SlideShare ist ein Scribd-Unternehmen logo
1 von 34
The Role of Data Integration and
              Context in Measuring User
                      Engagement



Pracitioner Web Analytics, My 25th, 2010



                                           1
The Media Revolution [A historical perspective]

                                                                              Future
                                        Super 8 mm
                                                                         Applications
                                           Film
                                                                               2050+
                                         Cartridges VCR
           Lithography 1798                1965                    TIVO
                                                    1972         TV Anytime
                    Photography 1860s                            Late 1990s
 User
                                                       Digital
Activity                                              Cameras                    Twitter
                              Brownie camera            1990s
                                        1900                                   YouTube
                                                                      Flickr

                                                                     Social Media!
                                               Time


                                               2
Trend I (Technical)




  Increased connectivity, public data, data centers
           Integrated devices and services




                           3
Trend II (behavioral)




         Strong dependence on computing
      On-off line convergence, real time, anywhere




                         4
Trend III (Socio-economic)




     Spread of technology, “Flat” world




                          5
Why do we care?
Yahoo! is ranked among the top 3 sites in 26 key categories and #1 in 12 of them
                                               Yahoo! Monthly Unique Visitors (000) Noted in Yellow

         E-mail                  Autos             Entertainment News                  Local/Maps                        Groups                        Home Pages
 1. Yahoo! Mail          1. eBay Motors U.S.      1. omg!                      1. Google Maps                  1. Facebook Groups              1. Yahoo! HP
 2. Win. Live Hotmail    2. Yahoo! Autos          2. TMZ                       2. Mapquest                     2. Yahoo! Groups                2. Google HP
 3. Google Gmail         3. KBB.com               3. People                    3. Yahoo! Maps                  3. Google Groups                3. Facebook HP
 Y! UVs: 106,166         Y! UVs: 6,972            Y! UVs: 20,428               Y! UVs: 13,163                  Y! UVs: 7,654                   Y! UVs: 118,011

         Games                   Search                    Finance                          TV                           News                               IM
 1. Yahoo! Games         1. Google Search        1. Yahoo! Finance              1. Yahoo! TV                   1. Yahoo! News                  1. Yahoo! Messenger
 2. EA Games             2. Yahoo! Search        2. AOL Money & Finance         2. AOL TV                      2. CNN                          2. AIM.com/AIM App
 3. Nickelodeon          3. ASK Network          3. MSN Money                   3. MSN TV                      3. MSNBC                        3. MSN Msngr
 Y! UVs: 18,797          Y! UVs: 90,191          Y! UVs: 21,671                 Y! UVs: 15,085                 Y! UVs: 48,433                  Y! UVs: 38,140



                         Why do we care?
         Movies                   Travel                    Music                                                        Sports                           Portals
                                                                                      My (Custom)*
1. IMDB.com              1. TravelAd Network                                                                   1. Yahoo! Sports                  1. Yahoo! Sites
                                                 1. AOL Music                  1. My Yahoo!
2. Yahoo! Movies         2. Tripadvisor                                                                        2. ESPN                           2. Microsoft Sites
                                                 2. MySpace Music              2. iGoogle
3. Moviefone             3. Yahoo! Travel                                                                      3. Fox Sports on MSN              3. AOL LLC
                                                 3. Yahoo! Music               3. My MSN
Y! UVs: 17,942           Y! UVs: 10,167                                                                        Y! UVs: 30,718                    Y! UVs: 156,506
                                                 Y! UVs: 21,889                Y! UVs: 24,644

 Shopping (Comparison)           Careers                Reference                       Personals                         Photos                        Real Estate
1. Yahoo! Shopping       1. Careerbuilder         1. Wikimedia                 1. Yahoo! Personals              1. Facebook.com Photos 1. Move Network
2. Shopzilla.com         2. Yahoo! HotJobs        2. Yahoo! Answers            2. SingelsNet                    2. Photobucket         2. Yahoo! Real Estate

