Top Banner
Lauren Conrad 1.7 Million Twitter Followers HOW HOLLYWOOD LEARNED TO LOVE THE SEMANTIC WEB
42

How Hollywood Learned to Love the Semantic Web

Nov 01, 2014

Download

Technology

Chris Testa

As a lean start-up seeking to bring the $50 Billion celebrity endorsement market to social media, Ad.ly had hit a wall. Where to find and programmatically access in-depth profiles and brand-association data on thousands of celebrities?

Engineering lead Chris Testa, set about exploring Linked Data. Within weeks, he'd put Freebase to work in a scalable solution, and began creating a robust celebrity affinity graph.

Learn how Chris is putting Linked Data to work to drive business results -- optimizing brand matches for popular influencers on Facebook, Twitter and more.

Learn:

* Tips & tricks for using Linked Data with social networks like Facebook and Twitter.
* That you can get surprisingly far with the Semantic Web without needing a cross Ph.D. in Philosophy and Computer Science.
* How to use Freebase and its Acre cloud infrastructure to run a data workflow that your non-technical team can use to maintain a high-quality data set.
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: How Hollywood Learned to Love the Semantic Web

Lauren Conrad 1.7 Million Twitter Followers

HOW HOLLYWOOD LEARNED TO LOVE THE SEMANTIC WEB

Page 2: How Hollywood Learned to Love the Semantic Web

Mandy Moore 2.3 Million Twitter Followers

A SEEMINGLY SIMPLE PROCESS

•  We match brands with celebrities that reach their target audiences on Twitter.

•  We write endorsement copy that is authentic to the celeb and will resonate with followers.

•  Through OAuth to celeb’s Twitter accounts, we distribute approved endorsements.

•  We count the conversations the

campaign inspires, plus clicks-though, retweets, etc.

Page 3: How Hollywood Learned to Love the Semantic Web

WHY CELEBRITIES?

Kim Kardashian 7.2 Million Twitter Followers

•  Top Celebrities can get 15,000 clicks per tweet.

•  The NYT and WSJ average about 400.

•  Celebrities cut through the noise.

Page 4: How Hollywood Learned to Love the Semantic Web

BBC AMERICA’S TOP GEAR

Page 5: How Hollywood Learned to Love the Semantic Web

BBC AMERICA’S TOP GEAR

We count the Clicks

We count the Retweets

We count the Conversations

Page 6: How Hollywood Learned to Love the Semantic Web

AUTHENTIC CONVERSATIONS

BBC campaign encouraged people to share stories of their first car. The hashtag #myfirstcar was distributed by celebrities who seeded the conversation with stories of their first vehicle. Success Metric: created over 15,000 responses for #myfirstcar, highest-rated show in Top Gear history

#myfirstcar #myfirstcar

#myfirstcar

Page 7: How Hollywood Learned to Love the Semantic Web

TOYOTA SIENNA – SWAGGER WAGON

Page 8: How Hollywood Learned to Love the Semantic Web

TOYOTA SIENNA – SWAGGER WAGON

We count the Clicks

We count the Video Views

We count the Retweets

2.8 MM Views

Page 9: How Hollywood Learned to Love the Semantic Web

DEVELOPING A UNIQUE EXPERTISE:

Ad.ly CONNECTS BRANDS WITH CONSUMERS VIA TOP CELEBS

Cristiano Ronaldo 2.5 Million Twitter Followers

•  1,000 of the top celebrities, artists and athletes on Twitter.

•  24,000 successful celebrity endorsements in 18 mos.

•  150 Brands: NBC, Sony, Best Buy, Old Navy, Microsoft, etc.

Page 10: How Hollywood Learned to Love the Semantic Web

DEVELOPING A UNIQUE EXPERTISE:

Ad.ly CONNECTS BRANDS WITH CONSUMERS VIA TOP CELEBS

Cristiano Ronaldo 2.5 Million Twitter Followers

•  1,000 of the top celebrities, artists and athletes on Twitter.

•  24,000 successful celebrity endorsements in 18 mos.

•  150 Brands: NBC, Sony, Best Buy, Old Navy, Microsoft, etc.

•  100K Prospects: accounts on Twitter over 10K followers

Page 11: How Hollywood Learned to Love the Semantic Web

Paul Pierce 1.8 Million Followers

•  Needed to get our arms around celebrity data & make it actionable.

•  Must integrate with all aspects of the

business from pre-to-post-campaign.

CHALLENGE: CODIFY OUR TRIBAL KNOWLEDGE

0  20000  40000  60000  80000  100000  120000  

Jan-­‐10  

Jun-­‐10  

Nov-­‐10  

Apr-­‐11  

Sep-­‐11  

Feb-­‐12  

#  Celebs  

Page 12: How Hollywood Learned to Love the Semantic Web

HOW CAN WE DO THIS?

