R Studio - R Language - Analyse Tweet
$30-250 AUD
S-au achitat serviciile după ce au fost prestate
Report on Joe Rogan - @joerogan
8.3 Identifying the topics in the cluster
(4 marks: 1+2+1) The Public Figure wants to be aware of the content of the most common topic. We do not want to present all tweets to them, so we must identify what is common in tweets. They also want you to examine the language used in these tweets and would like to have a general idea about what people are talking about.
We should analyse the most populated cluster that you found in the previous question.
12. Draw a word cloud of the words in the cluster.
13. Create the dendrogram of the words in the cluster and plot it. You do not need to visualize all words in the cluster in your dendrogram, set up appropriate boundaries to improve your visualization. Make sure your visualization is readable!
14. Interpret your findings. What are the common themes/topics in the cluster?
8.4 Building Networks
(7 marks: 1+1+3+1+1) In this section, we want to create an outlook of the Public Figure’s Twitter network. To perform this:
15. Find the most popular (who have the highest number of followers) 20 friends of the chosen Twitter handle.
16. Get the number of tweets they posted (statusesCount) and save it to use in the next question.
17. Obtain a 1.5-degree egocentric graph centred around the chosen Twitter handle. The vertex size of each vertex should be proportional to each user's statusesCount (do not forget to add the statuses count of the chosen Twitter handle to this list in this step). Note that you should check whether these 21 people are following each other to create a degree 1.5 egocentric graph.
Hint: You may prefer to use the lookup_friendships() function from the rtweet library.
18. Compute the centrality of each vertex using betweenness centrality. List the top 3 most central people in your graph.
19. Comment on your results.
ID Proiect: #31774771