3. Shopping.com          3. Monster               3. Answers.com               3. PlentyofFish                  3. FLICKR.COM                  3. AOL Real Estate

Y! UVs: 22,901           Y! UVs: 16,697           Y! UVs: 43,164               Y! UVs: 3,330                    Y! UVs: 24,686                 Y! UVs: 7,525


                                                            Source: comScore Media Metrix, July 2009
                                                            !"#$%&'()&*+,+&-"."/&01.$%&213$4"5$#&6#&71.&"&.8"-6.617"9&:".$518;&67&:13,:18$<#&#$8=6:$
                                                            *Not Shown: Yahoo! Green ranks #2 in Environment, Yahoo! Health ranks #3 in Health
                                                             Monthly figures unless otherwise indicated




                                                                             ACM RecSys 2009 Courtesy of Todd Beaupre (Y!) !
                                                                                                                                                                      5
Interaction Experience




(Video of angry PC user..)



                  8
Is he engaged?




            9
Or enraged..
But what do we see?


         A click!
We have…
   More data than at any time in history
   Better tools to store it, access it, process it
   Better (sometimes) technology for our day to day
   Overly complex systems, information overload
   Larger diversity of “users”




                 New business models
           Patterns, Data Mining, Interaction
But…


 It is not about the data…
Human-Centered Analytics!

   User                   Data
   Experience             analysis



           Human aspects             Machine Learning,
                                     Context,
                                     User Modeling,
                                     Engagement

                     14
Human-Centered Analytics


Social-cultural          Psychological    Context



                  Economic

                                         Key enabler


                              15
Key Differentiator?


 Analytics for customer experience innovation
  …. that is what should be optimized for .…
But how?

  Know your “users”
    •  What, how, and why?


    •  Who?
Two examples…
Example I

  Image Search
     1.4 Billion anonymous search queries (75 M
       unique queries)
     100K most frequent queries
Example I

  Results I
     100 most frequent queries account for 5.8% of
      query volume
     57 of celebrities (52 female)
     5 fictional (Spongebob, Hello Kitty, Santa..)
     6 tattoo related (e.g., tribal tattoo)
     2 “functional” (xmas wall paper)
Example I
  Results II (top 100K queries)
             7%            Entertainment_&_Music
        8%
                           Arts_&_Humanities
                     31%
                           Sports
   9%
                           Science_&_Mathematics

   9%
                           Beauty_&_Style

                           Travel
                    14%
        9%                 Society_&_Culture

              13%          Cars_&_Transportation
Example I
  Results III (top 100K queries)
                                       initial
                                  initial         next page
                                       next page
         2%                11%
        2%
          2%
         2%
                    15%
                     15%    11%
                                       more specific
                                  more specific   more generic
                                       more generic
               5%
               5%

                                       minor rewrite
                                  minor rewrite   major rewrite
                                       major rewrite
                           65%
                            65%
Example I

  Observations
     Most people that “search” for images are
      actually browsing!


     What is the right engagement metric here?


     Impact on experience design…
Example II

  Web Search            [weber & Castillo SIGIR ‘10]



     Anonymized Profiles of 28 million users
      (birth year, gender, ZIP)
     US census data
     Data aggregated (not per user)
Example II

  Example Queries
     “Wagner”


     “Lindsey”


     “Hal”
Example II

  Examples

  Female                 Male
  (Wagner=composer)      (Wagner=spray painter)

     Hal Lindsey: American evangelist and
      Christian writer
     Hal Higdon: American writer and runner
      (above average education areas)
Example II

  Observations
     Lots of public data unexplored


     Information flows? Profiles?


     Business strategy…
Social Media
   Clickstream
   Favorites
   Purchases
   Social network analysis
      Communities, influence, propagation, & dynamics
   Interest/activity-based user modeling
      Social “Network” of objects-people-interests
   Trend spotting
      Psycho-socio-cultural-economic perspectives
User Experience
   Browsing
   Discovery
   Personalization
   New services?


