Chang Heon Lee
June 13, 2013
Studying Social Selection vs Social Influence
in Virtual Financial Communities
 Dynamics of Networks and Behavior
 Selection vs Influence
 Studying Selection vs Influence
 Stochastic Actor-oriented...
3
Dynamics of Networks and Behavior
 Social network dynamics depends on individual behavioral
characteristics.
 Homophil...
4
Selection vs Influence
 Selection
 Individuals make changes to their social ties as a result
of the behavior or charac...
5
Studying Selection vs Influence
How can we separate cause and effect?
Net(tn)
Structural Effects
Behavioral Effects
Net(...
6
Stochastic Actor-oriented Model
 Assumption of stochastic actor-oriented models
 Network actors drive the process: ind...
7
Stochastic Actor-oriented Model-cont.
 ( , )i k ikk
f x s x   
 Network micro step
 individual decisions optio...
8
Stochastic Actor-oriented Model-cont.
 Model Parameters
 Estimated from observed data
 Stochastic simulation models
•...
9
 Organizational scholars have framed the advice network in
terms of information transmission, knowledge transfer,
and j...
10
Data
 Snowball Sample from the largest Australian VFCs
 The network consists of 707 active users.
 Panel Data
 The ...
11
Estimation Results
[Representation of Selection and Influence Effects]
Baseline Network Structure
Contribution Behavior...
Results(1): Structural Effects
Effects
Parameter
Estimate
Standard Error p-value
Endogenous Effects
Out-degree -2.798 0.28...
1313
Results(2): Selection
Effects
Parameter
Estimate
Standard
Error
p-value
Contribution Quantity Effects
Contribution Qu...
1414
Results(2): Selection
 Contribution behavior as antecedent to advice network structure
 Individuals who are salient...
1515
Results(3): Influence
Effects
Parameter
Estimate
Standard
Error
p-value
Rate Function
Rate of Contribution Quantity C...
1616
Results(3): Influence
 Contribution behavior as outcome of advice network structure
 The greater the number of inco...
1717
Conclusions
 Influence rather than Selection
 Individual adjust their level of contribution to that
their peers (pa...
Upcoming SlideShare
Loading in...5
×

Studying Social Selection vs Social Influence in Virtual Financial Communities

934

Published on

2013 한국데이터사이언스 창립기념 심포지움 발표 - 삼성화재 이창헌

Published in: Technology, Business
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
934
On Slideshare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
0
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Studying Social Selection vs Social Influence in Virtual Financial Communities

