Mailing-List: contact general-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: general@lucene.apache.org
Received-SPF: pass (athena.apache.org: local policy)
DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws;
  s=s1024; d=yahoo.com;
  h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID;
  b=LPbJtZ9MB41DvoSGZCidkrIkfA26vOiZvdJqHn3RaZMq0prq8VCLS0fnbWxQ/MRMYP62mdaK4viFSJcViTNx0MzXVpyggzagNPZy51qGUZPBJo887jcaI/Cs582GkBOoGO5Ceh/L78mVyyTO3EMmnxumaWV4KGBH2HMLAApwRpI=;
Date: Mon, 24 Mar 2008 17:17:40 -0700 (PDT)
From: Marko Novakovic <atisha34@yahoo.com>
Subject: Improving indexing and some questions
To: general@lucene.apache.org
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
Message-ID: <129808.88132.qm@web55710.mail.re3.yahoo.com>

Dear,

I have ideas for improving indexing for web search. I
have written the tutorial for IPSI conference in
Opatija about ranking in search engines:"The new
Avenues in Web Search". I will have been published
article in IPSI Magazine by October, 2008.
This tutorial and my ideas was inspired by articles
from IEEE, Computer Magazine, Issue August, 2007.
I wrote about individual, collaborative, sponsored and
mobile search and social aspects at the Web.
The main idea is to implement indexing based on
relational database. This database would involve
evidence about users, physical and logical
communities(like some enterprise, country, antonomous
sysem, provider, etc.), queries, and user's clicks.
The service which track and analyze user's behaviour
would be also involved.
Indexing will be dynamic propagated by user's recent
behavior(clicks for same or similar query). Ranking
would be implementad by support vector machine, which
would give relevance for each query for each user.
This algorithm is described in article:
T. Joachims, F. Radlinski: "Search Engines that
Laerning from Implicit Feedback," IEEE Computer,
August 2007, pp 38
Community indexin would be implemented by making
relevant promotions which is described in article:
B.Smyth:"A Community Based Approach to Personalizing
Web Search," IEEE Computer, August 2007, pp 45-46
I also deliberate some concepts, which could be
implemented for indexing in sponsored and mobile
search and social web.

I will be honoured giving feedback from Apache's
staff.

Best regards

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com