   Eye tracking
   Focus group user studies
Design Process



 Algorithm   Interface   User
Analytics and Design
   Interaction design                             Analytics


                         Human abilities, needs




                            Implementation
Socio-cultural context
Human-Centered Analytics

   User                   Data
   Experience             analysis



           Human aspects             Machine Learning,
                                     Context,
                                     User Modeling,
                                     Personalization

                     33
Thank you!
Alex Jaimes
ajaimes@yahoo-inc.com


© 2010 A. Jaimes. No portion of these slides can be reproduced
without permission. Personal opinions, not of Yahoo! Inc.

Weitere ähnliche Inhalte

Andere mochten auch

MDFF_Guidelines_Print version_FINAL_Low Res
MDFF_Guidelines_Print version_FINAL_Low ResMDFF_Guidelines_Print version_FINAL_Low Res
MDFF_Guidelines_Print version_FINAL_Low Res
ivanidrovo
 

Andere mochten auch (10)

Hai-varotra 2
Hai-varotra 2Hai-varotra 2
Hai-varotra 2
 
MDFF_Guidelines_Print version_FINAL_Low Res
MDFF_Guidelines_Print version_FINAL_Low ResMDFF_Guidelines_Print version_FINAL_Low Res
MDFF_Guidelines_Print version_FINAL_Low Res
 
Assure assignment
Assure assignmentAssure assignment
Assure assignment
 
Vom Server bis zum Workspace: Windows Anwendungen auf AWS - AWS Cloud Web Day...
Vom Server bis zum Workspace: Windows Anwendungen auf AWS - AWS Cloud Web Day...Vom Server bis zum Workspace: Windows Anwendungen auf AWS - AWS Cloud Web Day...
Vom Server bis zum Workspace: Windows Anwendungen auf AWS - AWS Cloud Web Day...
 
2.awiazuin uhaanii-sudlal
2.awiazuin uhaanii-sudlal2.awiazuin uhaanii-sudlal
2.awiazuin uhaanii-sudlal
 
үгийн эсрэг утгыг мэдэцгээе!
үгийн эсрэг утгыг мэдэцгээе!үгийн эсрэг утгыг мэдэцгээе!
үгийн эсрэг утгыг мэдэцгээе!
 
[Grup d'Altes Capacitas] Trabajo altas capacidades
[Grup d'Altes Capacitas] Trabajo altas capacidades[Grup d'Altes Capacitas] Trabajo altas capacidades
[Grup d'Altes Capacitas] Trabajo altas capacidades
 
Handling of pipette ,buret,separatory funnnel, graduated cylinder
Handling of pipette ,buret,separatory funnnel, graduated cylinderHandling of pipette ,buret,separatory funnnel, graduated cylinder
Handling of pipette ,buret,separatory funnnel, graduated cylinder
 
Treball curs altes capacitats
Treball curs altes capacitatsTreball curs altes capacitats
Treball curs altes capacitats
 
хоёр од нэг хүсэл үнэлгээний үр дүн
хоёр од нэг хүсэл үнэлгээний үр дүнхоёр од нэг хүсэл үнэлгээний үр дүн
хоёр од нэг хүсэл үнэлгээний үр дүн
 

Ähnlich wie The Role of Data Integration and Context in Measuring User Engagement

Understanding Digital Marketing and its implications in Latin America
Understanding Digital Marketing and its implications in Latin AmericaUnderstanding Digital Marketing and its implications in Latin America
Understanding Digital Marketing and its implications in Latin America
Jose Luis Lopez Mota
 
Digital Consumer FCCS0221
Digital Consumer FCCS0221Digital Consumer FCCS0221
Digital Consumer FCCS0221
Gregory Birgé
 
