1. 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
2. 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
3. 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 ?
5. 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)
6. 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
9. 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
10. 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)
12. 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?)
14. 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.