R Notebook

1. First, find tweets that other people are making about your chosen person using search_tweets(), and make a table of the most popular tweets about them.

TigerWoods <- search_tweets("TigerWoods", n = 1000, include_rts = F)

Downloading [=======>---------------------------------]  20%
Downloading [===========>-----------------------------]  30%
Downloading [===============>-------------------------]  40%
Downloading [===================>---------------------]  50%
Downloading [========================>----------------]  60%
Downloading [============================>------------]  70%
Downloading [================================>--------]  80%
Downloading [====================================>----]  90%
Downloading [=========================================] 100%

TigerWoods %>% 
  select(text, retweet_count) %>%    
  top_n(25) %>%                       # get the top 25 most popular tweets
  arrange(-retweet_count) %>%         # sort in descending order of popularity
  datatable()

Selecting by retweet_count

This table shows the most popular tweets about Tiger Woods right now.

2. Next get their tweets using get_timeline(). Find which hashtags they use most and make a table.

tiger_tweets <- get_timeline("TigerWoods", n = 5000)

TigerWoods %>% 
  select(hashtags) %>%                   # Focus on the hashtags
  unnest() %>%                           # Separate multiple hashtags
  mutate(hashtags = tolower(hashtags)) %>%      # make all hashtags lowercase
  count(hashtags, sort=TRUE) %>%                # count how often they appear
  datatable()                                   # create an interactive table

`cols` is now required when using unnest().
Please use `cols = c(hashtags)`

This is a table showing what hashtags people are using about Tiger Woods.

3. Make a table of the number of tweets each day, and find the overall average number of tweets per day.

tiger_tweets %>% 
  group_by(day = date(created_at)) %>%    # extract the date, group by it
  summarize(tweets_per_day = n())         # count the number of tweets each day

This shows the tweets per day in a table.

tiger_tweets %>% 
  group_by(day = date(created_at)) %>%    # extract the date, group by it
  summarize(tweets_per_day = n()) %>% # count the number of tweets each day
  summarize(mean(tweets_per_day))

This is the average tweets per day in a table.

4. Create a plotly graphic of the number of tweets per day.

tiger_tweets %>%
  mutate(day = date(created_at)) %>% 
  plot_ly(x = ~day) %>%                                        
  add_histogram()%>%
  layout(title = "how often @TigerWoods tweets")

This graph shows the number of times that tiger tweets per day.

5. Create a table and a plotly histogram of the hour of the day that they tweet.

tz(tiger_tweets$created_at)

[1] "UTC"

kim_tweets %>% 
  mutate(time = with_tz(created_at, "America/Detroit")) %>% 
  mutate(time = hour(time)) %>% 
  count(time) %>% 
  datatable(options = (list(pageLength = 24)), rownames = F)

NA

A table showing the hour of the day that Tiger tweets at.

tiger_tweets %>% 
  mutate(time = with_tz(created_at, "America/Detroit")) %>%    # convert to Detroit time zone
  mutate(time = hour(time)) %>%                                 # extract the hour
  plot_ly(x = ~time) %>%                                        # create plotly graph
  add_histogram() %>%                                              # make histogram
layout(title = "When Does @TigerWoods Tweet?", 
         xaxis = list(title = "Time of Day (0 = midnight)"),
         yaxis = list(title = "Number of Tweets"))

NA

A graph showing the times of day that Tiger Woods tweets.

6. Create a table and a plotly histogram of the week days that they tweet.

tiger_tweets %>% 
  mutate(Day = wday(created_at,           # find the weekday that the tweet was created
                    label = T)) %>%       # use labels (Sun, Mon, etc) rather than numbers
  count(Day) %>%                          # count the number of tweets each day
  datatable(rownames = F)

NA

This table shows the days of the week that tiger tweets.

tiger_tweets %>% 
  mutate(Day = wday(created_at,           # find the weekday that the tweet was created
                    label = T)) %>%       # use labels (Sun, Mon, etc) rather than numbers
  plot_ly(x = ~Day) %>%                                        # create plotly graph
  add_histogram() %>%                                              # make histogram
layout(title = "When Does @TigerWoods Tweet?", 
         xaxis = list(title = "Days of the week"),
         yaxis = list(title = "Number of Tweets"))

NA

A histogram showing the days of the week that Tiger tweets.

7. Create a plotly heatmap of the weekday and time of day that they tweet.

tiger_tweets %>% 
  mutate(day = wday(created_at, label = T)) %>% 
  mutate(hour = hour(with_tz(created_at, "America/Detroit"))) %>% 
  plot_ly(x = ~day, y = ~hour) %>% 
  add_histogram2d(nbinsx = 7, nbinsy = 24)%>%
  layout(title = "When Does @TigerWoods Tweet?", 
         xaxis = list(title = "Days of the week"),
         yaxis = list(title = "Hour of the day (0=midnight)"))

NA

A heatmap showing the days of the week that Tiger tweets.