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

[Rich Cooper]

Dear Amanda, Justin, et al,

 

I agree that a "sentiment detection module" hasn't
been perfected yet.  The problem, as Amanda puts
it, is that 

 

"once you start working with real data, both
statistical and grammatical ('semantic')
approaches will fail.  You need a more complex
model of information in order to be able to
understand that a tweet such as "Bummer, I left my
iPhone on the bus - I'm lost without it :-(","

 

The answer, IMHO, is to use large corpora of said
real data, and the best way to handle it is to
first, have analysts annotate the expressions for
their own perceived sentiment.  Second, use the
database partitioning techniques I have mentioned
before to organize those statement found to have
the same sentiment rating into groups, third to
reorganize each group into subclasses, and finally
to select key words and key grammar fragments that
match the observed patterns.  If still not
satisfied, then fourth recurse on each subclass of
statement.  For any newcomers, my recommendations
are encapsulated at

 

www.englishlogickernel.com/Patent-7-209-923-B1.pdf


 

But it will take LOTS of data to capture even MOST
of the comment styles.  

 

-Rich

 

Sincerely,

Rich Cooper

EnglishLogicKernel.com

Rich AT EnglishLogicKernel DOT com

9 4 9 \ 5 2 5 - 5 7 1 2

  _____  

From: corpora-bounces at uib.no
[mailto:corpora-bounces at uib.no] On Behalf Of
Amanda Schiffrin
Sent: Friday, December 16, 2011 12:21 PM
To: Justin Washtell
Cc: corpora at uib.no
Subject: Re: [Corpora-List] EmoText - Software for
opinion mining and lexical affect sensing

 

I think Justin has hit the nail on the head here.
I worked on an attempt to develop a sentiment
detection module for a text analytics software
system in my previous job, and I soon realised
that once you start working with real data, both
statistical and grammatical ('semantic')
approaches will fail.  You need a more complex
model of information in order to be able to
understand that a tweet such as "Bummer, I left my
iPhone on the bus - I'm lost without it :-(",
despite containing only indicators of negative
sentiment at the lexical level, still expresses
high positive sentiment toward the *product*.
Being able to distinguish this kind of sentiment
is one of the main drivers of commercial sentiment
detection, and I'd say we're still a very long way
away from anything like that level of
sophistication.

 

Mandy Schiffrin

 

On 16 December 2011 20:24, Justin Washtell
<lec3jrw at leeds.ac.uk> wrote:

"I would be very sad if this movie did not win a
prize."
high_neg
"I'm very happy that the other reviewers have seen
this movie for what it is: rubbish."
high_pos

Rather than (unfairly) singling out this system, I
think these examples serve to highlight that this
is a very difficult (if not impossibly
ill-defined) problem. One cannot just assess the
polarity of a statement - one needs to know
something about what the object of interest is. In
the above cases we are probably interested in [the
writer's opinion of] the movie... but that fact is
of course *pragmatic* information.

I'm out of my depth now, so I'll say no more :-)
No doubt much has been written on these issues.


Justin Washtell
University of Leeds

________________________________________

From: corpora-bounces at uib.no
[corpora-bounces at uib.no] On Behalf Of Angus
Grieve-Smith [grvsmth at panix.com]
Sent: 16 December 2011 17:25
To: corpora at uib.no
Subject: Re: [Corpora-List] EmoText - Software for
opinion mining and lexical affect sensing


On 12/16/2011 9:01 AM, Alexander Osherenko wrote:
> You didn't test the approach for complex
sentences. I always used the
> example "I am very sad if ..."

    I don't want to nitpick, but that's not a very
nativelike example
for a test sentence.  I've only heard English
speakers use "I am very
sad if ..." in habitual or generic contexts, and
even then "I get very
sad when ..." is much more common.  "I would be
very sad if ..." is also
used.  Maybe check your test sentences against the
CoCA or something?

--
                               -Angus B.
Grieve-Smith
                               grvsmth at panix.com


_______________________________________________
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

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20111216/7ce6fb40/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora