SlideShare ist ein Scribd-Unternehmen logo
1 von 14
Downloaden Sie, um offline zu lesen
Application of a simple visual attention model to 
     the communication overload problem
    Tags:  Information overload, Community, Social Media, Attention‐
    based Ranking model, visual attention model, Social computing 



Context: European research           Nicolas Maisonneuve, research associate 
project   www.atgentive.com          Centre for Advanced Learning Technologies, 
                                     INSEAD


                                                                         Sept. 2007
Scenario 1: Online Community


          Situation
          • Member of an active community
          • I’m overwhelmed by the unread messages
          • I only have 10 minutes to understand the highlights 
          since my last login. 


Problem : 
  Is there a way to recommend me the most important messages ?
  1) Avoiding uninteresting messages according my interests,
  2) … except if it’s about an important issue in the community
Scenario 2:  Weblogs & Social Media

   Situation 
   • I have subscribed to a lot of interesting blogs 
   • Now I’ m overloaded by too many posts
   • I only have 10 minutes to read all my feeds




   Same Question:
    How rank them and read only the most 
     important ones for me ? 
Research problem

Question:
In a rich information (and social) environment,  How do I 
choose items (message, blog posting, .. )  due to my limited 
resources (e.g. time, or people) ? 


Answer:  
in a rich information environment,  information competes  for the 
user’s attention (c.f Attention Economy)
    I choose the most attractive items

   Conception of an Attention‐based Ranking Model to select 
items
How does an item attract the user’s attention?


      Similarity in vision
      • In a scene (visual rich environment),  which area (item) will 
      attract my attention? 
      • how to predict where my attention will be guided? (Visual 
      Search problem)


Approach 
• Use of a visual search model: “guided Search2.0” (J. Wolfe, 1994)
• Turn visual signals  into  communication signals 
 (Message Reader = eye to  perceive the social activity)
How does an item attract the user’s attention?
  The Visual attention model “Guided Search 2.0”  ‐ 1/2

Saliency (i.e. attractivity) of a signal
The saliency of a signal is computed as the (weighted) sum of 
the saliency for each attractive feature of the signal (e.g. 
color, size, intensity, motion,etc…)

 Attention guiding the 2 types of features:
 • Top‐down features (User guidance)
 e.g.  user searching a green object

 • Bottom‐up features (Stimuli guidance) 
 e.g. flashy object in a dark scene
How does an item attract the user’s attention?
  The Visual attention model  Guided Search 2.0  ‐ 2/2
 Process 
 1) For each attractive feature,  the signals are computed into a 
 Feature Map (i.e. their levels of saliency according to the feature)
 2) Mix of the feature Maps into a global Saliency Map
In your context of communication signals… 




 Question 1: What are the top‐down features (user’s interest profile) ? 
 Question 2: What are the bottom‐up features? (i.e. attractive features 
 without knowing the user’s  intention)
 Question 3: How to compute a feature map?
 Question 4: how to  compute the saliency map? 
Question 1: What are the top‐down features?  
                           (User driven attention)
                                                         User's vigilance profile in a IT 
Top‐down features                                        Community (scenario 1)
• Message’s Topic: focus on specific topics
• Message’s User:  focus on specific users


Simple Vigilance profile P 
For a given context K (e.g. a task to do) ,              VG Market IT Industry Research
     P(k)  =  (C,W)  with:
     ‐ C = The set of concepts c (user, topic) I want 
                                                         User's vigilance profile in a 
     to pay specially attention to in a signal
                                                         Social Network (Scenario3)
     ‐W = their respective levels of  vigilance wc
     for the user 
‐ + Limited capacity H ( ∑wc<H  and wc>w min )
  (I can’t want to pay attention to everything)

                                                            userA     userB      userC
    Vigilance feature map
Question 2: What are attractive bottom‐up features? 
    (i.e. without knowing the user’s  intention)

       1) Exception                                             3) User’s effort
                                   2) About me 
   (temporal/spatial)
                                                          ‐ Type of Medium 
                             ‐ message audience 
 ‐ Unusual sender            focussed on me               (Text < Sound< Video)
                             (mailing‐list vs. personal  
 ‐ Unusual topic
                             message)
‐ Unusual activity (cf 5) 
                                               5) Other’s influence
       4) Urgency                 ‐ Collective attention  (burst of activity)
Lifecycle of the message          ‐ Explicit Attention asked (Subject: 
(3 months<now)                    [URGENT]… )
‐ See also 5)
Question 3: How to compute a feature map?

