) +
scale_fill_gradient(low = "light blue", high = "#0072B2") +
labs(
x = "Community Group",
y = "Party",
fill = "Number of \nSenators ",
title = "Republican and Democrat-Independent Divide",
subtitle = "These inferences were made based on the fellow Senators that individual Senators follow on Twitter.",
caption = "Note: White Spaces denote that no Senators from that party belong to that Community Group."
) +
ggthemes::theme_tufte()
2. What are they tweeting about?
From now on, rely on the information from the tweets stored in senator_tweets.RDS.
a) Most Common Topics over Time
Remove all tweets that are re-tweets (is_retweet) and identify which topics the senators tweet about. Rather than a full text analysis, just use the variable hashtags and identify the most common hashtags over time. Provide a visual summary.
senator_tweets <- readRDS("senator_tweets.RDS")
unique(senator_tweets$is_retweet) #character not boolean## [1] FALSE TRUEsenator_tweets_no_retweets <- senator_tweets %>%
filter(!is_retweet == 'TRUE')
unique(senator_tweets_no_retweets$is_retweet) #subset successful## [1] FALSElength(unique(senator_tweets_no_retweets$hashtags)) #that's a lot of hastags## [1] 21875senator_tweets_no_retweets$hashtags[0:20] #tweets have more than one hashtag## [[1]]
## [1] "ThisIsMyCrew" "OpeningDay"
##
## [[2]]
## [1] NA
##
## [[3]]
## [1] "AmericanJobsPlan" "BuildBackBetter"
##
## [[4]]
## [1] "TransDayOfVisibility" "WontBeErased"
##
## [[5]]
## [1] "MaskUpWisconsin" "StopTheSpread"
##
## [[6]]
## [1] "CesarChavezDay" "SiSePuede"
##
## [[7]]
## [1] "WomensHistoryMonth"
##
## [[8]]
## [1] "AmericanRescuePlan"
##
## [[9]]
## [1] "ForThePeople"
##
## [[10]]
## [1] NA
##
## [[11]]
## [1] "VaccinateMKE" "CrushCovidMKE"
##
## [[12]]
## [1] "COVID19"
##
## [[13]]
## [1] NA
##
## [[14]]
## [1] "ForThePeople" "VotingRightsAct"
##
## [[15]]
## [1] "KeepErMovin"
##
## [[16]]
## [1] "AmericanRescuePlan"
##
## [[17]]
## [1] "StopAsianHate" "StopAAPIHate"
##
## [[18]]
## [1] "AmericanRescuePlan" "HelpIsHere"
##
## [[19]]
## [1] "AmericanRescuePlan" "MKE"
##
## [[20]]
## [1] NAlibrary(tidyr)##
## Attaching package: 'tidyr'## The following object is masked from 'package:igraph':
##
## crossingexpand_senator_tweets_no_retweets <- senator_tweets_no_retweets %>%
tidyr::separate_rows(hashtags)## Warning in .f(.x[[i]], ...): argument is not an atomic vector; coercingunique(expand_senator_tweets_no_retweets$hashtags)[0:20] #much better## [1] "c" "ThisIsMyCrew" "OpeningDay"
## [4] "" NA "AmericanJobsPlan"
## [7] "BuildBackBetter" "TransDayOfVisibility" "WontBeErased"
## [10] "MaskUpWisconsin" "StopTheSpread" "CesarChavezDay"
## [13] "SiSePuede" "WomensHistoryMonth" "AmericanRescuePlan"
## [16] "ForThePeople" "VaccinateMKE" "CrushCovidMKE"
## [19] "COVID19" "VotingRightsAct"#now for time
expand_senator_tweets_no_retweets$year <- format(as.POSIXct(expand_senator_tweets_no_retweets$created_at), "%Y")
unique(expand_senator_tweets_no_retweets$year)[0:20] #nice## [1] "2021" "2020" "2019" "2018" "2017" "2016" "2015" "2014" "2013" "2012"
## [11] "2011" "2010" "2009" NA NA NA NA NA NA NAtable(expand_senator_tweets_no_retweets$year) #definitely more from recent years##
## 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019
## 285 271 282 303 1139 2609 5826 7302 19541 33693 71055
## 2020 2021
## 123265 29354expand_senator_tweets_no_retweets$year <- ifelse(expand_senator_tweets_no_retweets$year<=2015, '2015 and Before', expand_senator_tweets_no_retweets$year)
expand_senator_tweets_no_retweets$year <- ifelse(expand_senator_tweets_no_retweets$year>=2016 & expand_senator_tweets_no_retweets$year<2018, '2016-2017', expand_senator_tweets_no_retweets$year)
expand_senator_tweets_no_retweets$year <- ifelse(expand_senator_tweets_no_retweets$year>=2018 & expand_senator_tweets_no_retweets$year<2020, '2018-2019', expand_senator_tweets_no_retweets$year)
table(expand_senator_tweets_no_retweets$year) #slightly more balanced##
## 2015 and Before 2016-2017 2018-2019 2020 2021
## 10715 26843 104748 123265 29354top_hashtags <- expand_senator_tweets_no_retweets %>%
group_by(hashtags) %>% #counting individual hashtags
count() %>%
arrange(desc(n)) %>%
head(10) #first three don't mean anything
top_hashtags_meaningful <- top_hashtags[4:10, ]
hashtags_overtime <- expand_senator_tweets_no_retweets %>%
filter(hashtags %in% top_hashtags_meaningful$hashtags) %>%
drop_na(year) %>%
ggplot(.) +
geom_bar(aes(x = hashtags, fill = year)) +
labs(
x = 'Hashtags',
y = 'Count',
title= 'US Senator Hastags on Twitter over Time'
) +
theme(legend.title = 'Time Period') +
ggthemes::theme_tufte()
