18.43, Qs: Questions on NLP-Sentiment Detection/Word Formation Units

Tue Jan 9 23:08:34 UTC 2007

LINGUIST List: Vol-18-43. Tue Jan 09 2007. ISSN: 1068 - 4875.

Subject: 18.43, Qs: Questions on NLP-Sentiment Detection/Word Formation Units

Moderators: Anthony Aristar, Eastern Michigan U <aristar at linguistlist.org>
            Helen Aristar-Dry, Eastern Michigan U <hdry at linguistlist.org>
Reviews: Laura Welcher, Rosetta Project / Long Now Foundation  
         <reviews at linguistlist.org> 

Homepage: http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, Wayne
State University, and donations from subscribers and publishers.

Editor for this issue: Kevin Burrows <kevin at linguistlist.org>

We'd like to remind readers that the responses to queries are usually
best posted to the individual asking the question. That individual is
then strongly encouraged to post a summary to the list. This policy was
instituted to help control the huge volume of mail on LINGUIST; so we
would appreciate your cooperating with it whenever it seems appropriate.

In addition to posting a summary, we'd like to remind people that it
is usually a good idea to personally thank those individuals who have
taken the trouble to respond to the query.

To post to LINGUIST, use our convenient web form at


Date: 05-Jan-2007
From: Robert Berkman < robertberkman at gmail.com >
Subject: Questions on NLP-Sentiment Detection 

Date: 05-Jan-2007
From: Sascha Michel < sa.michel at gmx.de >
Subject: Word Formation Units 

-------------------------Message 1 ---------------------------------- 
Date: Tue, 09 Jan 2007 18:07:06
From: Robert Berkman < robertberkman at gmail.com >
Subject: Questions on NLP-Sentiment Detection 

Dear Linguist List Members,

Good day. My name is Robert Berkman, and I am a writer, editor, and author
living in Rochester, New York.

I am currently working on a book, tentatively titled ''The Art of Strategic
Listening'', (Paramount Market Press, 2007) which will provide businesses
with advice on how to carefully listen to discussions on blogs in order to
identify emerging trends and track current and potential customer needs.

One section of the book will examine firms (eg BuzzMetrics, Umbria,
Cymfony, etc.) that claim to be able to do this tracking job for its
clients, often by integrating a Natural Language Processing sentiment
analysis feature to identify whether postings and conversations can be
categorized as positive, negative or in some other manner.

As part of this book, I would like to provide some objective advice on how
reliable these sentiment software programs really are and how to best judge
their capabilities. Vendors claim a certain level of accuracy--usually 80-
85%--but I have yet to see any studies or independent reports that do any
kind of objective test to see if they truly live up to their claims.

I would be most grateful if anyone on this list can point me in the
direction to find any such studies. I'd also welcome any general comments
or views on the overall reliability and value of sentiment detection
software for this kind of purpose.

Thanks so much for any assistance!

Robert Berkman, faculty
MA Media Studies, The New School,
New York, NY
Editor, The Information Advisor
Rochester NY 14607 

Linguistic Field(s): Computational Linguistics

-------------------------Message 2 ---------------------------------- 
Date: Tue, 09 Jan 2007 18:07:09
From: Sascha Michel < sa.michel at gmx.de >
Subject: Word Formation Units 


Dear all,

I'm currently working on the status of word formation units such as -zine
(Metallic-Zine, PC-Zine), -minator (Ebayminator, Tomminator)and -tainment
(Center-tainment, Cover-tainment) in German. 

Obviously, these elements cannot be clearly classified as free words,
shortenings, affixes, semi-affixes or combining forms. They are rather
transitional/marginal phenomena on the parole-level that challenge the
assumptions of distinct categories and fixed definitions. 

Does anyone know any literature on the morphological status of the
mentioned elements?

I will post a summary, if I receive sufficient responses.

Thanks in advance,
Sascha Michel 

Linguistic Field(s): Morphology

LINGUIST List: Vol-18-43	


More information about the Linguist mailing list