Computation of a bottom‐up feature map
E = the set of unread items  e1, e2, .. , en 
• For each feature k , each item is computed  by a  function fk to give its 
saliency [0, 1] related to this feature
•A feature map is Mk={fk (e1), fk (e2), .. , fk (en)} 

Example: Simple Computation of the Burst of  (reading) Activity  feature
Definition: Burst = an abnormal high level of activity :  Last week, in average, a 
message has been read  10 times,  but the message A has been read  30 times. 

Computation:
   r(e,∆t) = the number of readings of  the message e during the interval ∆t, 
   m = the mean of r(e, ∆t) for the set of messages read during ∆t
  fburst(e)= 1                                    with 1<t1<t2 the bounds
              0
                    m     m*t1 m* t2      inf
Conclusion
Features of the Ranking Model
• Based on a Visual Attention Model 
     Not only what the user expects ( bottom up feature)
• Use of social factors to rank items. 
• Try to integrate the notions of  limited capacity & vigilance
•Adaptive to the context (possible change of the vigilance profile)

Future work
• Partially implemented  (collective activity observer,  burst of 
  Activity, Vigilance Profile) 
• Need to be evaluated (how to configure  the weight of each 
  Feature in the global saliency map computation?)
Thanks for your attention.  ☺
Scenario 3:  Traditional Communication
Situation :  
• Growth of the user’s connectivity (globalization + internet)
• I’m currently collaborating on a specific task with userA and 
      • 4 hours spent managing emails per day by senior 
  specially with userB. 
         management (Guardian Unlimited Newspaper, 2007) 
• I receive a lot of emails that interrupt my work
      • Economic Impact of the interruption caused by 
          email+online tools:  $588 billion/year  for the Us Economy  
          (Basex Research, 2005)


Problem 
Is there a way to notify me  on a new emails only if :
  ‐ it  is related to my current task (e.g. message from UserB)
  ‐ Or it  delivers unexpected but important information.

Weitere ähnliche Inhalte

Andere mochten auch

Social Attention Management in Online Community using Artificial Agents
Social Attention Management in Online Community using Artificial AgentsSocial Attention Management in Online Community using Artificial Agents
Social Attention Management in Online Community using Artificial AgentsNicolas Maisonneuve
 
Mapping Visual Perceptions using Google Street View
Mapping Visual Perceptions using Google Street ViewMapping Visual Perceptions using Google Street View
Mapping Visual Perceptions using Google Street ViewNicolas Maisonneuve
 
Team activity analysis / visualization
Team activity analysis / visualizationTeam activity analysis / visualization
Team activity analysis / visualizationNicolas Maisonneuve
 
Orientation of the Community's attention and User alignment
Orientation of the Community's attention and User alignmentOrientation of the Community's attention and User alignment
Orientation of the Community's attention and User alignmentNicolas Maisonneuve
 
NoiseTube: Participatory sensing for noise pollution via mobile phones
NoiseTube: Participatory sensing for noise pollution via mobile phonesNoiseTube: Participatory sensing for noise pollution via mobile phones
NoiseTube: Participatory sensing for noise pollution via mobile phonesNicolas Maisonneuve
 
Matching Game Mechanics and Human Computation Tasks in Games with a Purpose
Matching Game Mechanics and Human Computation Tasks in Games with a PurposeMatching Game Mechanics and Human Computation Tasks in Games with a Purpose
Matching Game Mechanics and Human Computation Tasks in Games with a PurposeLuca Galli
 

Andere mochten auch (8)

Social Attention Management in Online Community using Artificial Agents
Social Attention Management in Online Community using Artificial AgentsSocial Attention Management in Online Community using Artificial Agents
Social Attention Management in Online Community using Artificial Agents
 
Social Attention analysis
Social Attention analysisSocial Attention analysis
Social Attention analysis
 
Mapping Visual Perceptions using Google Street View
Mapping Visual Perceptions using Google Street ViewMapping Visual Perceptions using Google Street View
Mapping Visual Perceptions using Google Street View
 
Team activity analysis / visualization
Team activity analysis / visualizationTeam activity analysis / visualization
Team activity analysis / visualization
 
NoiseTube project
NoiseTube projectNoiseTube project
NoiseTube project
 
Orientation of the Community's attention and User alignment
Orientation of the Community's attention and User alignmentOrientation of the Community's attention and User alignment
Orientation of the Community's attention and User alignment
 
NoiseTube: Participatory sensing for noise pollution via mobile phones
NoiseTube: Participatory sensing for noise pollution via mobile phonesNoiseTube: Participatory sensing for noise pollution via mobile phones
NoiseTube: Participatory sensing for noise pollution via mobile phones
 
