Short presentation at Dagstuhl seminar on Physical-Cyber-Social Computing, September 29 to October 4, 2013.
http://www.dagstuhl.de/en/program/calendar/semhp/?semnr=13402
5. Table 1: Correlation Coefficients of dimensions
Dispersion Engagement Contribution Initiation Quality Popularity
Dispersion 1.000 0.277 0.168 0.389 0.086 0.356
Engagement 0.277 1.000 0.939** 0.284 0.151 0.926**
Contribution 0.168 0.939** 1.000 0.274 0.086 0.909**
Initiation 0.389 0.284 0.274 1.000 -0.059 0.513
Quality 0.086 0.151 0.086 -0.059 1.000 0.065
Popularity 0.356 0.926** 0.909** 0.513 0.065 1.000
Behaviour analysis of online communities
§ Bottom Up analysis
§ Every community member is
classified into a “role”
§ Unknown roles might be
identified
§ Copes with role changes
over time
ini#ators
lurkers
followers
leaders
Structural, social network,
reciprocity, persistence,
participation
Feature levels change with the
dynamics of the community
Associations of roles with a collection of
feature-to-level mappings
e.g. in-degree -> high, out-degree -> high
Run rules over each user’s features
and derive the community role
composition
Table 1: Correlation Coefficients of dimensions
Dispersion Engagement Contribution Initiation Quality Popularity
Dispersion 1.000 0.277 0.168 0.389 0.086 0.356
Engagement 0.277 1.000 0.939** 0.284 0.151 0.926**
Contribution 0.168 0.939** 1.000 0.274 0.086 0.909**
Initiation 0.389 0.284 0.274 1.000 -0.059 0.513
Quality 0.086 0.151 0.086 -0.059 1.000 0.065
Popularity 0.356 0.926** 0.909** 0.513 0.065 1.000
Table 1: Correlation Coefficients of dimensions
Dispersion Engagement Contribution Initiation Quality Popularity
Dispersion 1.000 0.277 0.168 0.389 0.086 0.356
Engagement 0.277 1.000 0.939** 0.284 0.151 0.926**
Contribution 0.168 0.939** 1.000 0.274 0.086 0.909**
Initiation 0.389 0.284 0.274 1.000 -0.059 0.513
Quality 0.086 0.151 0.086 -0.059 1.000 0.065
Popularity 0.356 0.926** 0.909** 0.513 0.065 1.000
Figure 7: Cumulative density functions of each dimension showing Figure 8: Boxplots of the feature distributions
6. Correlations
§ Between different behaviour
roles
0.0 0.2 0.4 0.6 0.8 1.0
0.00.20.40.60.81.0
Churn Rate
FPR
TPR
0.0 0.2 0.4 0.6 0.8 1.0
0.00.20.40.60.81.0
User Count
FPR
TPR
0.00.20.40.60.81.0
TPR
§ Between behaviour and activity
§ Between behaviours and community
health
15. Need to change consumption behaviour
Nov 2012
• Behaviour can be changed
• Individual/community approaches
• Multiple motivating factors
• Behaviour change is sustainable
key findings
• Quantitative impact of specific changes
• Socio-demographic factors
• Gas vs electricity vs water
• Cost-effectiveness of interventions
• Longevity of change
gaps
August 2012
16. • Personal energy-saving targets
• Community/social initiative lead to long-term change
• Dynamic pricing schemes don’t always work
• The “rebound effect” can emerge from short-term measures
• Role of technology, age, economic situation, culture, marketing, etc.
• Consumer ability to handle new technology, capital cost, trade-offs, and
expected convenience
18. Feedback
§ What’s the optimal level of
detail ?
§ What feedback is suitable
for what type of
consumer?
§ What feedback tools?
What visualisations?