Initiation réseaux sociaux
Initiation réseaux sociauxInitiation réseaux sociaux
Initiation réseaux sociaux
LudiqPlayground
 
Mobile Recruiting (October 2011)
Mobile Recruiting (October 2011)Mobile Recruiting (October 2011)
Mobile Recruiting (October 2011)
David Lee
 
Ignition session welcome
Ignition session welcomeIgnition session welcome
Ignition session welcome
Babbel
 

Ähnlich wie The Role of Data Integration and Context in Measuring User Engagement (20)

TWIMPACT: Know your audience!
TWIMPACT: Know your audience!TWIMPACT: Know your audience!
TWIMPACT: Know your audience!
 
Understanding Digital Marketing and its implications in Latin America
Understanding Digital Marketing and its implications in Latin AmericaUnderstanding Digital Marketing and its implications in Latin America
Understanding Digital Marketing and its implications in Latin America
 
Why all payments innovations are rubbish
Why all payments innovations are rubbishWhy all payments innovations are rubbish
Why all payments innovations are rubbish
 
Introduction Aux Réseaux Sociaux Katheline Jean Pierre
Introduction Aux Réseaux Sociaux Katheline Jean PierreIntroduction Aux Réseaux Sociaux Katheline Jean Pierre
Introduction Aux Réseaux Sociaux Katheline Jean Pierre
 
How to connect with media when journalists go social/ real-time reporting
How to connect with media when journalists go social/ real-time reportingHow to connect with media when journalists go social/ real-time reporting
How to connect with media when journalists go social/ real-time reporting
 
Who wants to be a billionaire
Who wants to be a billionaireWho wants to be a billionaire
Who wants to be a billionaire
 
Hotel Website Marketing Online social media opportunities for the hospitality...
Hotel Website Marketing Online social media opportunities for the hospitality...Hotel Website Marketing Online social media opportunities for the hospitality...
Hotel Website Marketing Online social media opportunities for the hospitality...
 
The Eight Things I Learned in Asia
The Eight Things I Learned in AsiaThe Eight Things I Learned in Asia
The Eight Things I Learned in Asia
 
South African & African Digital Stats PUB QUIZ
South African & African Digital Stats PUB QUIZSouth African & African Digital Stats PUB QUIZ
South African & African Digital Stats PUB QUIZ
 
Social Media Tomorrow : conference with LinkedIn VP Mike Gamson ( his deck is...
Social Media Tomorrow : conference with LinkedIn VP Mike Gamson ( his deck is...Social Media Tomorrow : conference with LinkedIn VP Mike Gamson ( his deck is...
Social Media Tomorrow : conference with LinkedIn VP Mike Gamson ( his deck is...
 
Digital Korea Plus8Star
Digital Korea Plus8StarDigital Korea Plus8Star
Digital Korea Plus8Star
 
TheTrendWatch #04
TheTrendWatch #04TheTrendWatch #04
TheTrendWatch #04
 
Digital Consumer FCCS0221
Digital Consumer FCCS0221Digital Consumer FCCS0221
Digital Consumer FCCS0221
 
Médias Sociaux en Belgique et ailleurs
Médias Sociaux en Belgique et ailleursMédias Sociaux en Belgique et ailleurs
Médias Sociaux en Belgique et ailleurs
 
Initiation réseaux sociaux
Initiation réseaux sociauxInitiation réseaux sociaux
Initiation réseaux sociaux
 
Saving media: The UC Berkeley Media Technolgy Summit
Saving media: The UC Berkeley Media Technolgy SummitSaving media: The UC Berkeley Media Technolgy Summit
Saving media: The UC Berkeley Media Technolgy Summit
 
Online Video &amp; Social Media Facts
Online Video &amp; Social Media FactsOnline Video &amp; Social Media Facts
Online Video &amp; Social Media Facts
 
Online Video & Social Media Facts
Online Video & Social Media FactsOnline Video & Social Media Facts
Online Video & Social Media Facts
 