hashtags_overtime
3. Are you talking to me?
Often tweets are simply public statements without addressing a specific audience. However, it is possible to interact with a specific person by adding them as a friend, becoming their follower, re-tweeting their messages, and/or mentioning them in a tweet using the @ symbol.
a) Identifying Re-Tweets
Select the set of re-tweeted messages from other senators and identify the source of the originating message. Calculate by senator the amount of re-tweets they received and from which party these re-tweets came. Essentially, I would like to visualize whether senators largely re-tweet their own party colleagues’ messages or whether there are some senators that get re-tweeted on both sides of the aisle. Visualize the result and comment briefly.
senator_tweets_retweets <- senator_tweets %>%
filter(is_retweet == 'TRUE')
#colnames(senator_tweets_retweets) #retweet_screen_name is what we want
fellow_senator_tweets_retweets <- senator_tweets_retweets %>%
filter(retweet_screen_name %in% senate$twitter_handle) #this gives us senators retweeting other senators only
fellow_senator_tweets_retweets <- fellow_senator_tweets_retweets %>%
rename(
twitter_handle = screen_name
)
fellow_senator_tweets_retweets_party <- left_join(fellow_senator_tweets_retweets, senate, by='twitter_handle')
#colnames(fellow_senator_tweets_retweets_party)
myvars <- c('twitter_handle', 'retweet_screen_name','party')
sub_fellow_senator_tweets_retweets_party <- fellow_senator_tweets_retweets_party[myvars] #dataframe is getting a little unwiedly in size
sub_fellow_senator_tweets_retweets_party <- sub_fellow_senator_tweets_retweets_party %>%
rename(
retweeter = twitter_handle,
twitter_handle = retweet_screen_name,
retweeter_party = party
)
glimpse(sub_fellow_senator_tweets_retweets_party)## Rows: 5,417
## Columns: 3
## $ retweeter <chr> "SenatorBaldwin", "SenatorBaldwin", "SenatorBaldwin",…
## $ twitter_handle <chr> "maziehirono", "SenSherrodBrown", "PattyMurray", "Mar…
## $ retweeter_party <chr> "D", "D", "D", "D", "D", "D", "D", "D", "D", "D", "D"…senator_retweeted_identity <- left_join(sub_fellow_senator_tweets_retweets_party, senate, by='twitter_handle')
glimpse(senator_retweeted_identity)## Rows: 5,417
## Columns: 6
## $ retweeter <chr> "SenatorBaldwin", "SenatorBaldwin", "SenatorBaldwin",…
## $ twitter_handle <chr> "maziehirono", "SenSherrodBrown", "PattyMurray", "Mar…
## $ retweeter_party <chr> "D", "D", "D", "D", "D", "D", "D", "D", "D", "D", "D"…
## $ senator <chr> "Hirono, Mazie K.", "Brown, Sherrod", "Murrary, Patty…
## $ state <chr> "HI", "OH", "WA", "NM", "OR", "NV", "DE", "RI", "DE",…
## $ party <chr> "D", "D", "D", "D", "D", "D", "D", "D", "D", "D", "D"…senator_retweeted_identity$senator <- senator_retweeted_identity$state <- NULL
senator_retweeted_complete <- senator_retweeted_identity %>%
rename(
retweeted = twitter_handle,
retweeted_party = party
)
#Calculate by senator the amount of re-tweets they received and from which party these re-tweets came
senators_got_retweeted <- as.data.frame(table(senator_retweeted_complete$retweeted))
senators_got_retweeted <- senators_got_retweeted %>%
rename(
retweeted = Var1
)
senators_got_retweeted_party <- left_join(senators_got_retweeted, senator_retweeted_complete, by='retweeted')
#I am not going to include Independent Senators for this question
senators_got_retweeted_party$party_lines <- ifelse(senators_got_retweeted_party$retweeter_party == 'D' & senators_got_retweeted_party$retweeted_party == 'D', 'D Retweets D', 0)
