[Air-l] counting google hits

[Thomas Koenig]

Citeren Barry Wellman <wellman at chass.utoronto.ca>:

> Q: From a librarian:
> "Dear Barry: I do not know much about this debate, but I have a
> question for you: Please tell me how do you find in google the
> hits? what is the procedure? i.e. if I would like to know how
> many time the word Caribbean appears in Google, how will I
> proceed? Thanks for your help! Nelly"
>
> A:
> 1. Go to www.google.com
> 2. type in Carribean
> 3. Look at the light blue web bar on top of the first list of hits. It
> will show you the approximate number of hits:
> Example: "Results 1 - 10 of about 38,100,000 for caribbean"

I distinctly remember an article, which reports that the google hits
estimate is extremely unreliable for larger numbers (>10K or so) of hits,
alas I cannot find the text. I would be grateful, if anyone could point me
to the reference.

Also, if you use google as a corpus substitute, beware that there are many
non-human-generated webpages, which seriously can skew your results.

See: http://itre.cis.upenn.edu/~myl/languagelog/archives/000194.html

Thomas


--
thomas koenig, ph.d.
department of social sciences, loughborough university, u.k.
http://www.lboro.ac.uk/research/mmethods/staff/thomas/index.html