SlideShare a Scribd company logo
1 of 23
Taxonomy at AOL Classifying the parts of a whole Noel Agnew (@noelagnewny) Ashley Marty (@ashleykmarty) June 09, 2011
The problem:Aol did not have a common vocabulary
56+ Media brands, including: DAM New York 2011 Page 3
Multiple ad systems and content platforms Content platforms: Blogsmith Huffington Post (Movable type) 5min Truveo StudioNow DAM New York 2011 Page 4 Some ad systems: AdTech Advertising.com Feedpoint/Dynamic Banners
All speaking different languages… DAM New York 2011 Page 5 Tag.aol.com “beyonce” Tag… “beyonceknowles” AOL Music “beyonce” AOL music “beyonceknowles” Moviefone “beyonceknowles” Huffington Post “beyonce” H… Post “beyonceknowles”
What we were asked to do Effectively and granularly classify content:    For improved ad sales    To relate content within and between the brands    In some cases, to assist editors with external-facing tags    All sorts of other bits of magic (which will be touched on later) DAM New York 2011 Page6
The solution:Classify all AOL content in the same way
Faceted Ontology DAM New York 2011 Page 8 “…structural frameworks for organizing information on the semantic Web and within semantic enterprises. They provide unique benefits in discovery, flexible access, and information integration due to their inherent connectedness; that is, their ability to represent conceptual relationships. ” -M.K. Bergman, “An Executive Intro to Ontologies” http://www.mkbergman.com/900/an-executive-intro-to-ontologies/
Subjects We have approx. 6800 subjects Generally hierarchical, but some associative relationships Iterative process with editors (subject specialists) 12 Top levels (or classes) DAM New York 2011 Page 9 Arts and Humanities Education Entertainment Health and Medicine Lifestyle Money and Finance News and Politics Science and Tech Social Sciences Sports Transportation Travel and Tourism
Entities Named Things (includes persons) Locations Works Events Groups Brands Products DAM New York 2011 Page 10 Proper nouns (specific persons, places, things) Not hierarchical, but rather associative relationships 7 Entities Vocabularies
Taxonomy/ontology mashup DAM New York 2011 Page 11 Sprint HTC Evo 4G OSX iPhone Verizon Apple AT&T
Making it work
HELLO TEL AVIV! When we were tasked with this, we had very little direct communication with the team in Tel Aviv that runs the classification engine… We also were under the impression that auto-classification was their issue and they’d just have to classify with whatever we gave them. This was WRONG! DAM New York 2011 Page 13
Train in vain? DAM New York 2011 Page 14 ‘Women's Shoes’ We had to find training data for each subject in the taxonomy… and are continually doing so to improve classification.
DAM New York 2011 Page 15 More Contact with the Classification Team 	Providing Feedback on tagging results 	Collaborating on priorities 	What data is most valuable to the tagger? Getting to Know You
Turning large amounts of data into an ontology DAM New York 2011 Page 16 More data sources means multiple records for the same Entity More sources = More effort required in Merging records Name: Beyoncé MusicPerson MoviePerson Alias (synonym): Beyonce Knowles Alias (synonym): Beyonce Source:Wikipedia Source: AolMusicDB Source: AolMovieDB After Merge, one record remains with metadata and relationships from all sources More sources = More valuable records
Where we are now
DAM New York 2011 Page 18 Integrating with Advertising systems Our subjects can be mapped to Advertising categories to serve ads for related products Current Department Store campaign:  Page 18
Recommending Tags for Editorial DAM New York 2011 Page 19
Where we’re going
On the Roadmap… More projects with Advertising teams More data in our ontology to make classification better Refining the ontology- because it’s a living thing DAM New York 2011 Page 21
Lessons learned
Life lessons… Keep your eye on the prize Expect people to think this is a much smaller task than it is Don’t reinvent the wheel Never underestimate the power of the ability to manipulate data DAM New York 2011 Page 23

More Related Content

Viewers also liked

Toronto Housing Market Charts November_2010
Toronto Housing Market Charts November_2010Toronto Housing Market Charts November_2010
Toronto Housing Market Charts November_2010James Metcalfe
 
lecture_9
lecture_9lecture_9
lecture_9farcrys
 
lecture_5
lecture_5lecture_5
lecture_5farcrys
 
Fnul selling techniques and handling objection
Fnul selling techniques and handling objectionFnul selling techniques and handling objection
Fnul selling techniques and handling objectionPik Lertsavetpong
 
