Get Ronaldo’s tweets timeline

Due to limitations of twitter new policy, we can only retrieve last 3200 tweets of a user. In our case, as of writing this article his total tweets are just 3733. So we are covering most of his twitter journey here.

Ronaldo <- get_timeline("@cristiano", n= 3200)

Plotting tweets per months over the time period

As the first user case lets see how he tweets over these years.

ggplot(data = Ronaldo,
       aes(month(created_at, label=TRUE, abbr=TRUE),
           group=factor(year(created_at)), color=factor(year(created_at))))+
  geom_line(stat= "count") +
  geom_point(stat="count") +
  labs(x="Month", colour="Year", xlab = "Month", ylab = "Number of tweets",
       title = "Cristiano Ronaldo's tweets over the time period", 
       caption = "Created by Arun Gopinath") +
  theme_minimal()

It’s quite difficult to obtain a trend here. But one thing is sure, his interest in twitter is just fading away.

ggplot(data = Ronaldo, aes(x = year(created_at))) +
  geom_bar(aes(fill = ..count..)) +
  xlab("Year") + ylab("Number of tweets") + 
  labs(title = "Cristiano Ronaldo's tweets over the time period", 
       subtitle = "2013 & 2014 been his prime time in twitter",
       caption = "Created by Arun Gopinath")+
  scale_x_continuous (breaks = c(2010:2021)) +
  theme_minimal() +
  scale_fill_gradient(low = "yellow", high = "darkgreen")

What about Hashtags frequency ?

What are the top 10 hashtags he tweeted ?

Ronaldo %>% 
  unnest_tokens(hashtag, text, "tweets", to_lower = FALSE) %>%
  filter(str_detect(hashtag, "^#")) %>%
  count(hashtag, sort = TRUE) %>%
  top_n(10) %>% 
  ggplot(aes(x = reorder(hashtag, -n), y =n))+
  geom_segment( aes(xend=hashtag, yend=0)) +
  geom_point( size=4, color="red") +
  theme_bw() +
  ylab("Count")+
  xlab("Hashtags")+
  labs(title = "Cristiano Ronaldo's top 10 twitter #hashtags", 
       subtitle = "",
       caption = "Created by Arun Gopinath")+
  coord_flip()

Most of them are sports related, especially about teams he represented and his personal milestones.

Most retweeted tweet

Which tweet is the most retweeted tweet ?

Ronaldo %>% 
  arrange(-retweet_count) %>%
  slice(1) %>% 
  select(created_at, screen_name, text, retweet_count, status_id)

So happy to be able to hold the two new loves of my life 🙏❤ pic.twitter.com/FIY11aWQm9

— Cristiano Ronaldo (@Cristiano) June 29, 2017

Most liked tweet

Ronaldo %>% 
  arrange(-favorite_count) %>%
  top_n(5, favorite_count) %>% 
  select(created_at, screen_name, text, favorite_count)

So sad to hear the heartbreaking news of the deaths of Kobe and his daughter Gianna. Kobe was a true legend and inspiration to so many. Sending my condolences to his family and friends and the families of all who lost their lives in the crash. RIP Legend💔 pic.twitter.com/qKb3oiDHxH

— Cristiano Ronaldo (@Cristiano) January 26, 2020

Top mentions

Ronaldo %>% 
  unnest_tokens(mentions, text, "tweets", to_lower = FALSE) %>%
  filter(str_detect(mentions, "^@")) %>%  
  count(mentions, sort = TRUE) %>%
  top_n(10)

## # A tibble: 10 x 2
##    mentions             n
##    <chr>            <int>
##  1 @Cristiano         177
##  2 @nikefootball       54
##  3 @GAMEbyRonaldo      37
##  4 @realmadrid         25
##  5 @VivaRonaldo        25
##  6 @cristiano          18
##  7 @TAGHeuer           17
##  8 @Herbalife          16
##  9 @SavetheChildren    16
## 10 @HeadsUp            13

Find top words

Here we want to remove white spaces, symbols, signs etc. Also remove stop words, words which are frequently used by everyone, from the list.And finally sort it ¹.

words <- Ronaldo %>%
  mutate(text = str_remove_all(text, "&amp;|&lt;|&gt;"),
         text = str_remove_all(text, "\\s?(f|ht)(tp)(s?)(://)([^\\.]*)[\\.|/](\\S*)"),
         text = str_remove_all(text, "[^\x01-\x7F]")) %>% 
  unnest_tokens(word, text, token = "tweets") %>%
  filter(!word %in% stop_words$word,
         !word %in% str_remove_all(stop_words$word, "'"),
         str_detect(word, "[a-z]"),
         !str_detect(word, "^#"),         
         !str_detect(word, "@\\S+")) %>%
  count(word, sort = TRUE)

set.seed(1234)

words %>% 
  with(wordcloud(word, n, random.order = FALSE, max.words = 150, 
                 scale=c(2.6,0.25),colors=brewer.pal(8, "Dark2")))

Sentiment analysis

Sentiment analysis (or opinion mining) is a natural language processing (NLP) technique used to determine whether data is positive, negative or neutral. Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs².

Here we analyse 10 emotions from positive to disgust.

• First convert text to ASCII to tackle strange characters like what we done above.

tweet_text <- iconv(words, from="UTF-8", to="ASCII", sub="")

• Since we are playing with tweets of Ronaldo ignore retweets.

Tweet_text <- gsub("(RT|via)((?:\\b\\w*@\\w+)+)","",tweet_text)

• Also remove mentions

Tweet_text <- gsub("@\\w+","",tweet_text)

• Get sentiment score using ‘get_nrc_sentiment’ function.

Ron_sentiment <- get_nrc_sentiment((tweet_text))

• To display it in ggplot we want to convert it into a data frame.

Sentimentscores <- data.frame(colSums(Ron_sentiment[,]))

• For better understanding of data frame better headers are assigned.

names(Sentimentscores) <- "Score"
Sentimentscores <- cbind("sentiment"=rownames(Sentimentscores),Sentimentscores)
rownames(Sentimentscores) <- NULL

Sentiment plot

Finally our sentiment plot of Cristiano Ronaldo’s tweets ³.

ggplot(data=Sentimentscores,aes(x=sentiment,y=Score))+
  geom_bar(aes(fill=sentiment),stat = "identity")+
  theme(legend.position="none")+
  xlab("Sentiments")+ylab("Scores")+
  labs(title = "Total sentiment of Cristiano Ronaldo's tweets based on scores",
       subtitle = "Positive vibes")+
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

• Positive vibes overall.