Mobile Recruiting (October 2011)
Mobile Recruiting (October 2011)Mobile Recruiting (October 2011)
Mobile Recruiting (October 2011)
 
Ignition session welcome
Ignition session welcomeIgnition session welcome
Ignition session welcome
 

Kürzlich hochgeladen

EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Kürzlich hochgeladen (20)

The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 

The Role of Data Integration and Context in Measuring User Engagement

  • 1. The Role of Data Integration and Context in Measuring User Engagement Pracitioner Web Analytics, My 25th, 2010 1
  • 2. The Media Revolution [A historical perspective] Future Super 8 mm Applications Film 2050+ Cartridges VCR Lithography 1798 1965 TIVO 1972 TV Anytime Photography 1860s Late 1990s User Digital Activity Cameras Twitter Brownie camera 1990s 1900 YouTube Flickr Social Media! Time 2
  • 3. Trend I (Technical) Increased connectivity, public data, data centers Integrated devices and services 3
  • 4. Trend II (behavioral) Strong dependence on computing On-off line convergence, real time, anywhere 4
  • 5. Trend III (Socio-economic) Spread of technology, “Flat” world 5
  • 6. Why do we care?
  • 7. Yahoo! is ranked among the top 3 sites in 26 key categories and #1 in 12 of them Yahoo! Monthly Unique Visitors (000) Noted in Yellow E-mail Autos Entertainment News Local/Maps Groups Home Pages 1. Yahoo! Mail 1. eBay Motors U.S. 1. omg! 1. Google Maps 1. Facebook Groups 1. Yahoo! HP 2. Win. Live Hotmail 2. Yahoo! Autos 2. TMZ 2. Mapquest 2. Yahoo! Groups 2. Google HP 3. Google Gmail 3. KBB.com 3. People 3. Yahoo! Maps 3. Google Groups 3. Facebook HP Y! UVs: 106,166 Y! UVs: 6,972 Y! UVs: 20,428 Y! UVs: 13,163 Y! UVs: 7,654 Y! UVs: 118,011 Games Search Finance TV News IM 1. Yahoo! Games 1. Google Search 1. Yahoo! Finance 1. Yahoo! TV 1. Yahoo! News 1. Yahoo! Messenger 2. EA Games 2. Yahoo! Search 2. AOL Money & Finance 2. AOL TV 2. CNN 2. AIM.com/AIM App 3. Nickelodeon 3. ASK Network 3. MSN Money 3. MSN TV 3. MSNBC 3. MSN Msngr Y! UVs: 18,797 Y! UVs: 90,191 Y! UVs: 21,671 Y! UVs: 15,085 Y! UVs: 48,433 Y! UVs: 38,140 Why do we care? Movies Travel Music Sports Portals My (Custom)* 1. IMDB.com 1. TravelAd Network 1. Yahoo! Sports 1. Yahoo! Sites 1. AOL Music 1. My Yahoo! 2. Yahoo! Movies 2. Tripadvisor 2. ESPN 2. Microsoft Sites 2. MySpace Music 2. iGoogle 3. Moviefone 3. Yahoo! Travel 3. Fox Sports on MSN 3. AOL LLC 3. Yahoo! Music 3. My MSN Y! UVs: 17,942 Y! UVs: 10,167 Y! UVs: 30,718 Y! UVs: 156,506 Y! UVs: 21,889 Y! UVs: 24,644 Shopping (Comparison) Careers Reference Personals Photos Real Estate 1. Yahoo! Shopping 1. Careerbuilder 1. Wikimedia 1. Yahoo! Personals 1. Facebook.com Photos 1. Move Network 2. Shopzilla.com 2. Yahoo! HotJobs 2. Yahoo! Answers 2. SingelsNet 2. Photobucket 2. Yahoo! Real Estate 3. Shopping.com 3. Monster 3. Answers.com 3. PlentyofFish 3. FLICKR.COM 3. AOL Real Estate Y! UVs: 22,901 Y! UVs: 16,697 Y! UVs: 43,164 Y! UVs: 3,330 Y! UVs: 24,686 Y! UVs: 7,525 Source: comScore Media Metrix, July 2009 !"#$%&'()&*+,+&-"."/&01.$%&213$4"5$#&6#&71.&"&.8"-6.617"9&:".$518;&67&:13,:18$<#&#$8=6:$ *Not Shown: Yahoo! Green ranks #2 in Environment, Yahoo! Health ranks #3 in Health Monthly figures unless otherwise indicated ACM RecSys 2009 Courtesy of Todd Beaupre (Y!) ! 5
