In this chapter, you'll learn the basics of using the bag-of-words method for analyzing text data.

What is text mining?

Understanding text mining

Quick taste of text mining

Getting started

Load some text

Make the vector a VCorpus object (1)

Make the vector a VCorpus object (2)

Make a VCorpus from a data frame

Cleaning and preprocessing text

Common cleaning functions from tm

Cleaning with qdap

All about stop words

Intro to word stemming and stem completion

Word stemming and stem completion on a sentence

Apply preprocessing steps to a corpus

The TDM & DTM

Understanding TDM and DTM

Make a document-term matrix

Make a term-document matrix

Jumping into Text Mining with Bag-of-Words

This chapter will teach you how to visualize text data in a way that's both informative and engaging.

Common text mining visuals

Test your understanding of text mining

Frequent terms with tm

Frequent terms with qdap

Intro to word clouds

A simple word cloud

Stop words and word clouds

Plot the better word cloud

Improve word cloud colors

Use prebuilt color palettes

Other word clouds and word networks

Find common words

Visualize common words

Visualize dissimilar words

Polarized tag cloud

Visualize word networks

Teaser: simple word clustering

Word Clouds and More Interesting Visuals

In this chapter, you'll learn more basic text mining techniques based on the bag of words method.

Raggruppamento semplice di parole

Metti alla prova la tua comprensione del text mining

Matrice delle distanze e dendrogramma

Crea una TDM adatta al dendrogramma

Metti tutto insieme: un dendrogramma basato sul testo

Estetica del dendrogramma

Usare le associazioni tra parole

Oltre le singole parole

Tokenizzazione con n-gram

Modificare gli n-gram

Come influenzano i bigrammi le word cloud?

Criteri di frequenza diversi

Modificare i pesi di frequenza

Acquisire i metadati in tm

Adding to Your TM Skills

This chapter ties everything together with a case study in text mining for HR analytics.

Amazon vs. Google

Organizing a text mining project

Step 1: Problem definition

Step 2: Identifying the text sources

Step 3: Text organization

Text organization

Working with Google reviews

Steps 4 & 5: Feature extraction & analysis

Feature extraction & analysis: amzn_pros

Feature extraction & analysis: amzn_cons

amzn_cons dendrogram

Word association

Quick review of Google reviews

Cage match! Amazon vs. Google pro reviews

Cage match, part 2! Negative reviews

Step 6: Reach a conclusion

Draw conclusions, insights, or recommendations

Draw another conclusion, insight, or recommendation

Finished!

Battle of the Tech Giants for Talent

Coffee tweets

Chardonnay tweets

Anonymous online reviews: Amazon

Anonymous online reviews: Google

Si stima che oltre il 70% delle informazioni aziendali potenzialmente utilizzabili sia non strutturato, spesso sotto forma di dati testuali. Il text mining offre un insieme di tecniche per ricavare insight azionabili dai dati non strutturati. In questo corso, esploreremo le basi del text mining usando il metodo bag-of-words. I primi tre capitoli presentano vari argomenti essenziali per analizzare e visualizzare dati testuali. L'ultimo capitolo ti permette di applicare tutto ciò che hai imparato in un case study reale, per estrarre insight dalle recensioni dei dipendenti di due grandi aziende tech.

Intermediate R

Scopri le basi del text mining con il metodo bag of words e altri temi essenziali per analizzare dati in R.

Text mining con Bag-of-Words in R

Impara la tecnica del bag of words per il text mining con R.

Estrazione del testo in R

Tokenizzazione con n-gram

Text mining con Bag-of-Words in R

Esercizio pratico interattivo