Intro To The Valuation Council 1.11.10
Intro To The Valuation Council 1.11.10Intro To The Valuation Council 1.11.10
Intro To The Valuation Council 1.11.10RICS Americas
 
Pharma Field Sales Learning and Development
Pharma Field Sales Learning and DevelopmentPharma Field Sales Learning and Development
Pharma Field Sales Learning and DevelopmentAnup Soans
 
Cyber Bullying...NOT
Cyber Bullying...NOTCyber Bullying...NOT
Cyber Bullying...NOTMeg Cumming
 
Preview guide st852ifr1
Preview guide st852ifr1Preview guide st852ifr1
Preview guide st852ifr1lhghom
 
What is Called Design ?
What is Called Design ?What is Called Design ?
What is Called Design ?Stéphane Vial
 
Learningapps2
Learningapps2Learningapps2
Learningapps2skatelal
 
Simple machines
Simple machines Simple machines
Simple machines jaisal1
 
Thesis writing assignment; thesis presentation
Thesis writing assignment; thesis presentationThesis writing assignment; thesis presentation
Thesis writing assignment; thesis presentationtykl94
 
Why gold is different from other assets
Why gold is different from other assetsWhy gold is different from other assets
Why gold is different from other assetsHochleitner Marine
 
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...Abigail Brown
 
Pharma Field Force Excellence - MedicinMan January 2013
Pharma Field Force Excellence - MedicinMan January 2013Pharma Field Force Excellence - MedicinMan January 2013
Pharma Field Force Excellence - MedicinMan January 2013Anup Soans
 
Presentation by Neil Macintyre
Presentation by Neil MacintyrePresentation by Neil Macintyre
Presentation by Neil MacintyreRam Vijapurapu
 

Viewers also liked (19)

Creating a Dorm Room Sleep Sanctuary
Creating a Dorm Room Sleep SanctuaryCreating a Dorm Room Sleep Sanctuary
Creating a Dorm Room Sleep Sanctuary
 
Toronto Housing Market Charts November_2010
Toronto Housing Market Charts November_2010Toronto Housing Market Charts November_2010
Toronto Housing Market Charts November_2010
 
lecture_9
lecture_9lecture_9
lecture_9
 
lecture_5
lecture_5lecture_5
lecture_5
 
Fnul selling techniques and handling objection
Fnul selling techniques and handling objectionFnul selling techniques and handling objection
Fnul selling techniques and handling objection
 
Intro To The Valuation Council 1.11.10
Intro To The Valuation Council 1.11.10Intro To The Valuation Council 1.11.10
Intro To The Valuation Council 1.11.10
 
Pharma Field Sales Learning and Development
Pharma Field Sales Learning and DevelopmentPharma Field Sales Learning and Development
Pharma Field Sales Learning and Development
 
Cyber Bullying...NOT
Cyber Bullying...NOTCyber Bullying...NOT
Cyber Bullying...NOT
 
Preview guide st852ifr1
Preview guide st852ifr1Preview guide st852ifr1
Preview guide st852ifr1
 
Apply for Graduate Schemes - Strategies for success - Network Rail
Apply for Graduate Schemes - Strategies for success - Network Rail   Apply for Graduate Schemes - Strategies for success - Network Rail
Apply for Graduate Schemes - Strategies for success - Network Rail
 
Ramzan Mubarak
Ramzan MubarakRamzan Mubarak
Ramzan Mubarak
 
What is Called Design ?
What is Called Design ?What is Called Design ?
What is Called Design ?
 
Learningapps2
Learningapps2Learningapps2
Learningapps2
 
Simple machines
Simple machines Simple machines
Simple machines
 
Thesis writing assignment; thesis presentation
Thesis writing assignment; thesis presentationThesis writing assignment; thesis presentation
Thesis writing assignment; thesis presentation
 
Why gold is different from other assets
Why gold is different from other assetsWhy gold is different from other assets
Why gold is different from other assets
 
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...
Bathed in Modernity: Spatial Relegation of Houseless Individuals and Liberato...
 