senators_got_retweeted_party$party_lines <- ifelse(senators_got_retweeted_party$retweeter_party == 'R' & senators_got_retweeted_party$retweeted_party == 'R', 'R Retweets R', senators_got_retweeted_party$party_lines)
senators_got_retweeted_party$party_lines <- ifelse(senators_got_retweeted_party$retweeter_party == 'R' & senators_got_retweeted_party$retweeted_party == 'D', 'R Retweets D', senators_got_retweeted_party$party_lines)
senators_got_retweeted_party$party_lines <- ifelse(senators_got_retweeted_party$retweeter_party == 'D' & senators_got_retweeted_party$retweeted_party == 'R', 'D Retweets R', senators_got_retweeted_party$party_lines)
glimpse(senators_got_retweeted_party)## Rows: 5,417
## Columns: 6
## $ retweeted <chr> "ChrisCoons", "ChrisCoons", "ChrisCoons", "ChrisCoons…
## $ Freq <int> 106, 106, 106, 106, 106, 106, 106, 106, 106, 106, 106…
## $ retweeter <chr> "SenatorBaldwin", "SenatorBaldwin", "SenatorBaldwin",…
## $ retweeter_party <chr> "D", "D", "D", "D", "D", "R", "R", "R", "R", "R", "D"…
## $ retweeted_party <chr> "D", "D", "D", "D", "D", "D", "D", "D", "D", "D", "D"…
## $ party_lines <chr> "D Retweets D", "D Retweets D", "D Retweets D", "D Re…retweets_senators <- senators_got_retweeted_party %>%
filter(!party_lines == 0) %>% #some party information seems to be missing
ggplot(.) +
geom_bar(aes(x=party_lines)) +
ggthemes::theme_tufte() +
labs(
x = 'Who Retweets Who',
y = 'Number of Retweets',
title = 'Senators Tend to Retweet Colleagues from their Own Party'
)
retweets_senators
It seems that senators tend to retweet colleagues from their own party; with a minority that retweet across the aisle. From a raw count, Democratic Senators tend to do this more than Republican Senators; but it could be because they are more active on Twitter.
b) Identifying Mentions
Identify the tweets in which one senator mentions another senator directly (the variable is mentions_screen_name). For this example, please remove simple re-tweets (is_retweet == FALSE). Calculate who re-tweets whom among the senate members. Convert the information to an undirected graph object in which the number of mentions is the strength of the relationship between senators. Visualize the network graph using the party identification of the senators as a group variable (use blue for Democrats and red for Republicans) and some graph centrality measure to size the nodes. Comment on what you can see from the visualization.
class(senator_tweets$mentions_screen_name)## [1] "list"unique(senator_tweets$mentions_screen_name)[20:40] #multiple mentions are possible## [[1]]
## [1] "SenStabenow" "SenBobCasey"
##
## [[2]]
## [1] "TonyEquality" "SenatorBaldwin" "repmarkpocan" "SenRonJohnson"
## [5] "RepGwenMoore"
##
## [[3]]
## [1] "cpa_tradereform"
##
## [[4]]
## [1] "BCBSProgress" "SenatorBaldwin" "SenatorBraun" "lisamurkowski"
## [5] "SenTinaSmith"
##
## [[5]]
## [1] "_ACHP" "SenatorBaldwin" "SenatorBraun" "SenTinaSmith"
## [5] "lisamurkowski"
##
## [[6]]
## [1] "rconniff" "SenatorBaldwin"
##
## [[7]]
## [1] "SenatorBraun" "lisamurkowski" "SenTinaSmith"
##
## [[8]]
## [1] "JudiciaryDems"
##
## [[9]]
## [1] "USDOL"
##
## [[10]]
## [1] "BadgerWHockey"
##
## [[11]]
## [1] "CA_PPI" "SenatorBaldwin"
##
## [[12]]
## [1] "uph_meriter" "UnityPointNews"
##
## [[13]]
## [1] "RonWyden" "ChrisVanHollen" "SenatorBennet" "SenBooker"
##
## [[14]]
## [1] "PVA1946" "PVA1946" "SenatorBaldwin"
##
## [[15]]
## [1] "340BHealth" "SenJohnThune" "SenatorBaldwin" "SenCapito"
## [5] "SenatorCardin" "senrobportman" "SenStabenow"
##
## [[16]]
## [1] "RethinkTrade" "POTUS"
##
## [[17]]
## [1] "XavierBecerra" "HHSGov"
##
## [[18]]
## [1] "PCGTW" "POTUS"
##
## [[19]]
## [1] "cpa_tradereform" "SenSherrodBrown" "SenatorBaldwin"
##
## [[20]]
## [1] "civilrightsorg" "SenatorBaldwin"
##
## [[21]]
## [1] "SenateDems" "SenatorBaldwin"expand_senator_tweets_mentions <- senator_tweets %>%
tidyr::separate_rows(mentions_screen_name) %>%
