Comments on: Blog Analysis Tools: Not Quite Ready for Prime Time

By: Daniel Tunkelang

Daniel Tunkelang — Sun, 07 Dec 2008 03:56:40 +0000

Come to think of it, I’ve never found a blog that GenderAnalyzer believes to be published by a female.

By: Erica Naone

Erica Naone — Wed, 03 Dec 2008 21:38:57 +0000

I’m always a little slow getting through the feed reader, but I just saw this. I tried GenderAnalyzer on my mostly blog (which is mostly about literature), and it declared it was highly likely the blog was written by a male — doesn’t appear to be just science and technology that confuses it. TypeAnalyzer was wildly off for me as well. I test INFJ, but my blog came up ISTP.

By: Daniel Tunkelang

Daniel Tunkelang — Wed, 26 Nov 2008 14:40:41 +0000

Are you suggesting I should remove remove Chief Scientologist from my business cards?

Seriously, we’ve been doing a lot of work with clarity (a concept related to “query clarity”) at Endeca, so it’s been hard for me to resist the Scientology jokes. Xenu saves!

By: Jason Adams

Jason Adams — Wed, 26 Nov 2008 14:34:18 +0000

Touché! Those come with a little more extra baggage than I’m prepared to deal with. No free lunch and all..

By: Daniel Tunkelang

Daniel Tunkelang — Wed, 26 Nov 2008 14:15:19 +0000

Hey, if you want a free personality test, there’s always the Scientologists. Though the E-meter costs extra.

http://en.wikipedia.org/wiki/Oxford_Capacity_Analysis

http://en.wikipedia.org/wiki/E-meter

By: Jason Adams

Jason Adams — Wed, 26 Nov 2008 13:55:41 +0000

I come down on the side of fun for this kind of thing. Yeah most of these things are unscientific and are the intellectual equivalent of peanut brittle blah blah blah, but it amuses me to speculate on just how they are coming to their conclusions. In the case of Typealyzer, it also pointed me to uClassify, which has been interesting to play with. Win-win. And I just like the idea of a classifier sitting in the cloud that you can call through an API.

Btw, my blog came up as ISTP, though I consistently test as INTP. Not too far off! I wonder if they do 16-way classification or if they combine 4 classifiers — one for each attribute. Or something else. Seems like the combine of 4 would be better for dealing with sparsity.

By: Daniel Tunkelang

Daniel Tunkelang — Wed, 26 Nov 2008 04:23:20 +0000

BTW: Breanne’s comment was posted at 11:07pm. I finally adjusted my blog to account for the time change a few weeks ago, but time stamps aren’t adjusted retroactively.

By: Daniel Tunkelang

Daniel Tunkelang — Wed, 26 Nov 2008 04:22:29 +0000

Well, I see that you do agree they’re good for entertainment. To be clear I was inspired to check these sites out because there is a lot of discussion about applying text mining to blogs. And some serious work too, e.g., http://www.hongqu.com/publications/Blog_Classification_NLP.pdf

By: Breanne

Breanne — Wed, 26 Nov 2008 04:07:49 +0000

Those sites are total junk. I wrote a blog specifically about how bad Typealyzer is: http://www.thembtiblog.com/2008/11/websites-that-ruin-my-day.html