Page 13: How Hollywood Learned to Love the Semantic Web

My Profile Studied at Maryland Did a project @ MINDSWAP with Prof. Jim Hendler on early SPARQL implementation Did the IBM Extreme Blue Internship Program working on OLAP Went to Google / YouTube – not much culture of SemTech Never deployed semantic technologies until… Ad.ly: •  Had a pressing business need •  Had limited resources •  Had limited funds

Disclaimer:  I  was  a  skep0c  

Page 14: How Hollywood Learned to Love the Semantic Web

FREEBASE SATIATED MY SKEPTIC

http://www.freebase.com/view/en/kim_kardashian

/en/kim_kardashian

Page 15: How Hollywood Learned to Love the Semantic Web

WHY LINKED DATA IS WORKING

Tera-sized datasets are now available for real world concepts. Celebrities are well-annotated. Lots of industry interest: •  Google buys Freebase, dataset grows •  Linked Data explodes •  Facebook’s OpenGraph embeds RDFa

everywhere •  Facebook’s Graph API brings graph datasets to

the masses w/ REST+JSON

Great data & technology licensing terms for business. •  Freebase Acre is a great way to prototype This just wasn’t true 6 years ago.

Page 16: How Hollywood Learned to Love the Semantic Web

How: 5 steps to integrating linked data

UNDERSTAND WHAT YOUR “THINGS” ARE

CHOOSE A LINKED DATASET

RECONCILE YOUR THINGS

1

2

3

BUILD BUSINESS INTELLIGENCE

FEEDBACK & MAINTENANCE

4

5

Page 17: How Hollywood Learned to Love the Semantic Web

ADLY DATA MODEL

Endorsement*  Adver@ser*   Celebrity*  

150 Total 24K Total 1K Total

Expected 10K in 6 months Prospect 100K inside of a year

*All entities have performance & analytics data

Page 18: How Hollywood Learned to Love the Semantic Web

ADLY CELEBRITY

Snoop  Dogg  (Celebrity)  

hHp://twiHer.com/snoopdogg  

hHp://facebook.com/snoopdogg  

Followers:  3.3M  

Gender:  54.3%  Male,  45.7%  Female  

Top  Ci@es:  LA,  NYC,  Chicago,  Atlanta,  DC  

Top  Countries:  USA,  India,  Philippines  

Avg  RTs  per  Ad:  21  

Fans:  8.9M  

…  

Avatar:            aaa  

Page 19: How Hollywood Learned to Love the Semantic Web

How: 5 steps to integrating linked data

UNDERSTAND WHAT YOUR “THINGS” ARE

CHOOSE A LINKED DATASET

RECONCILE YOUR THINGS

1

2

3

BUILD BUSINESS INTELLIGENCE

FEEDBACK & MAINTENANCE

4

5

Page 20: How Hollywood Learned to Love the Semantic Web

CHOOSING WHAT TO LINK TO

Linking Open Data cloud diagram, by Richard Cyganiak and Anja Jentzsch. http://lod-cloud.net/

Page 21: How Hollywood Learned to Love the Semantic Web

TOUR OF LINKED DATA

Page 22: How Hollywood Learned to Love the Semantic Web

How: 5 steps to integrating linked data

UNDERSTAND WHAT YOUR “THINGS” ARE

CHOOSE A LINKED DATASET

RECONCILE YOUR THINGS

1

2

3

BUILD BUSINESS INTELLIGENCE

FEEDBACK & MAINTENANCE

4

5

Page 23: How Hollywood Learned to Love the Semantic Web

ADLY CELEBRITY

Snoop  Dogg  

hHp://twiHer.com/snoopdogg  

hHp://facebook.com/snoopdogg  

Followers:  3.3M  

Gender:  54.3%  Male,  45.7%  Female  

Top  Ci@es:  LA,  NYC,  Chicago,  Atlanta,  DC  

Top  Countries:  USA,  India,  Philippines  

Avg  RTs  per  Ad:  21  

Fans:  8.9M  

…  

Avatar:            aaa  

Page 24: How Hollywood Learned to Love the Semantic Web

ADLY CELEBRITY WITH FREEBASE

Snoop  Dogg  

hHp://twiHer.com/snoopdogg  

hHp://facebook.com/snoopdogg  

Followers:  3.3M  

Gender:  54.3%  Male,  45.7%  Female  

Top  Ci@es:  LA,  NYC,  Chicago,  Atlanta,  DC  

Top  Countries:  USA,  India,  Philippines  

Avg  RTs  per  Ad:  21  

Fans:  8.9M  

…  

Avatar:            aaa  

hHp://freebase.com/en/snoop_dogg  

Image:                  aaa  

Aliases:  Calvin  Cordozar  Broadus,  Jr.  

