WELCOME TO ENGLISH 109H!

I'm Dr. Mary Bell, and I'm your instructor for this course. I will conduct course communication via this blog. Please check daily! mebell@email.arizona.edu

Wednesday, September 30, 2015

For Fun: Word Cloud from your Unit One Reflections

I made this word cloud last night from several of your posted reflections on Unit One. I used worditout.com to produce it.
Word cloud of Unit One reflections by ENG 109H students. Created in worditout.com. 

Word Clouds can be a useful way to see what the most frequently-used words are in a text or group of texts. The program counts the frequencies of each word in a group of texts, usually skipping over common words such as prepositions (you can give it a "stoplist" to tell it what words to skip). The program then sorts the resulting words from most to least frequent. You can give the program a threshold over which you consider the frequency significant (in this example, freq >= 3), and then choose the number of words over that threshold to display (in this example, 30). The program displays the word frequencies in a cloud, with bigger words being the most frequent, and smaller words being less frequent. Usually the colors are used to help set the sizes apart as well. Notice that Green is the color for the largest font, and only one word, "writing," is in that size font. The next most frequent words are in teal, then the next in navy blue, then dark purple, then light purple.

Don't make the mistake of assuming that the most frequent words are the most important, although there are more sophisticated algorithms for word cloud computation that can provide more nuanced results. But even a simple word frequency count can provide some interesting insights, and I think it can be a useful visualization tool for exploring texts.

No comments:

Post a Comment