Pharma Field Force Excellence - MedicinMan January 2013
Pharma Field Force Excellence - MedicinMan January 2013Pharma Field Force Excellence - MedicinMan January 2013
Pharma Field Force Excellence - MedicinMan January 2013
 
Presentation by Neil Macintyre
Presentation by Neil MacintyrePresentation by Neil Macintyre
Presentation by Neil Macintyre
 

Similar to Aol dam taxonomy

Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...
Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...
Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...Alexander Serebrenik
 
Open Calais @ Transparent Text
Open Calais @ Transparent TextOpen Calais @ Transparent Text
Open Calais @ Transparent TextKrista Thomas
 
Collaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateCollaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateAxiell ALM
 
Salesforce: How To Win The War On the Web
Salesforce: How To Win The War On the WebSalesforce: How To Win The War On the Web
Salesforce: How To Win The War On the WebWriterAccess
 
Semantic Technology 2009: Hybrid Approaches to Taxonomy and Folksonomy
Semantic Technology 2009:  Hybrid  Approaches to Taxonomy and FolksonomySemantic Technology 2009:  Hybrid  Approaches to Taxonomy and Folksonomy
Semantic Technology 2009: Hybrid Approaches to Taxonomy and FolksonomyEarley Information Science
 
Joe Bavonese Psychotherapy Networker presentation March 2011
Joe Bavonese Psychotherapy Networker presentation March 2011Joe Bavonese Psychotherapy Networker presentation March 2011
Joe Bavonese Psychotherapy Networker presentation March 2011Joe Bavonese, PhD
 
Conversion for companies that put people in touch with each other (like class...
Conversion for companies that put people in touch with each other (like class...Conversion for companies that put people in touch with each other (like class...
Conversion for companies that put people in touch with each other (like class...Conversion Rate Experts
 
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docx
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docxKey Term TARIFFS- (800 words minimum) 1-5After you have s.docx
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docxcroysierkathey
 
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docx
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docxRunning Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docx
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docxtodd521
 
Mobile Search Generating Revenues At The Intersection Of Content And Context
Mobile Search Generating Revenues At The Intersection Of Content And ContextMobile Search Generating Revenues At The Intersection Of Content And Context
Mobile Search Generating Revenues At The Intersection Of Content And ContextMobile Groove
 
Impact Of Piracy And Free ( T O C F F)
Impact Of Piracy And Free ( T O C  F F)Impact Of Piracy And Free ( T O C  F F)
Impact Of Piracy And Free ( T O C F F)Brian O'Leary
 
PhD Day: Entity Linking using Generic Linked Data Datasets
PhD Day: Entity Linking using Generic Linked Data DatasetsPhD Day: Entity Linking using Generic Linked Data Datasets
PhD Day: Entity Linking using Generic Linked Data DatasetsBianca Pereira
 
"Why the Semantic Web will Never Work" (note the quotes)
"Why the Semantic Web will Never Work"  (note the quotes)"Why the Semantic Web will Never Work"  (note the quotes)
"Why the Semantic Web will Never Work" (note the quotes)James Hendler
 
Collaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateCollaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateAxiell ALM
 
MN AMA Search101
MN AMA Search101MN AMA Search101
MN AMA Search101Azul 7
 
draft bpl
draft bpldraft bpl
draft bplmparhar
 
Chanimal Alliance Presentation
Chanimal Alliance PresentationChanimal Alliance Presentation
Chanimal Alliance Presentationtedfinch
 

Similar to Aol dam taxonomy (20)

Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...
Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...
Invited Talk MESOCA 2014: Evolving software systems: emerging trends and chal...
 
Open Calais @ Transparent Text
Open Calais @ Transparent TextOpen Calais @ Transparent Text
Open Calais @ Transparent Text
 
Collaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateCollaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – Update
 
Salesforce: How To Win The War On the Web
Salesforce: How To Win The War On the WebSalesforce: How To Win The War On the Web
Salesforce: How To Win The War On the Web
 
Semantic Technology 2009: Hybrid Approaches to Taxonomy and Folksonomy
Semantic Technology 2009:  Hybrid  Approaches to Taxonomy and FolksonomySemantic Technology 2009:  Hybrid  Approaches to Taxonomy and Folksonomy
Semantic Technology 2009: Hybrid Approaches to Taxonomy and Folksonomy
 
Semantic search
Semantic searchSemantic search
Semantic search
 
Joe Bavonese Psychotherapy Networker presentation March 2011
Joe Bavonese Psychotherapy Networker presentation March 2011Joe Bavonese Psychotherapy Networker presentation March 2011
Joe Bavonese Psychotherapy Networker presentation March 2011
 
Conversion for companies that put people in touch with each other (like class...
Conversion for companies that put people in touch with each other (like class...Conversion for companies that put people in touch with each other (like class...
Conversion for companies that put people in touch with each other (like class...
 
