the future of search engines

23
The Future of Search Engines Take it personally! Emil Ismalon Co-founder and CTO Collarity, Inc. Internet 2008 February 25, טטטטטטט2008

Upload: march

Post on 04-Jan-2016

27 views

Category:

Documents


0 download

DESCRIPTION

The Future of Search Engines. Take it personally!. אינטרנט 2008. Emil Ismalon Co-founder and CTO Collarity, Inc. Internet 2008 February 25, 2008. My Tag cloud. Physics Buddhist meditation Quantum Holistic approach measurement problems - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: The Future of Search Engines

The Future of Search EnginesTake it personally!

Emil IsmalonCo-founder and CTO

Collarity, Inc.

Internet 2008February 25, 2008

2008אינטרנט

Page 2: The Future of Search Engines

2The Wisdom of Your Crowd

PhysicsPhysics BuddhistBuddhist meditation meditation

Quantum Quantum Holistic approachHolistic approach measurement problemsmeasurement problems

Machine learningMachine learning cognition & realitycognition & reality

ZenZen

The forceThe force AAbbstractions stractions

LoveLove information retrieval information retrieval mathmath MindMind & & matter matter LiaLia NoaNoa COLLABORATIONCOLLABORATION

Multidimensional Multidimensional clusteringclustering basketball basketball

Social networkingSocial networking how? how? DRUMS DRUMS

CollarityCollarity high frequency lasers high frequency lasers Swimming Swimming dear mamadear mama

My Tag cloud

Page 3: The Future of Search Engines

3The Wisdom of Your Crowd

Beyond the Limits of Keyword Search

Amount of data

Pro

duct

ivity

of S

earc

h

Databases

Web 1.0 Web 1.0 1990 - 2000

The World Wide Web

PC EraPC Era1980 - 1990

The Desktop Keyword search

Directories

2000 - 2010Web 2.0 Web 2.0

The Social Web

Files & Folders

Tagging

Naturallanguage

search

2010 - 2020

Web 3.0 Web 3.0 The Semantic Web

Automated Content Analysis

2010 - 2020

Web 3.0 Web 3.0 User Modeling

Universal/Open IDUser profiling

** From: Making Sense of the Semantic Web, BY Nova Spivack

Syndicated WebIntelligent Web

Web 4.0 Web 4.0

Page 4: The Future of Search Engines

4The Wisdom of Your Crowd

The Next Steps

Methods

Automated Content Analysis

Latent Space construction

(Augmented LSA LDA methods)

Semantic Web

Today’s ContentSocial networking

Media consumption

Commercial consumption

User ModelingUniversal/Open ID

User Profiling

Behavioral & Intentional Targeting

User interactions with content

TechnologicalEnablement

Page 5: The Future of Search Engines

5The Wisdom of Your Crowd

Projection into the future

1. Better rankings-relevant results

2. Recommendation engine

3. Deep personalization

4.Digidentity

Page 6: The Future of Search Engines

6The Wisdom of Your Crowd

DigidentityDigidentity

Digital Identity Entity

Shabti statues

“What I’m about”

My digital imprint

Independent Entity

AvatarUser

Page 7: The Future of Search Engines

7The Wisdom of Your Crowd

PERSONALIZATION

Key Element:

Page 8: The Future of Search Engines

8The Wisdom of Your Crowd

The pros & cons of personalization

Pros:• This is how the “real world” behaves: intents and

meanings can’ t usually described by a query• It is the natural way to achieve higher relevance and

enhanced user experience• Think about web navigation in 5-10 years from now..

Do you really think intelligent personal web agents will not emerge?

Page 9: The Future of Search Engines

9The Wisdom of Your Crowd

Cons:• Lockup problems • Cold start - it takes time and education• Is there a general solution to personalization or is

it strongly dependent on contexts • Privacy ethics• Manipulations

The pros & cons of personalization

Page 10: The Future of Search Engines

10The Wisdom of Your Crowd

Gradual perception of personalization

• Language preferences

• Geo targeting

• Simple Lingual Disambiguation The case of Java; is it programming OR island OR coffee?

• Social networking

• Form of preferable media Textual OR visual? Summary OR deep analysis?

== ==

Page 11: The Future of Search Engines

11The Wisdom of Your Crowd

• Understanding the right perception while interacting: Pro OR anti Believer OR skeptical

• Subtle ones Quantum physics article most suitable to a biologist

Gradual perception of personalization

Page 12: The Future of Search Engines

12The Wisdom of Your Crowd

bush

Page 13: The Future of Search Engines

13The Wisdom of Your Crowd

bush

Page 14: The Future of Search Engines

14The Wisdom of Your Crowd

Java

Page 15: The Future of Search Engines

15The Wisdom of Your Crowd

User modeling

Eleanor Rigby’s recent queries:

Paul is dead

Did we land on the moon?

Elvis is alive!

Who murdered JFK?

Page 16: The Future of Search Engines

16The Wisdom of Your Crowd

ABSTRUCTION

Collarity live example of conspiracy:

Moon Elvis JFK

http://www.collarity.com/search?query=Moon+Elvis+JFK

Page 17: The Future of Search Engines

17The Wisdom of Your Crowd

Natural Audience Segmentation

Before: Traffic

• What are my important segments doing?• What are their likes/dislikes?• Are they finding what they’re looking for?• How are their tastes changing?

After: Natural Communities

Page 18: The Future of Search Engines

18The Wisdom of Your Crowd

WAR – what is it good for?Augmented Personalization in Action

Page 19: The Future of Search Engines

19The Wisdom of Your Crowd

The ability to personalizeIn order to materialize the subtle level of personalization an holistic approach is needed!

understand the user from many different aspects:

•Implicit Informational networking

•SegmentationCluster users in information space

•Topic based communities Clustering users around topics

Page 20: The Future of Search Engines

20The Wisdom of Your Crowd

Space & Beyond

•Establishing the “Space”• Live metric - relevancy coordinates (attributes) • Embedding users profile

•Space dynamics• Predictions – Segmentation, Clustering

Page 21: The Future of Search Engines

21The Wisdom of Your Crowd

Future of DigidentityFuture of DigidentityDigidentities Spontaneously Behave

User

TVTV

NewsNews WorkWork

MusicMusic HobbiesHobbies

InterestsInterestsKnowledgeKnowledge

SocialSocial

Page 22: The Future of Search Engines

22The Wisdom of Your Crowd

Conclusions and Summary

1. Personalization involves “intelligence” characteristic; abstraction, generalization, predictive clustering

2. Users implicit informational communities can serve as a natural enhancement of user searching and browsing modeling

3. Enable Users to control personalization features and variables

Page 23: The Future of Search Engines

23The Wisdom of Your Crowd

Further readings

• Pros & cones personalized search http://searchengineland.com/070309-081324.php

• Dynamic Social Network Analysis using Latent Space Modelshttp://books.nips.cc/papers/files/nips18/NIPS2005_0724.pdf

• Constraint-based Personalization Model: Multi-Channel Messaginghttp://www.research.att.com/~rjana/TothNagboth.pdf

• A Hybrid Web Personalization Model. Based on Site Connectivity.• Miki Nakagawa, Bamshad Mobasher ... on non-sequential models, such as

association rules and ...http://maya.cs.depaul.edu/~mobasher/papers/NM03b.pdf

• Social Balance Theory• Revisiting Heider’s Balance Theory for many agents

http://www.au.af.mil/au/awc/awcgate/lanl/social_balance_0405041.pdf