Yeah, Ed! I'm totally looking forward to results. Unlikely as it is, if 
there's anything I can do....

and I understand about limiting to 650, but ... well, let's see how it goes.

kc

On 12/10/13, 1:37 PM, Edward Summers wrote:
> I was going to try to reduce the space a bit by focusing on 650 fields. Each record with a Dewey number will be a tab separated line, that will include each 650 field in order. So something like:
>
> 305.42/0973 <tab> Women's rights -- United States -- History -- Sources. <tab> Women -- United States -- History — Sources <tab> Manuscripts, American -- Facsimiles.
>
> I thought it might be a place to start at least … it’s running on an ec2 instance right now :-)
>
> //Ed
>
> On Dec 10, 2013, at 4:26 PM, Karen Coyle <[log in to unmask]> wrote:
>
>> I've often thought that this would be an interesting exercise if someone would undertake it.
>>
>> Just a reminder: in theory (IN THEORY) the first subject heading in an LC record is the one most semantically close to the assigned subject classification. So perhaps a first pass with the FIRST 6xx might give a more refined matching. And then it would be interesting to compare that with the results using all 600-651's.
>>
>> kc
>>
>> On 12/10/13, 1:18 PM, Edward Summers wrote:
>>> Not a naive idea at all. If you have the stomach for it, you could extract the Subject Heading / Dewey combinations out of say the LC Catalog MARC data [1] to use as training data for some kind of clustering [2] algorithm. You might even be able to do something simple like keep a count of the Dewey ranges associated with each subject heading.
>>>
>>> I’m kind of curious myself, so I could work on getting the subject heading / dewey combinations if you want?
>>>
>>> //Ed
>>>
>>> [1] https://archive.org/details/marc_records_scriblio_net
>>> [2] https://en.wikipedia.org/wiki/Cluster_analysis
>>>
>>> On Dec 10, 2013, at 8:18 AM, Irina Arndt <[log in to unmask]> wrote:
>>>
>>>> Hi CODE4LIB,
>>>>
>>>> we would like to add DDC classes to a bunch of MARC records, which contains only LoC Subject Headings.
>>>> Does anybody know, if a mapping between LCSH and DDC is anywhere existent (and available)?
>>>>
>>>> I understood, that WebDewey http://www.oclc.org/dewey/versions/webdewey.en.html  might provide such a service, but
>>>>
>>>> ·         we are no OCLC customers or subscribers to WebDewey
>>>>
>>>> ·         even if we were, I'm not sure, if the service matches our needs
>>>>
>>>> I'm thinking of a tool, where I can upload my list of subject headings and get back a list, where the matching Dewey classes have been added (but a 'simple' csv file with LCSH terms and DDC classes would be helpful as well- I am fully aware, that neither LCSH nor DDC are simple at all...) . Naïve idea...?
>>>>
>>>> Thanks for any clues,
>>>> Irina
>>>>
>>>>
>>>> -------
>>>>
>>>> Irina Arndt
>>>> Max Planck Digital Library (MPDL)
>>>> Library System Coordinator
>>>> Amalienstr. 33
>>>> D-80799 Muenchen, Germany
>>>>
>>>> Tel. +49 89 38602-254
>>>> Fax +49 89 38602-290
>>>>
>>>> Email: [log in to unmask]<mailto:[log in to unmask]>
>>>> http://www.mpdl.mpg.de
>>
>> --
>> Karen Coyle
>> [log in to unmask] http://kcoyle.net
>> m: 1-510-435-8234
>> skype: kcoylenet
>
>

-- 
Karen Coyle
[log in to unmask] http://kcoyle.net
m: 1-510-435-8234
skype: kcoylenet