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docx
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docxKey Term TARIFFS- (800 words minimum) 1-5After you have s.docx
Key Term TARIFFS- (800 words minimum) 1-5After you have s.docx
 
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docx
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docxRunning Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docx
Running Head STRATEGIC MANAGEMENT PLAN1STRATEGIC MANAGEMENT.docx
 
Mobile Search Generating Revenues At The Intersection Of Content And Context
Mobile Search Generating Revenues At The Intersection Of Content And ContextMobile Search Generating Revenues At The Intersection Of Content And Context
Mobile Search Generating Revenues At The Intersection Of Content And Context
 
Impact Of Piracy And Free ( T O C F F)
Impact Of Piracy And Free ( T O C  F F)Impact Of Piracy And Free ( T O C  F F)
Impact Of Piracy And Free ( T O C F F)
 
PhD Day: Entity Linking using Generic Linked Data Datasets
PhD Day: Entity Linking using Generic Linked Data DatasetsPhD Day: Entity Linking using Generic Linked Data Datasets
PhD Day: Entity Linking using Generic Linked Data Datasets
 
"Why the Semantic Web will Never Work" (note the quotes)
"Why the Semantic Web will Never Work"  (note the quotes)"Why the Semantic Web will Never Work"  (note the quotes)
"Why the Semantic Web will Never Work" (note the quotes)
 
Collaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – UpdateCollaborative Project to Improve EMu for Managing Archives – Update
Collaborative Project to Improve EMu for Managing Archives – Update
 
Amazon
AmazonAmazon
Amazon
 
Amazon
AmazonAmazon
Amazon
 
MN AMA Search101
MN AMA Search101MN AMA Search101
MN AMA Search101
 
draft bpl
draft bpldraft bpl
draft bpl
 
Chanimal Alliance Presentation
Chanimal Alliance PresentationChanimal Alliance Presentation
Chanimal Alliance Presentation
 

Recently uploaded

Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Celine George
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesFatimaKhan178732
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppCeline George
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptxPoojaSen20
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3JemimahLaneBuaron
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Concept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfConcept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfUmakantAnnand
 

Recently uploaded (20)

Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and Actinides
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website App
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptx
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Concept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.CompdfConcept of Vouching. B.Com(Hons) /B.Compdf
Concept of Vouching. B.Com(Hons) /B.Compdf
 

