AV Delivery

AV Delivery

setwd("/Users/subasishdas1/Desktop/tweets/tweets2/02")
library(readxl)
dat= read_excel("autonomous_delivery.xlsx")
dat=head(dat, 200)

library(tidyverse)    

clean_tweets <- function(x) {
  x %>%
    str_remove_all(" ?(f|ht)(tp)(s?)(://)(.*)[.|/](.*)") %>%
    str_replace_all("&amp;", "and") %>%
    str_remove_all("[[:punct:]]") %>%
    str_remove_all("^RT:? ") %>%
    str_remove_all("@[[:alnum:]]+") %>%
    str_remove_all("#[[:alnum:]]+") %>%
    str_remove_all("pictwittercom") %>%
    str_replace_all("\\\n", " ") %>%
    str_to_lower() %>%
    str_trim("both")
}

dat$tweet1= dat$tweet %>% clean_tweets
dat$hashtags1= dat$hashtags %>% clean_tweets
library(qdapRegex)
dat$mentions2= dat$mentions %>% clean_tweets
dat$mentions3=stringr::str_extract_all(dat$mentions2, regex("(?<=screenname\\s)[:alpha:]*\\b"))


names(dat)

##  [1] "id"              "conversation_id" "created_at"      "date"           
##  [5] "time"            "timezone"        "user_id"         "username"       
##  [9] "name"            "place"           "tweet"           "language"       
## [13] "mentions"        "urls"            "photos"          "replies_count"  
## [17] "retweets_count"  "likes_count"     "hashtags"        "cashtags"       
## [21] "link"            "retweet"         "quote_url"       "video"          
## [25] "thumbnail"       "near"            "geo"             "source"         
## [29] "user_rt_id"      "user_rt"         "retweet_id"      "reply_to"       
## [33] "retweet_date"    "translate"       "trans_src"       "trans_dest"     
## [37] "tweet1"          "hashtags1"       "mentions2"       "mentions3"

library(igraph)
library(hrbrthemes)
library(ggraph)
library(tidyverse)

filter(dat, retweets_count > 0) %>% 
  select(username, mentions3) %>%
  unnest(mentions3) %>% 
  filter(!is.na(mentions3)) %>% 
  graph_from_data_frame() -> rt_g

V(rt_g)$node_label <- unname(ifelse(degree(rt_g)[V(rt_g)] > 2, names(V(rt_g)), "")) 
V(rt_g)$node_size <- unname(ifelse(degree(rt_g)[V(rt_g)] > 2, degree(rt_g), 0)) 


ggraph(rt_g, layout = 'linear', circular = TRUE) + 
  geom_edge_arc(edge_width=0.125, aes(alpha=..index..)) +
  geom_node_label(aes(label=node_label, size=node_size),
                  label.size=0, fill="#ffffff66", segment.colour="springgreen",
                  color="slateblue", repel=TRUE, fontface="bold") +
  coord_fixed() +theme_bw()+
  theme(axis.title=element_blank(),
        axis.text=element_blank(),
        axis.ticks=element_blank())+
  scale_size_area(trans="sqrt") +
  theme(legend.position="none")

library(tidytext)
dat$hashtags1= dat$hashtags %>% clean_tweets

str(dat)

