La potenza dei dati di Twitter

Il volume e la velocità dei tweet pubblicati su Twitter ogni secondo sono un indicatore della potenza dei dati di Twitter.

La quantità enorme di informazioni disponibili, dal testo del tweet ai relativi metadati, offre un grande potenziale per analizzare i tweet estratti e ricavarne insight.

Estrai un campione casuale dell’1% di tweet in tempo reale usando stream_tweets() per una finestra di 120 secondi e salvalo in un data frame.

Le dimensioni del data frame ti daranno indicazioni sul numero di tweet live estratti e sul numero di colonne che contengono il testo effettivo dei tweet e i metadati dei tweet.

Questo esercizio fa parte del corso

Analisi dei dati dei social media in R

Visualizza il corso

Istruzioni dell'esercizio

Estrai tweet live per una finestra temporale di 120 secondi.
Visualizza le dimensioni del data frame con i tweet estratti.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Extract live tweets for 120 seconds window
tweets120s <- stream_tweets("", timeout = ___)

# View dimensions of the data frame with live tweets
dim(___)

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Analisi dei dati dei social media in R

IntermediárioNível de habilidade

4.9+

Inizia il corso gratis

Get started with understanding the power of Twitter data and what you can achieve using social media analysis. In this chapter, you’ll extract your first set of tweets using the Twitter API and functions from the powerful ‘rtweet’ library. Then it’s time to explore how you can use the components from your extracted Twitter data to derive insights for social media analysis.

Exercise 1: Analizzare i dati di Twitter Exercise 2: La potenza dei dati di Twitter

Esercizio in corso

Exercise 3: Pro e contro dei dati di Twitter Exercise 4: Estrazione dei dati da Twitter Exercise 5: Prerequisiti per configurare l'ambiente R Exercise 6: Cerca ed estrai tweet Exercise 7: Cerca ed estrai le timeline Exercise 8: Componenti dei dati di Twitter Exercise 9: Interesse degli utenti e conteggio dei tweet Exercise 10: Confronta il numero di follower Exercise 11: Conteggi dei retweet

It’s time to go deeper. Learn how you can apply filters to tweets and analyze Twitter user data using the golden ratio and the Twitter lists they subscribe to. You’ll also learn how to extract trending topics and analyze Twitter data over time to identify interesting insights.

Exercise 1: Filtering tweets Exercise 2: Filtering for original tweets Exercise 3: Filtering on tweet language Exercise 4: Filter based on tweet popularity Exercise 5: Twitter user analysis Exercise 6: Extract user information Exercise 7: Explore users based on the golden ratio Exercise 8: Subscribers to twitter lists Exercise 9: Twitter trends Exercise 10: Available trends Exercise 11: Trends by country name Exercise 12: Trends by city and most tweeted trends Exercise 13: Plotting twitter data over time Exercise 14: Visualizing frequency of tweets Exercise 15: Create time series objects Exercise 16: Compare tweet frequencies for two brands

A picture is worth a thousand words! In this chapter, you’ll discover how you can visualize text from tweets using bar plots and word clouds. You’ll learn how to process tweet text and prepare a clean text corpus for analysis. Imagine being able to extract key discussion topics and people's perceptions about a subject or brand from the tweets they are sharing. You’ll be able to do just that using topic modeling and sentiment analysis.

Exercise 1: Processing twitter text Exercise 2: Remove URLs and characters other than letters Exercise 3: Build a corpus and convert to lowercase Exercise 4: Remove stop words and additional spaces Exercise 5: Visualize popular terms Exercise 6: Removing custom stop words Exercise 7: Visualize popular terms with bar plots Exercise 8: Word clouds for visualization Exercise 9: Topic modeling of tweets Exercise 10: The LDA algorithm Exercise 11: Create a document term matrix Exercise 12: Create a topic model Exercise 13: Twitter sentiment analysis Exercise 14: Extract sentiment scores Exercise 15: Perform sentiment analysis

Twitter users tweet, like, follow, and retweet creating complex network structures. In this final chapter, you’ll learn how to analyze these network structures and visualize the relationships between these individual people as a retweet network. By extracting geolocation data from the tweets you’ll also discover how to display tweet locations on a map, and answer powerful questions such as which states or countries are talking about your brand the most? Geographic data adds a new dimension to your Twitter data analysis.

Exercise 1: Twitter network analysis Exercise 2: Preparing data for a retweet network Exercise 3: Create a retweet network Exercise 4: Network centrality measures Exercise 5: Calculate out-degree scores Exercise 6: Compute the in-degree scores Exercise 7: Calculate the betweenness scores Exercise 8: Visualizing twitter networks Exercise 9: Create a network plot with attributes Exercise 10: Network plot based on centrality measure Exercise 11: Follower count to enhance the network plot Exercise 12: Putting twitter data on the map Exercise 13: Extract geolocation coordinates Exercise 14: Twitter data on the map Exercise 15: Course wrap-up