Social Network Technology to Evaluate and Facilitate Collaboration - PowerPoint PPT Presentation

1 / 19
About This Presentation
Title:

Social Network Technology to Evaluate and Facilitate Collaboration

Description:

Social Network Technology to Evaluate and Facilitate Collaboration – PowerPoint PPT presentation

Number of Views:54
Avg rating:3.0/5.0
Slides: 20
Provided by: danielolg
Category:

less

Transcript and Presenter's Notes

Title: Social Network Technology to Evaluate and Facilitate Collaboration


1
Social Network Technology to Evaluate and
Facilitate Collaboration
  • Prof. Alex (Sandy) Pentland
  • Daniel Olguin Olguin, PhD Candidate
  • MIT Media Laboratory
  • Human Dynamics Research

NIDA International Forum Technological
Innovations to Build International Research
Capacity Quebec City, Canada, June 15-18, 2007
2
Human Dynamics Research
Group MEDIA
Wearable Computing
LiveNet
Learning Humans
Reality Mining
Sensible Organizations
3
A Brief History of Wearable Computing
  • 1268 Earliest recorded mention of eyeglasses.
  • 1762 First pocket watch.
  • 1966 First wearable computer used to predict
    roulette wheels (Ed Thorp and Claude Shannon,
    MIT).
  • 1968 First digital wrist watch.
  • 1979 Sony Walkman.
  • 1993 Thad Starner starts using his wearable
    computer at MIT.
  • 1997 First International Symposium on Wearable
    Computers.
  • 2003 Motorola introduces a series of wearable
    devices
  • 2007 Nintendo Wiis controller

4
Wearable Computing at the MIT Media Lab
2007
1993
5
Our Approach
  • Social signals
  • From speech engagement, emphasis, mirroring,
    activity
  • From body gesture motion, energy, activity
  • We have been able to identify
  • Central connectors, boundary spanners,
    information brokers and peripheral people in a
    social network
  • The boss in an organization
  • The leader of a team
  • The outcome of negotiations
  • The degree of persuasiveness in speech
  • Group affiliations

Automatically captured group dynamics
6
Real Life Experiments
7
Learning Humans
  • Techniques for learning human behavior in an
    office or social situation.
  • How to automatically capture and model human
    behavior.
  • Influence modeling of multi-agent interactions.
  • Eigenbehavior theory

8
GroupMEDIA
  • The Jerk-O-Meter Is he paying attention?
  • VibeFones that measure tourists interest.
  • Measuring persuasion in elevator pitches.
  • Predicting the outcome of phone calls in call
    centers.
  • Measuring attraction Does she like me?

9
The LiveNet System
  • Distributed modular framework
  • Commodity PDA/cell phone hardware
  • Variety of custom/commercial sensors
  • Real-time data streaming
  • Resource allocation/discovery
  • Local processing for context classification
  • Rapid application prototyping

LiveNet a flexible mobile platform that is at
the same time a long-term health monitor,
context-aware agent, multi-modal feedback
interface for proactive healthcare applications
10
Non-invasive Sensing
  • Movement
  • spectral features, energy, orientation
  • Voice Features
  • energy, pitch, entropy, voicing dynamics
  • Temperature/heat flux
  • Metabolic activity, environmental cues
  • Heart rate
  • IBI, HRV measures, spectral ratios
  • Skin conductance
  • slope analysis, peak detection
  • Behavioral
  • Location, sleep/activity patterns, socialization
    dynamics

BioSense Board
Bluetooth Location Beacon
11
MGH Depression and ECT Treatment Study
Clinical Outcomes
Subjective emotion ratings
LiveNet Depression Rig
Physiology correlations (1 day)
Emotion rating correlations
12
Other Healthcare Applications
  • DiaBetNet
  • Wearable computer for diabetic children
  • Wearable Monitor for Parkinson Disease Treatment
  • Weight management

DiaBetNet Interactive game to monitor blood
glucose levels and make predictions
13
Reality Mining
Eigenbehaviors
14
Sensible Organizations
Scientific management through sensor networks
Understanding Organizational Dynamics
Using social sensors technology to measure
Creativity
Efficiency
Combining social, physical, and digital
information
Innovation
Productivity
15
Sociometric Badges
16
Automatically Measuring Organizational Behavior
Experiments in real organizations
  • Face-to-face interaction
  • Speech features
  • Proximity to other people
  • Relative location
  • Physical activity levels

Sociometric Badge
17
Experimental Results
  • Personal productivity r 0.33
  • face to face - no. of people time
    meeting
  • Job satisfaction r -0.48
  • - total communication
  • How much work did you do r 0.32
  • face to face
  • Quality of group interaction r -0.64
  • - total communication betweeness
  • Email versus face-to-face r -0.55

18
Communication Patterns
  • Top Face-to-face
  • Bottom E-mail

19
Thanks!
  • For more information visit
  • http//hd.media.mit.edu
  • or e-mail us at
  • dolguin_at_media.mit.edu
  • pentland_at_media.mit.edu
Write a Comment
User Comments (0)
About PowerShow.com