drop_na(mentions_screen_name) %>%
filter(as.character(mentions_screen_name) %in% senate$twitter_handle) #this gives us senators mentioning other senators only## Warning in .f(.x[[i]], ...): argument is not an atomic vector; coercingunique(expand_senator_tweets_mentions$mentions_screen_name)[20:40] #all good ## [1] "SenToddYoung" "ChrisMurphyCT" "PattyMurray" "MartinHeinrich"
## [5] "SenJeffMerkley" "SenCortezMasto" "ChrisCoons" "SenJackReed"
## [9] "SenatorCarper" "SenatorMenendez" "MarkWarner" "SenatorCantwell"
## [13] "SenatorTester" "SenBlumenthal" "SenatorLujan" "SenBrianSchatz"
## [17] "SenatorHick" "SenAlexPadilla" "SenWhitehouse" "SenJackyRosen"
## [21] "SenatorHassan"exp_senator_tweets_mentions <- expand_senator_tweets_mentions %>%
filter(is_retweet=='FALSE')
exp_senator_tweets_mentions <- exp_senator_tweets_mentions %>%
rename(
twitter_handle = screen_name
)
exp_senator_tweets_mentions_party <- left_join(exp_senator_tweets_mentions, senate, by='twitter_handle')
myvars <- c('twitter_handle', 'mentions_screen_name', 'party')
for_mentions_edgelist <- exp_senator_tweets_mentions_party[myvars]
for_mentions_edgelist <- for_mentions_edgelist %>%
rename(
source = twitter_handle,
target = mentions_screen_name,
mentioner_party = party
)
number_mentions <- for_mentions_edgelist %>%
group_by(source, target) %>%
count()
for_mentions_edgelist_w_number <- left_join(for_mentions_edgelist, number_mentions, by=c('source' = 'source', 'target' = 'target'))
head(for_mentions_edgelist_w_number)## # A tibble: 6 x 4
## source target mentioner_party n
## <chr> <chr> <chr> <int>
## 1 SenatorBaldwin RonWyden D 4
## 2 SenatorBaldwin maziehirono D 1
## 3 SenatorBaldwin SenDuckworth D 5
## 4 SenatorBaldwin SenStabenow D 4
## 5 SenatorBaldwin SenBobCasey D 8
## 6 SenatorBaldwin SenatorBraun D 5mentions_party <- graph_from_data_frame(for_mentions_edgelist_w_number, directed=F)
mentions_party <- igraph::simplify(mentions_party, edge.attr.comb="min")
library(tidygraph)
graph_mentions<- mentions_party %>%
as_tbl_graph() %>%
activate(nodes) %>%
mutate(size = centrality_degree())
#mentions_layout <- create_layout(graph_mentions, layout = 'igraph', algorithm = 'kk')
senate_tomerge_mentions = senate %>%
rename(
name = twitter_handle
)
mentions_layout = left_join(graph_mentions, senate_tomerge_mentions, by = 'name')
cols = c("D" = "dodgerblue", "R" = "red4", "I" = "springgreen")
#now to plot
ggraph(mentions_layout, layout = 'kk', maxiter=1000) +
geom_edge_link(aes(width = n, alpha = 0.5), show.legend = F) +
geom_node_point(aes(size = size, color = as.factor(party)), show.legend = F) +
scale_color_manual(
values = cols
) +
theme_graph(fg_text_colour = 'white', title_size = 30, subtitle_size = 20, caption_size = 20) +
labs(
title = "US Senators' Mentions of Other Senators on Twitter",
subtitle = "Red = Rep.; Blue = Dem.; Green = Indp."
) 
It seems like senators who are less central in this network also mention others less. Interestingly, senators who are less central in this network also seem to mention politicians from another party less often. There also seems to be a relatively clean grouping of senators by party, which indicates that senators tend to, more often, mention fellow senators from their own party.