However, there are only few examples when insult words are used explicitly in a NL text. Sally Planalp collects statistics of emotion word use that confirms that there are only insignificant number of explicit cases where emotion words are used in real NLP utterances to convey the emotional meaning. They rather use implicit cues that is influenced by the context.
I would collect words in their NL context and consider approaches by Janyce Wiebe. Here "Creating Subjective and Objective Sentence Classiﬁers from Unannotated Texts" http://people.cs.pitt.edu/~wiebe/pubs/papers/Temp/cicling05.pdf.
-- Alexander Osherenko, Dr. rer. nat. Humboldt Innovation <http://www.humboldt-innovation.de/> Humboldt-Universität zu Berlin Senior HCI architect
Socioware Development <http://www.socioware.de/> Founder and R&D
2014-04-14 5:30 GMT+02:00 Jim Fidelholtz <fidelholtz at gmail.com>:
> Hi, All,
> You might try _Anatomy of the dirty joke_ (2 vols.) by Gershon Legman for
> a thorough analysis of that topic. I don't remember if he gives (even
> implicitly) a categorization of 'offensive language', but you'd certainly
> get at least a lot of data. He collected another two volumes called
> (anonymously) _The limerick_, with, as I recall, about a thousand entries
> in each volume, of wildly varied quality,but, as limericks are wont to be,
> almost all at least moderately offensive. Likewise, you might look through
> the journal _Maledicta_ (started in the 70's) and other such journals, and
> check out books or articles on 'taboo' and related terms. You should also
> check out writings in the fields of Anthropology and Sociology on this and
> related topics, as well as handbooks and other general works in Anth.,
> Soc., Linguistics, etc.
> James L. Fidelholtz
> Posgrado en Ciencias del Lenguaje
> Instituto de Ciencias Sociales y Humanidades
> Benemérita Universidad Autónoma de Puebla, MÉXICO
> On Sun, Apr 13, 2014 at 7:14 AM, Emad Mohamed <emohamed at umail.iu.edu>wrote:
>> Hello All,
>> Is there a categorization of insults / derogatory words?
>> I'm thinking of something like:
>> -ethnic insults
>> -insults attacking mental abilities
>> -insults attacking religion
>> -insults attacking physical traits
>> and so on.
>> Google has failed me so far. Maybe I'm not using the right search terms.
>> I would appreciate your help.
>> Thank you
>> Emad Mohamed
>> Suez University,
>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>> Corpora mailing list
>> Corpora at uib.no
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 6093 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20140414/734998ed/attachment.txt>