Aol dam taxonomy

  • 1. Taxonomy at AOL Classifying the parts of a whole Noel Agnew (@noelagnewny) Ashley Marty (@ashleykmarty) June 09, 2011
  • 2. The problem:Aol did not have a common vocabulary
  • 3. 56+ Media brands, including: DAM New York 2011 Page 3
  • 4. Multiple ad systems and content platforms Content platforms: Blogsmith Huffington Post (Movable type) 5min Truveo StudioNow DAM New York 2011 Page 4 Some ad systems: AdTech Advertising.com Feedpoint/Dynamic Banners
  • 5. All speaking different languages… DAM New York 2011 Page 5 Tag.aol.com “beyonce” Tag… “beyonceknowles” AOL Music “beyonce” AOL music “beyonceknowles” Moviefone “beyonceknowles” Huffington Post “beyonce” H… Post “beyonceknowles”
  • 6. What we were asked to do Effectively and granularly classify content: For improved ad sales To relate content within and between the brands In some cases, to assist editors with external-facing tags All sorts of other bits of magic (which will be touched on later) DAM New York 2011 Page6
  • 7. The solution:Classify all AOL content in the same way
  • 8. Faceted Ontology DAM New York 2011 Page 8 “…structural frameworks for organizing information on the semantic Web and within semantic enterprises. They provide unique benefits in discovery, flexible access, and information integration due to their inherent connectedness; that is, their ability to represent conceptual relationships. ” -M.K. Bergman, “An Executive Intro to Ontologies” http://www.mkbergman.com/900/an-executive-intro-to-ontologies/
  • 9. Subjects We have approx. 6800 subjects Generally hierarchical, but some associative relationships Iterative process with editors (subject specialists) 12 Top levels (or classes) DAM New York 2011 Page 9 Arts and Humanities Education Entertainment Health and Medicine Lifestyle Money and Finance News and Politics Science and Tech Social Sciences Sports Transportation Travel and Tourism
  • 10. Entities Named Things (includes persons) Locations Works Events Groups Brands Products DAM New York 2011 Page 10 Proper nouns (specific persons, places, things) Not hierarchical, but rather associative relationships 7 Entities Vocabularies
  • 11. Taxonomy/ontology mashup DAM New York 2011 Page 11 Sprint HTC Evo 4G OSX iPhone Verizon Apple AT&T
  • 13. HELLO TEL AVIV! When we were tasked with this, we had very little direct communication with the team in Tel Aviv that runs the classification engine… We also were under the impression that auto-classification was their issue and they’d just have to classify with whatever we gave them. This was WRONG! DAM New York 2011 Page 13
  • 14. Train in vain? DAM New York 2011 Page 14 ‘Women's Shoes’ We had to find training data for each subject in the taxonomy… and are continually doing so to improve classification.
  • 15. DAM New York 2011 Page 15 More Contact with the Classification Team Providing Feedback on tagging results Collaborating on priorities What data is most valuable to the tagger? Getting to Know You
  • 16. Turning large amounts of data into an ontology DAM New York 2011 Page 16 More data sources means multiple records for the same Entity More sources = More effort required in Merging records Name: Beyoncé MusicPerson MoviePerson Alias (synonym): Beyonce Knowles Alias (synonym): Beyonce Source:Wikipedia Source: AolMusicDB Source: AolMovieDB After Merge, one record remains with metadata and relationships from all sources More sources = More valuable records
  • 18. DAM New York 2011 Page 18 Integrating with Advertising systems Our subjects can be mapped to Advertising categories to serve ads for related products Current Department Store campaign: Page 18
  • 19. Recommending Tags for Editorial DAM New York 2011 Page 19
  • 21. On the Roadmap… More projects with Advertising teams More data in our ontology to make classification better Refining the ontology- because it’s a living thing DAM New York 2011 Page 21
  • 23. Life lessons… Keep your eye on the prize Expect people to think this is a much smaller task than it is Don’t reinvent the wheel Never underestimate the power of the ability to manipulate data DAM New York 2011 Page 23

Editor's Notes

  1. How many of you knew that all of these are owned by aolHow many of these were purchased since we started the taxonomy process
  2. Photo platform (mention it)At a minimum, 3 ad systems that we’ve had to deal with
  3. url to link out here
  4. Ad Sales: so products with some relation to the article can be served2.Relating content: Within: e.g. Someone on Aol Music can see all Beyonce articles Between: see Beyonce articles on Moviefone, Stylelist, Popeater: keep people on Aol sites instead of linking out3. Assist editors: standardize tags so content not being lost without relationships – can’t find it if not tagged properly
  5. Difference between taxo and onto
  6. Be flexible and remember your purpose (for us its aol content)Subjects may be called topics/categories in other placesSubjects describe ‘aboutness’ of an articlee.g. Report on world series is about ‘Baseball’e.g. Article about best airlines is about ‘Air Travel’
  7. We have around 3.8 million and countingTogether subjects and entities make up the taxonomy
  8. More Contact with the Classification Team Providing Feedback on tagging results Collaborating on priorities Focus on what is most valuable to the tagger
  9. Mix of NLP and machine learningPicks up important related terms that imply content is about a subject (heels, flats, etc).. Brands..etcMention that now entities extracted can actually improve subject taggingDMOZ: Voluntary human-edited directory of the web: lists of websites by subject
  10. One record will have multiple node types, aliases, metadata will be brought together: albums, date of birth, marriedto, spokesperson for brandVery rich records result: opportunity to create multiple relationships
  11. Subjects and entitiesWe met with teams, one thing they liked was the fact they could tag a ‘master version’ with a taxonomy ID-Bring all articles mentioning ‘Charlie Sheen’ together, just like the Beyonce example not different versions like charliesheen,charlie sheen, charlie+sheen
  12. Need title