Professions:  Rapper,  Musician,  Actor  

Date  of  Birth:  10-­‐20-­‐1971  

Gender:  Male  

Marital  Status:  Married  

Page 25: How Hollywood Learned to Love the Semantic Web

RECONCILING WITH FREEBASE

•  As new Celebrities come into our system, they are added to the “Match Queue”

•  When 2 experts agree on a match, the Celebrity is “reconciled” with the freebase entity

New  Celebrity  enters  queue  

Judgement  s@ll  out  

Skip

New

Freebase  ID  Matched!  

2x Confirmation

Page 26: How Hollywood Learned to Love the Semantic Web

RECONCILING WITH FREEBASE

Page 27: How Hollywood Learned to Love the Semantic Web

RECONCILING WITH FREEBASE

MATCH!  

Page 28: How Hollywood Learned to Love the Semantic Web

RECONCILING WITH FREEBASE

Page 29: How Hollywood Learned to Love the Semantic Web

RECONCILING WITH FREEBASE No  clear  match  

Page 30: How Hollywood Learned to Love the Semantic Web

ADLY DATA WITH FREEBASE

Snoop  Dogg  

hHp://twiHer.com/snoopdogg  

hHp://facebook.com/snoopdogg  

Followers:  3.3M  

Gender:  54.3%  Male,  45.7%  Female  

Top  Ci@es:  LA,  NYC,  Chicago,  Atlanta,  DC  

Top  Countries:  USA,  India,  Philippines  

Avg  RTs  per  Ad:  21  

Fans:  8.9M  

…  

Avatar:            aaa  

hHp://freebase.com/en/snoop_dogg  

Image:                  aaa  

Aliases:  Calvin  Cordozar  Broadus,  Jr.  

Professions:  Rapper,  Musician,  Actor  

Date  of  Birth:  10-­‐20-­‐1971  

Gender:  Male  

Marital  Status:  Married  

Page 31: How Hollywood Learned to Love the Semantic Web

FREEBASE RELATIONAL MAPPING

•  Special shout out to author Jeff Schenck •  Also could be called FreebaseAlchemy •  RDFAlchemy already exists!

Page 32: How Hollywood Learned to Love the Semantic Web

DATA FLOW

<code>  c.freebase_date_of_birth  

</code>  Freebase  

MQL  Query  

web1   cache1  

<code>  c.name  </code>  

db1  SQL  Query  

web1  

DATABASE PROPERTY:

FREEBASE PROPERTY:

Page 33: How Hollywood Learned to Love the Semantic Web

FREEBASE TOOLS

http://matchmaker.freebaseapps.com/

Matchmaker

http://freebase.com/queryeditor

Schema Explorer http://schemas.freebaseapps.com/

Acre http://acre.freebase.com/

MQL Query Editor

Page 34: How Hollywood Learned to Love the Semantic Web

How: 5 steps to integrating linked data

UNDERSTAND WHAT YOUR “THINGS” ARE

CHOOSE A LINKED DATASET

RECONCILE YOUR THINGS

1

2

3

BUILD BUSINESS INTELLIGENCE

FEEDBACK & MAINTENANCE

4

5

Page 35: How Hollywood Learned to Love the Semantic Web

DEMO: FILTERING

Page 36: How Hollywood Learned to Love the Semantic Web

DEMO: AUGMENT VISUAL DISPLAY

https://admin.ad.ly/admin/celebrity/5391/bio/

Page 37: How Hollywood Learned to Love the Semantic Web

PLAYING WITH SEMANTIC DATA

WHAT YOU CAN DO •  Provide context on reconciled

entities

•  Filter on Properties –  We do this in our Celeb Finder

•  Machine learning on Properties –  Add into clustering as signal

•  Reasoning

–  Need to serialize internal facts into RDF & create Ontology

–  Query a SPARQL endpoint

TOOLS I’D USE TO DO IT

Cwm

Page 38: How Hollywood Learned to Love the Semantic Web

How: 5 steps to integrating linked data

UNDERSTAND WHAT YOUR “THINGS” ARE

CHOOSE A LINKED DATASET

RECONCILE YOUR THINGS

1

2

3

BUILD BUSINESS INTELLIGENCE

FEEDBACK & MAINTENANCE

4

5

Page 39: How Hollywood Learned to Love the Semantic Web

FEEDBACK & MAINTENANCE

Tell  us  what’s  b0rked!  

Negative Feedback

Op-Amp Abstraction

In Out

Page 40: How Hollywood Learned to Love the Semantic Web

FEEDBACK QUEUE

Page 41: How Hollywood Learned to Love the Semantic Web

Summary

•  You don’t need a cross PhD in Computer Science and Philosophy to use SemTech today for visual augmentation and business model properties

•  Linking datasets benefit from human intervention, but tools like the Reconciliation Queue makes this task easier & scalable

•  This 5 step process sets you up to do long term advanced Semantic Analysis with Reasoning, Machine Learning, and so much more

Page 42: How Hollywood Learned to Love the Semantic Web

THANK YOU!

50 Cent 5.4 Million Twitter Followers

Chris Testa [email protected] @crstesa