  1. 1. Chang Heon Lee June 13, 2013 Studying Social Selection vs Social Influence in Virtual Financial Communities
  2. 2.  Dynamics of Networks and Behavior  Selection vs Influence  Studying Selection vs Influence  Stochastic Actor-oriented Model  Advice Network  Data  Estimation Results 2 Outline
  3. 3. 3 Dynamics of Networks and Behavior  Social network dynamics depends on individual behavioral characteristics.  Homophily vs. Heterophily  But individuals’ behavior can depend on the network.  Assimilation vs. Differentiation
  4. 4. 4 Selection vs Influence  Selection  Individuals make changes to their social ties as a result of the behavior or characteristics of the ego, the alter, and the dyad.  Influence  Individuals’ behavior changes as a function of interaction with alters.
  5. 5. 5 Studying Selection vs Influence How can we separate cause and effect? Net(tn) Structural Effects Behavioral Effects Net(tn+1) Beh(tn) Beh(tn+1 )
  6. 6. 6 Stochastic Actor-oriented Model  Assumption of stochastic actor-oriented models  Network actors drive the process: individual decisions; • decisions about network selection or termination • decisions about own behavior  Longitudinal versions of Exponential Random Graph Model (ERGM)  Assumption: network change driven by change in tie variables
  7. 7. 7 Stochastic Actor-oriented Model-cont.  ( , )i k ikk f x s x     Network micro step  individual decisions options - change tie variable to one other actor - or change nothing  maximize an objective function with respect to the network configuration.  The probability that actor i changes his ties variable with j is 1 exp( ( , ( 젨? ) ( , ) exp( ( , ( 젨? )       i ij n i k f x i j p x f x i j ↝ ↝
  8. 8. 8 Stochastic Actor-oriented Model-cont.  Model Parameters  Estimated from observed data  Stochastic simulation models •Markov Chain Monte Carlo(MCMC) algorithm •Approximate the solution of the Method of Moment  Parameter Estimation  Choose statistics  Obtain parameters such that the expected values of the statistics are equal to the observed values  Expected values are approximated as the averages over a lot of simulated network  Observed values are calculated from the dataset (target values)↝
  9. 9. 9  Organizational scholars have framed the advice network in terms of information transmission, knowledge transfer, and joint problem solving.  Simply, stock message board sites include; Advice Network in Virtual Financial Community I K J I K J
  10. 10. 10 Data  Snowball Sample from the largest Australian VFCs  The network consists of 707 active users.  Panel Data  The network data is divided into three successive two-month periods.
  11. 11. 11 Estimation Results [Representation of Selection and Influence Effects] Baseline Network Structure Contribution Behavior Changes in Individual Contribution Behavior Changes in Peer Network Time 1 Time 2 Structural Effects Behavioral Tendencies
  12. 12. Results(1): Structural Effects Effects Parameter Estimate Standard Error p-value Endogenous Effects Out-degree -2.798 0.287 <.001*** Reciprocity 2.753 0.135 <.001*** Popularity-Alter 0.487 0.073 <.001*** Activity-Alter -0.084 0.022 <.001*** In-In Degree Assortativity 0.057 0.015 <.001*** Out -Out Degree Assortativity -0.035 0.017 <0.05* In-Out Degree Assortativity 0.085 0.02 0.42 Out-In Degree Assortativity 0.005 0.011 <.001*** 1212 *p <0.05; **p <0.01; ***p <0.001
  13. 13. 1313 Results(2): Selection Effects Parameter Estimate Standard Error p-value Contribution Quantity Effects Contribution Quantity-Alter 0.328 0.127 <.001** Contribution Quantity -Ego -0.352 0.201 0.080 Contribution Quantity -Similarity 0.443 0.467 0.949 *p <0.05; **p <0.01; ***p <0.001
  14. 14. 1414 Results(2): Selection  Contribution behavior as antecedent to advice network structure  Individuals who are salient in terms of contribution quantity are more likely to be sought as an advice partner for repeated advice exchanges over time.  People don’t select similar others when seeking information.
  15. 15. 1515 Results(3): Influence Effects Parameter Estimate Standard Error p-value Rate Function Rate of Contribution Quantity Change 1 192.130 17.352 <.001*** Rate of Contribution Quantity Change 2 158.051 14.952 <.001*** Rate of Contribution Quantity Change 3 175.543 15.093 <.001*** Linear Shape 0.1312 0.2834 0.463 Quadratic Shape -0.0103 0.0155 0.665 Contribution Quantity- In-degree 0.0096 0.0028 <.001*** Contribution Quantity- Out-degree -0.0094 0.0124 0.758 Contribution Quantity Total Similarity 0.4754 0.2210 <0.05* *p <0.05; **p <0.01; ***p <0.001
  16. 16. 1616 Results(3): Influence  Contribution behavior as outcome of advice network structure  The greater the number of incoming advice ties to an individual, the higher the quantity of contributions he makes to the community over time. Thus, individuals adjust their level of contribution quantity as a result of their advice tie formation.  But, individuals contribution in terms of the number of postings are likely to become similar to that of other partners.
  17. 17. 1717 Conclusions  Influence rather than Selection  Individual adjust their level of contribution to that their peers (patterns of assimilation).  There is no patterns of homophily.

×