## tibble [200 × 40] (S3: tbl_df/tbl/data.frame)
##  $ id             : num [1:200] 1.34e+18 1.34e+18 1.34e+18 1.34e+18 1.34e+18 ...
##  $ conversation_id: num [1:200] 1.34e+18 1.34e+18 1.34e+18 1.34e+18 1.34e+18 ...
##  $ created_at     : chr [1:200] "2020-12-12 17:21:11 CST" "2020-12-12 16:54:24 CST" "2020-12-12 08:41:42 CST" "2020-12-12 04:59:35 CST" ...
##  $ date           : POSIXct[1:200], format: "2020-12-12" "2020-12-12" ...
##  $ time           : POSIXct[1:200], format: "1899-12-31 17:21:11" "1899-12-31 16:54:24" ...
##  $ timezone       : num [1:200] -600 -600 -600 -600 -600 -600 -600 -600 -600 -600 ...
##  $ user_id        : num [1:200] 9.97e+17 4.83e+07 1.01e+18 2.89e+09 9.58e+17 ...
##  $ username       : chr [1:200] "smythekin" "tombamonte" "idugrp" "kellyalspals" ...
##  $ name           : chr [1:200] "Michael Ekin Smyth" "Thomas Bamonte" "IDU GROUP" "chris kelly" ...
##  $ place          : chr [1:200] NA NA NA NA ...
##  $ tweet          : chr [1:200] "@stevol321 Autonomous delivery vehicles are now allowed in San Francisco. Lidar, a form of radar, allows them t"| __truncated__ ".@RefractionAI, the robotics startup in Ann Arbor and creator of the REV-1, a lightweight autonomous delivery r"| __truncated__ "IDU will be participating in the virtual Technology and Smart Cities Trade Mission to Saudi Arabia through the "| __truncated__ "love this.     Pennsylvania legalizes autonomous delivery robots, classifies them as pedestrians  https://t.co/aGw2i76eFY" ...
##  $ language       : chr [1:200] "en" "en" "en" "en" ...
##  $ mentions       : chr [1:200] "[]" "[{'screen_name': 'refractionai', 'name': 'refraction ai', 'id': '1145761720171974656'}, {'screen_name': 'dbusin"| __truncated__ "[]" "[]" ...
##  $ urls           : chr [1:200] "[]" "['https://www.dbusiness.com/people/refraction-al-announces-luke-schneider-as-ceo/']" "[]" "['https://www.pghcitypaper.com/pittsburgh/pennsylvania-legalizes-autonomous-delivery-robots-classifies-them-as-"| __truncated__ ...
##  $ photos         : chr [1:200] "[]" "[]" "['https://pbs.twimg.com/media/EpC2WydW8AABbLT.jpg']" "[]" ...
##  $ replies_count  : num [1:200] 1 0 0 0 0 0 0 0 0 1 ...
##  $ retweets_count : num [1:200] 0 0 0 0 0 0 0 0 0 0 ...
##  $ likes_count    : num [1:200] 0 0 1 0 1 0 0 0 0 1 ...
##  $ hashtags       : chr [1:200] "[]" "[]" "[]" "[]" ...
##  $ cashtags       : chr [1:200] "[]" "[]" "[]" "[]" ...
##  $ link           : chr [1:200] "https://twitter.com/SmythEkin/status/1337900332911759360" "https://twitter.com/TomBamonte/status/1337893593755901957" "https://twitter.com/IDUGRP/status/1337769602034622465" "https://twitter.com/KellyAlspals/status/1337713706482823170" ...
##  $ retweet        : logi [1:200] FALSE FALSE FALSE FALSE FALSE FALSE ...
##  $ quote_url      : chr [1:200] NA NA NA NA ...
##  $ video          : num [1:200] 0 0 1 0 0 0 1 0 0 0 ...
##  $ thumbnail      : chr [1:200] NA NA "https://pbs.twimg.com/media/EpC2WydW8AABbLT.jpg" NA ...
##  $ near           : logi [1:200] NA NA NA NA NA NA ...
##  $ geo            : logi [1:200] NA NA NA NA NA NA ...
##  $ source         : logi [1:200] NA NA NA NA NA NA ...
##  $ user_rt_id     : logi [1:200] NA NA NA NA NA NA ...
##  $ user_rt        : logi [1:200] NA NA NA NA NA NA ...
##  $ retweet_id     : logi [1:200] NA NA NA NA NA NA ...
##  $ reply_to       : chr [1:200] "[{'screen_name': 'stevol321', 'name': 'truthdriver', 'id': '811826520'}]" "[]" "[]" "[]" ...
##  $ retweet_date   : logi [1:200] NA NA NA NA NA NA ...
##  $ translate      : logi [1:200] NA NA NA NA NA NA ...
##  $ trans_src      : logi [1:200] NA NA NA NA NA NA ...
##  $ trans_dest     : logi [1:200] NA NA NA NA NA NA ...
##  $ tweet1         : chr [1:200] "stevol321 autonomous delivery vehicles are now allowed in san francisco lidar a form of radar allows them to se"| __truncated__ "refractionai the robotics startup in ann arbor and creator of the rev1 a lightweight autonomous delivery robot "| __truncated__ "idu will be participating in the virtual technology and smart cities trade mission to saudi arabia through the "| __truncated__ "love this     pennsylvania legalizes autonomous delivery robots classifies them as pedestrians" ...
##  $ hashtags1      : chr [1:200] "" "" "" "" ...
##  $ mentions2      : chr [1:200] "" "screenname refractionai name refraction ai id 1145761720171974656 screenname dbusiness name dbusiness magazine id 21400091" "" "" ...
##  $ mentions3      :List of 200
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "refractionai" "dbusiness"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr "intengineering"
##   ..$ : chr [1:12] "selfdrivingvehi" "andyfitze" "jenstirrup" "fisheyeboxindia" ...
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "ford" "argoai"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:12] "" "fmfrancoise" "haroldsinnott" "joshinishadblog" ...
##   ..$ : chr "walmart"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "educationfund" "ford"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:5] "mohuaindia" "utmohua" "smartcitieshua" "cdiaasia" ...
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "ryandeto" "pghcitypaper"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "cruise" "walmart"
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "gatikai" "loblawco"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "wrapify" "kiwicampus"
##   ..$ : chr "intengineering"
##   ..$ : chr "elonmusk"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr "driverlessnow"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr [1:2] "unmannedlife" "oxfordshirecc"
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr ""
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   ..$ : chr(0) 
##   .. [list output truncated]

