Dan Goldstein sends along this bit of research, distinguishing terms used in two different subfields of psychology. Dan writes:
Intuitive calls included not listing words that don’t occur 3 or more times in both programs. I [Dan] did this because when I looked at the results, those cases tended to be proper names or arbitrary things like header or footer text. It also narrowed down the space of words to inspect, which means I could actually get the thing done in my copious free time.
I think the bar graphs are kinda ugly, maybe there’s a better way to do it based on classifying the words according to content? Also the whole exercise would gain a new dimension by comparing several areas instead of just two. Maybe that’s coming next.
But, the scale is deceiving. Apparently, SJDM is just more wordy than SPSP. There needs to be a re-scaling of one of the paradigms or SJDM will always be more likely to use any concept.
Andrew –
"I think the bar graphs are kinda ugly"
You seem to dislike grouped bars. Perhaps the solution is the same as in the other post: Replace the bars with differently colored lines.
"maybe there's a better way to do it based on classifying the words according to content?"
Maybe, but if this thing gets any more subjective it'll become an art project.
"Also the whole exercise would gain a new dimension by comparing several areas instead of just two."
Right now, I can show the tails of the distribution where the absolute rate difference between two fields is largest. But if I had four academic fields … hmm … need to think about that one.
Rodney – Those are rates reflecting what fraction of the conference program each word makes up. It's completely resistant to how wordy each field is.
In addition, there's not much difference in rates. For both fields, the favored words are used about 1.5 times per 10k on the median.
Yes, I see now. But, you have to look at both graphs to make that judgment. If you focus on just one of the graphs at a time, it looks biased. Perhaps one big graph with all of the concepts would prevent data "poaching". Thanks.