* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *
LINGUIST List 18.43

Tue Jan 09 2007

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

Editor for this issue: Kevin Burrows <kevinlinguistlist.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 http://linguistlist.org/LL/posttolinguist.html.
        1.    Robert Berkman, Questions on NLP-Sentiment Detection
        2.    Sascha Michel, Word Formation Units

Message 1: Questions on NLP-Sentiment Detection
Date: 05-Jan-2007
From: Robert Berkman <robertberkmangmail.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: Word Formation Units
Date: 05-Jan-2007
From: Sascha Michel <sa.michelgmx.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

Respond to list|Read more issues|LINGUIST home page|Top of issue

Please report any bad links or misclassified data

LINGUIST Homepage | Read LINGUIST | Contact us

NSF Logo

While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.