set1 <- dat %>%
  unnest_tokens(word, hashtags1)
data(stop_words)

set1  <- set1  %>%
  anti_join(stop_words)

set2= set1  %>%
  count(word, sort = TRUE)

library(DT)
datatable(set2)

dat$mentions4= dat$mentions3 %>% clean_tweets
names(dat)

##  [1] "id"              "conversation_id" "created_at"      "date"           
##  [5] "time"            "timezone"        "user_id"         "username"       
##  [9] "name"            "place"           "tweet"           "language"       
## [13] "mentions"        "urls"            "photos"          "replies_count"  
## [17] "retweets_count"  "likes_count"     "hashtags"        "cashtags"       
## [21] "link"            "retweet"         "quote_url"       "video"          
## [25] "thumbnail"       "near"            "geo"             "source"         
## [29] "user_rt_id"      "user_rt"         "retweet_id"      "reply_to"       
## [33] "retweet_date"    "translate"       "trans_src"       "trans_dest"     
## [37] "tweet1"          "hashtags1"       "mentions2"       "mentions3"      
## [41] "mentions4"

dat1= dat[, c(8, 41)]
net <- dat1 %>% 
  group_by(mentions4) %>% 
  mutate(count = n()) %>% 
  ungroup() %>% 
  filter(count > 1)
library(tidygraph)

net1= subset(net, mentions4!="character0")
glimpse(net1)

## Rows: 10
## Columns: 3
## $ username  <chr> "ieeefuturedir", "vincentsuppe", "vision_asset", "kitmuelle…
## $ mentions4 <chr> "intengineering", "cryandeto pghcitypaper", "intengineering…
## $ count     <int> 2, 2, 2, 2, 4, 4, 2, 2, 4, 4

g2 <- net1 %>% 
  select(username, mentions4) %>%  # drop the count column
  as_tbl_graph(directed = F) %>%  # make undirected
  activate(nodes) %>% 
  mutate(centrality = centrality_betweenness())
g2

## # A tbl_graph: 12 nodes and 10 edges
## #
## # An undirected multigraph with 4 components
## #
## # Node Data: 12 x 2 (active)
##   name            centrality
##   <chr>                <dbl>
## 1 ieeefuturedir            0
## 2 vincentsuppe             0
## 3 vision_asset             0
## 4 kitmueller               0
## 5 quantumbusicomm          0
## 6 business_ai              0
## # … with 6 more rows
## #
## # Edge Data: 10 x 2
##    from    to
##   <int> <int>
## 1     1     9
## 2     2    10
## 3     3     9
## # … with 7 more rows

ggraph(g2) +
  geom_edge_link() +
  geom_node_point(aes(size = centrality, colour = centrality)) +
  theme_graph()