Matching Game Mechanics and Human Computation Tasks in Games with a Purpose
Matching Game Mechanics and Human Computation Tasks in Games with a PurposeMatching Game Mechanics and Human Computation Tasks in Games with a Purpose
Matching Game Mechanics and Human Computation Tasks in Games with a Purpose
 

Ähnlich wie An attention-based Ranking Model for social media

Who is the Customer? What is Experience? Indispensable Insights to empower yo...
Who is the Customer? What is Experience? Indispensable Insights to empower yo...Who is the Customer? What is Experience? Indispensable Insights to empower yo...
Who is the Customer? What is Experience? Indispensable Insights to empower yo...CHI Poland
 
Silverlight won't save your user experience - you will!
Silverlight won't save your user experience - you will!Silverlight won't save your user experience - you will!
Silverlight won't save your user experience - you will!Shane Morris
 
Exploring communication
Exploring communicationExploring communication
Exploring communicationashok kumar
 
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)Paolo Massa
 
Project Management for Mobile/#MWeb2014/Aheibel
Project Management for Mobile/#MWeb2014/AheibelProject Management for Mobile/#MWeb2014/Aheibel
Project Management for Mobile/#MWeb2014/AheibelAmy Heibel
 
Aol News Review Oct2008
Aol News Review Oct2008Aol News Review Oct2008
Aol News Review Oct2008Mrinal Sharma
 
Teaching 2.0 Learning & Leading in the Digital Age
Teaching 2.0 Learning & Leading in the Digital AgeTeaching 2.0 Learning & Leading in the Digital Age
Teaching 2.0 Learning & Leading in the Digital AgeMatthew Hayden
 
Evaluating ISE (2012)
Evaluating ISE (2012)Evaluating ISE (2012)
Evaluating ISE (2012)Kim Arcand
 
NYU Web Intensive - Week 3 Class 1
NYU Web Intensive - Week 3 Class 1NYU Web Intensive - Week 3 Class 1
NYU Web Intensive - Week 3 Class 1studiokandm
 
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...museums and the web
 

Ähnlich wie An attention-based Ranking Model for social media (13)

Who is the Customer? What is Experience? Indispensable Insights to empower yo...
Who is the Customer? What is Experience? Indispensable Insights to empower yo...Who is the Customer? What is Experience? Indispensable Insights to empower yo...
Who is the Customer? What is Experience? Indispensable Insights to empower yo...
 
Silverlight won't save your user experience - you will!
Silverlight won't save your user experience - you will!Silverlight won't save your user experience - you will!
Silverlight won't save your user experience - you will!
 
ITP / SED Day 6
ITP / SED Day 6ITP / SED Day 6
ITP / SED Day 6
 
Exploring communication
Exploring communicationExploring communication
Exploring communication
 
Insemtives stanford
Insemtives stanfordInsemtives stanford
Insemtives stanford
 
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)
Web2.0: from "I know nothing" to "I know something" in 2 hours (what?!?)
 
Project Management for Mobile/#MWeb2014/Aheibel
Project Management for Mobile/#MWeb2014/AheibelProject Management for Mobile/#MWeb2014/Aheibel
Project Management for Mobile/#MWeb2014/Aheibel
 
Social Media Data analyzis and Semantics for Tourism Understanding
Social Media Data analyzis and Semantics for Tourism UnderstandingSocial Media Data analyzis and Semantics for Tourism Understanding
Social Media Data analyzis and Semantics for Tourism Understanding
 
Aol News Review Oct2008
Aol News Review Oct2008Aol News Review Oct2008
Aol News Review Oct2008
 
Teaching 2.0 Learning & Leading in the Digital Age
Teaching 2.0 Learning & Leading in the Digital AgeTeaching 2.0 Learning & Leading in the Digital Age
Teaching 2.0 Learning & Leading in the Digital Age
 
Evaluating ISE (2012)
Evaluating ISE (2012)Evaluating ISE (2012)
Evaluating ISE (2012)
 
NYU Web Intensive - Week 3 Class 1
NYU Web Intensive - Week 3 Class 1NYU Web Intensive - Week 3 Class 1
NYU Web Intensive - Week 3 Class 1
 
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...
Renee Anderson, Techniques for prioritizing, road-mapping, and staffing your ...
 

Kürzlich hochgeladen

"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 

Kürzlich hochgeladen (20)

E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 

An attention-based Ranking Model for social media