[Corpora-List] EmoText - Software for opinion mining and lexical affect sensing

[Michal Ptaszynski]

Interesting, how quickly we got from emotions to metaphors :)

Michal

--------------------
Od: Erin McKean <erin at logocracy.com>
Do: corpora at uib.no
Data: Wed, 28 Dec 2011 10:30:58 -0800
Temat: Re: [Corpora-List] EmoText - Software for opinion mining and  
lexical affect sensing

I can't resist replying to this with a link to Mark Peters' blog:

http://rosaparksofblogs.blogspot.com/

"Everybody is the Rosa Parks of something—or at least the Michael Phelps,  
Cap'n Crunch, Dick Cheney, Elmer Fudd, or Paris Hilton of whatever. This  
blog collects examples of the adaptable idiom "X is the Y of Z", which is  
a snowclone. Feel free to use these descriptions when discussing your  
beautiful children, longtime companions, sworn enemies, favorite foods,  
and elected congress-scum."

If you want to model "The X of Y", it's a nice data set for you.

Erin

On 12/28/11 8:30 AM, Justin Washtell wrote:
John,

I doubt that any statistical technique could do much with that data.

With the exception of dead metaphors, isn't metaphorical language almost  
by definition highly creative [productive]? In that light, your analyses  
seems rather restrictive...

How many times do you find "it's the _ of _"?
And "Chicken Tikka Masala"?

Justin Washtell
University of Leeds
________________________________________
From: corpora-bounces at uib.no [corpora-bounces at uib.no] On Behalf Of John F.  
Sowa [sowa at bestweb.net]
Sent: 28 December 2011 14:20
To: corpora at uib.no
Subject: Re: [Corpora-List] EmoText - Software for opinion mining and    
lexical affect sensing

On 12/23/2011 11:31 AM, Justin Washtell wrote:
stuff like the kind of metaphors people use
("it's the Chicken Tikka Masala of mobile phones")

I checked Google for the phrase "it's the Chicken Tikka Masala of"
and found only three terms after "of":  "Thai food", "religion",
and a non-metaphorical word "course".

If you drop the words "it's the" from the front, you get many
non-metaphorical terms like "India", "course", and "all time",
along with some metaphorical examples like "a film".  You also
get the word "it", which could point to a metaphorical term,
but in the examples I checked, the referent was non-metaphorical.

I doubt that any statistical technique could do much with that data.

... no amount of tuning on the data is going to solve the problem:
rather it suggests that something about our base model is inadequate.

Fundamental principle: If you want a computer to understand language,
you need to design a system that can understand language.

John






_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora

_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora