Oh, this is red meat. I'd talk about recommendation systems till you
all throw me off.
1. You can't draw conclusions based upon a small number of overlapping
"trips." If one trip were enough and you knew I'd looked at something
super-obscure, you could probably figure out the other pages I'd
looked at too. Just go to the page you saw me browsing and see what
appears in the "people who looked at this also looked at..." box. If
my obscure book of Hellenistic poetry overlaps with "Having an Affair
for Dummies," I'm in trouble with the missus.
2. But if you need multiple overlaps, the amount of usable data goes
way down. This is, I submit, what Ann Arbor's recommendation system
showed. You need a lot of data in a recommendation system for it to
work. The worse the data, the more you need. (On LibraryThing, we do
not generally even *try* to make a recommendation when there are fewer
than 15 copies of a book in the system, and those aren't books you
casually looked at, those are books in people's personal collection.)
3. Like other systems that follow where users go, not whether they
liked it there and what they did there, BibTip is susceptible to "ant
navigation" problems. You know how ants find their way about? They
follow the trail put down by other ants. This works well in general,
but it can also go bad. An ant gets lost. Another ant happens on the
trail, and gets lost too, a third and sees a really strong trail, so
three are lost, etc. At its worst you have the famous phenomenon of
ants going round and round in a circle, following other ants and their
ever-stronger trail, until all the ants die of exhaustion!
I ask you: Do we want library patrons dying of exhaustion?
4. In all seriousness, the ant problem is real. Every time the catalog
sends you somewhere you don't want to go, you've made a trail telling
the next guy to go there too. If library catalogs worked, ant-tracking
would too. But when I type "Harry Potter" into the search box of a
large public library I use all the time, I don't get a real-live
English-language Harry Potter book until item number nine!
5. At one point I looked into the "people who've looked at this also
looked at that" algorithm, and I thought that Amazon claimed a patent
on it. All I can find now is a really general patent on recommendation
systems. If others know the situation, I'd love to hear of it.
Tim
On Thu, May 15, 2008 at 4:42 PM, Eric Lease Morgan <emorgan_at_nd.edu> wrote:
> The May/June 2008 issue of D-Lib Magazine includes an article called
> "Adding Value to the Library Catalog by Implementing a Recommendation
> System" that may be of interest people on this mailing list. [1]
>
> Specifically, the article describes an "implicit" recommender
> services called BibTip. The application sits between a user and the
> "catalog" while collecting what gets used by whom and when. Based on
> this sort of information, the application makes suggestions for other
> items in the "catalog".
>
> One thing I found particularly interesting was that this application
> is not necessarily "catalog" specific in that is can be envoked
> through a Javascript call in head element of HTML. Again, it is not
> about creating a specific application that people come to. Instead,
> it is about creating applications that can be integrated and
> syndicated to other venues.
>
> [1] http://www.dlib.org/dlib/may08/monnich/05monnich.html
>
> --
> Eric Lease Morgan
> Head, Digital Access and Information Architecture Department
> Hesburgh Libraries, University of Notre Dame
>
> (574) 631-8604
>
--
Check out my library at http://www.librarything.com/profile/timspalding
Received on Thu May 15 2008 - 16:25:38 EDT