  • 8. Interaction Experience (Video of angry PC user..) 8
  • 11. But what do we see? A click!
  • 12. We have…   More data than at any time in history   Better tools to store it, access it, process it   Better (sometimes) technology for our day to day   Overly complex systems, information overload   Larger diversity of “users” New business models Patterns, Data Mining, Interaction
  • 13. But… It is not about the data…
  • 14. Human-Centered Analytics! User Data Experience analysis Human aspects Machine Learning, Context, User Modeling, Engagement 14
  • 15. Human-Centered Analytics Social-cultural Psychological Context Economic Key enabler 15
  • 16. Key Differentiator? Analytics for customer experience innovation …. that is what should be optimized for .…
  • 17. But how? Know your “users” •  What, how, and why? •  Who?
  • 19. Example I Image Search 1.4 Billion anonymous search queries (75 M unique queries) 100K most frequent queries
  • 20. Example I Results I 100 most frequent queries account for 5.8% of query volume 57 of celebrities (52 female) 5 fictional (Spongebob, Hello Kitty, Santa..) 6 tattoo related (e.g., tribal tattoo) 2 “functional” (xmas wall paper)
  • 21. Example I Results II (top 100K queries) 7% Entertainment_&_Music 8% Arts_&_Humanities 31% Sports 9% Science_&_Mathematics 9% Beauty_&_Style Travel 14% 9% Society_&_Culture 13% Cars_&_Transportation
  • 22.
  • 23. Example I Results III (top 100K queries) initial initial next page next page 2% 11% 2% 2% 2% 15% 15% 11% more specific more specific more generic more generic 5% 5% minor rewrite minor rewrite major rewrite major rewrite 65% 65%
  • 24. Example I Observations Most people that “search” for images are actually browsing! What is the right engagement metric here? Impact on experience design…
  • 25. Example II Web Search [weber & Castillo SIGIR ‘10] Anonymized Profiles of 28 million users (birth year, gender, ZIP) US census data Data aggregated (not per user)
  • 26. Example II Example Queries “Wagner” “Lindsey” “Hal”
  • 27. Example II Examples Female Male (Wagner=composer) (Wagner=spray painter) Hal Lindsey: American evangelist and Christian writer Hal Higdon: American writer and runner (above average education areas)
  • 28. Example II Observations Lots of public data unexplored Information flows? Profiles? Business strategy…
  • 29. Social Media   Clickstream   Favorites   Purchases   Social network analysis   Communities, influence, propagation, & dynamics   Interest/activity-based user modeling   Social “Network” of objects-people-interests   Trend spotting   Psycho-socio-cultural-economic perspectives
  • 30. User Experience   Browsing   Discovery   Personalization   New services?   Eye tracking   Focus group user studies
  • 31. Design Process Algorithm Interface User
  • 32. Analytics and Design Interaction design Analytics Human abilities, needs Implementation Socio-cultural context
  • 33. Human-Centered Analytics User Data Experience analysis Human aspects Machine Learning, Context, User Modeling, Personalization 33
  • 34. Thank you! Alex Jaimes ajaimes@yahoo-inc.com © 2010 A. Jaimes. No portion of these slides can be reproduced without permission. Personal opinions, not of Yahoo! Inc.