Word clouds give greater prominence to words that appear more frequently in any given text. They are also called tag clouds or weighted words. The significance of a word's strength in terms of its number of occurrences visually maps to the size of its appearance. In other words, the word that appears the largest in visualization is the one that has appeared the most in the text.
Beyond showing the occurrences of the words in shapes and colors, word clouds have several useful applications for social media and marketing as follows:
- Businesses could get to know their customers and how they view their products. Some organizations have used a very creative way of asking their fans or followers to post words about what that they think of their brand, taking all these words to a word cloud to understand what the most common impressions of their product brand are.
- Finding ways to know competitors by identifying a brand whose online presence is popular. Creating a word cloud from their content to better understand what words and themes hook the product target market.
In order to create a word cloud, one can write the Python code or use something that already exists. Andreas Mueller from NYU Center for Data Science created a word cloud in Python. This is pretty simple and easy to use. The RemachineScript.ttf font file can be downloaded from http://www.fonts101.com/fonts/view/Script/63827/Remachine_Script.
STOPWORDS consist of extremely common words, for example a, an, the, is, was, at, in, and many more. The following code creates a word cloud using a list of STOPWORDS in order to ignore them:
from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
from os import path
d = path.dirname("__file__")
text = open(path.join(d, '/Users/MacBook/kirthi/results.txt')).read()
wordcloud = WordCloud(
font_path='/Users/MacBook/kirthi/RemachineScript.ttf',
stopwords=STOPWORDS,
background_color='#222222',
width=1000,
height=800).generate(text)In order to plot this, first set the figure size and use imshow() that will display the word cloud as an image.
# Open a plot of the generated image.
plt.figure(figsize=(13,13))
plt.imshow(wordcloud)
plt.axis("off")
plt.show()To summarize, we will first extract the sentiments from the TextBlob example and assume that the extracted results are in results.txt. Then, we will use these words to visualize data as a word cloud with the matplotlib package.
The results of wordcloud are shown in the following image:
