Word Cloud Interpretation for Fun and Profit

That last blog posting generated some interest and I’ve been thinking more about the idea of word clouds as a possible adjunct to what we do as qualitative researchers.

Lois Kelly, who is a brilliant word-of-mouth marketer, had a very interesting comment and turned me on to psychologist James Pennebaker’s work. Pennebaker, a psychology professor at the University of Texas, has published some interesting research about his spin on content analysis. His systems counts and classifies the different types of words that people use (such as adverbs, adjectives, verbs, and even pronouns), and also catalogs them by their different emotional implications. He has published, along with co-authors, some interesting work analyzing and comparing different types of written texts and spoken words. He had even started a business from it, selling the LIWC, or Linguistic Inquiry and Word Count software program.

It is intriguing, relevant, high-end, sophisticated stuff, and I am seeing a lot of work in this area as different companies are working hard to develop software that can do sophisticated content analyses of all of the textual information contained online. Companies like netbase, AC Nielsen Buzzmetrics, Cymfony, and Motivequest are all over this emotionally-oriented, passion-and-enthusiasm content coded stuff, and for good reason. It makes good sense.

But when I was speculating about word clouds and their qualitative research usage, I was being a bit more open-ended in my ruminations. I wasn’t thinking about such well-developed systems, ones that provided you with such well though out schemata for analyzing texts.

I was thinking more about doodling. Perhaps even diddling with the doodling.

I was wondering what we could do with the simple word clouds we generate with online engines like wordle.net, which I’ve been playing around with a bit after the Latin American marketing research visionary Pablo Sanchez Kohn set me up with it in one of his online experiments.

I’ve been tooling around with it, and I like it. Why? Well, the people who post it online call it a “toy” and that’s a real insight. It’s just a lot of fun to play with it. It makes decent art, too. The pictures are nice to look at. And to think with, I think. I may frame a couple, or turn them into t-shirts. Why not?

In the play, in that visual appeal, I think there is something deeper that can happen. Because we get some good analysis packed into an at-a-glance form, I think we have opportunities to use that ultimate piece of ‘software,’ the human mind and imagination, to glean insight from these word pictures. We can run poetic comparisons on these scrambled word omelets. And then we can use them to launch creative inquiries into the text. Delving deeper using all our other tools, from content analysis word counts to hermeneutic mindful deep breathing.

A couple of examples today, and then maybe a few in the next post.

Below, I have posted a couple of recent blog pages from Brandthroposophy run through the word cloud generator at wordle.net. I think they’re fairly easy to identify. See if you recognize them.

brandthro4.jpg

That one was the recent set of postings having to do with netnographic resources. It is interesting how that big http dominates the frame; the posting is full of links. But it also captures at a glance some central meaning on the page about a community of Internet research scholars coming together to offer a list of new and different places and things to study. The cloud somehow captures all of this for me rather quickly. You get the academic content, the variety of internet forms, as well as the sense of a knowledge network that is building.

Here’s another one. Do you recognize it?

costcowordcooud3a.jpg

For that one, I took one of my favorite postings, the sad saga about my screws from Costco.com. Can you see at a glance how different these two postings are? This one tells a story about Costco, please Trudy, the screws, the wall, the chair, in March. It’s all somehow squeezed in there. And nice to look at, too.

Unfortunately, I wasn’t able to read in my entire blog, all of the entries from day one, and then construct a single word cloud from it. The software just pulled up one page or entry at a time. That’s too bad, because it would have been exciting to see what the common words have been for the 18 months or so this blog has been in existence. I wonder…

Word cloud: toy, art, or serious research tool. Why should we have to choose?

Obama’s Inaugural Speech: A New Qualitative Analysis Method?

I have been following all of the press coverage of the Obama inauguration this week. There sure has been a lot of it.

One of the most remarkable things I’ve been seeing, repeatedly, is bloggers and different newspapers carrying reports or stories that simply enter the text of Obama’s inaugural speech into a word cloud generating program. There are many such programs available on the Internet. They often also include comparisons of the speech to other word cloud generated inaugural speeches. I’ll include an example here.

Below are the word cloud versions Obama inaugural speech, followed by George W. Bush’s inaugural speech, and Clinton’s inaugural speech.

As you can see, it makes for a quite interesting contrast. It’s almost like poetry, where we are reading the most “important” words into a sort of pattern. “Nation, common people, generation America. Today work, prosperity, spirit, world.” But we can also read in complexity, and word choice. And tell something about structure, and the relationship between words as well. And this allow comparison and contrast. Why is the word America important in Obama’s speech, but not American? Why doesn’t the word “world” appear in George Bush’s speech? And so on…

obama_inaug1.jpg

bush_inaug2.jpg

clinton_inaug1.jpg

A nice, flash version, interactive word cloud that actually gives you word counts as you pass your mouse over the cloud is carried in the Toronto Star’s coverage of the Obama Inaugural word cloud. They also have some more historic speeches, like George Washington’s and Abraham Lincoln. You can see that story and those clouds here.

Now, word clouds are becoming popular modes of representation, and I can’t see why we wouldn’t start to think about them as content analysis tool to bring into our qualitative research toolkit. They allow and facilitate a certain kind of graphical representation of verbal, qualitative data that make more straightforward particular kinds of comparison (like this one).

  • So, we could compare interviews with matching culture members.
  • We could compare different blog pages or newsgroup postings.
  • We could compare archival data from the same organization over time.
  • We could compare related articles by scholars with different methodological. approaches or from different paradigms.. Or the same scholar over time.

You can see where I’m going with this…right? Somebody needs to write up a rigorous methodology for analyzing word cloud output and putting it into a qualtative data analysis framework. If it’s already been done, I’d love to see it. I’ll have some more related ideas on this soon…and some more original word clouds.

The End of Academia?

Check out this book review/article on yesterday’s New York Times Opinion blog by the famous professor Stanley Fish (famous for his work on interpretive communities and reader response theory): it’s called The Last Professor.

According to the book“The Last Professors: The Corporate University and the Fate of the Humanities,” by Frank Donoghue, reviewed by Prof. Fish, academic life as we know it is on its last legs. Universities are being run more like corporations, and the old style academics (who, apparently, are pretty damn useless with all their knowledge of dead languages) are soon going to be a thing of the past. What do we have instead? More lower-priced but highly skilled adjunct professors.

I have to say, this does look like the universities around us. Adjuncts are often excellent teachers, and they get paid a fraction what we full-time, research-active (and often research-inactive, ouch!) tenured faculty get paid.

The review seems to even hold up as some sort of an ideal the University of Phoenix, which makes no bones about the fact that it is all about getting people trained and on the job market, not educated in a broad-thinking sort of way.

I just have to wonder, along with many of those who commented eloquently and somewhat sadly (as if this was the first stage of mourning for this lost institution of learning), what is lost. The ability to think broadly and critically, to synthesize and draw connections, is not going to come from job training. And whither the Ph.D. in this brave new world of adjunct faculty?

Interesting questions for interesting times.

The thing I think Donoghue’s book misses is that these events tend not to progress in such a linear fashion. Perhaps on an individual level Universities can decline and fall, but on an institutional level I think we see a historical rise and fall. To me, that means we have feedback mechanisms. And in this case, I think that we need to look at the role and rise of the rating systems. Now that university quality is being rated, and full-time faculty, research productivity, inspired students, and turned-on recruiters are part of a university and a departments’ allure, then I think we’re going to continue to see famous departments and star professors playing a big part in the future of academia. And of business. And of society.

We’ve just seen one such instance in the way that Henry Jenkins was wooed away from MIT to USC’s Annenberg School. That’s not the rise of the adjunct system. That’s concrete evidence that high-level academic thinkers have more value than ever.

Don’t count the big thinkers out yet. We need them now, more than ever.