Upload
cael
View
34
Download
0
Embed Size (px)
DESCRIPTION
Towards a manipulative mediator Lecture for Statistical Methods (89-326). Yehoshua (Yoshi) Gev [email protected] Joint work with: S. Kraus, M. Gelfand, J. Wilkenfeld & E. Salmon. Outline. Background on negotiation and mediation Our goal Agent design Experiments and results Conclusions. - PowerPoint PPT Presentation
Citation preview
1
Towards a manipulative mediatorLecture for Statistical Methods (89-326)
Yehoshua (Yoshi) [email protected]
Joint work with:S. Kraus, M. Gelfand, J. Wilkenfeld & E. Salmon
2
Outline Background on negotiation and mediation Our goal Agent design Experiments and results Conclusions
3
Background
4
Domain of negotiation Human-to-human negotiation
Closed set of issues with discrete solution values
Private utility function
For example, in our neighbors’ dispute – noise issue with these solution values:
“Tyler will continue to be loud” “Tyler will be quiet after 1am” “Tyler will be quiet after 12am” etc.
5
Mediation Assistance from a third party
Mediation styles: facilitation
organize logistics (e.g., communication channel) formulation
propose new solutions encourage to move towards agreement
manipulation offer incentives or impose penalties
[Wilkenfeld et al., 2005]
6
Previous work Very few automated mediators:
PERSUADER [Sycara, 1991]
based on CBR (on an existing knowledge base) AutoMed [Chalamish & Kraus, 2009]
a formulative mediator rule based monitors the negotiations and proposes possible solutions qualitative model for preferences representation
7
Our Goal
8
Motivation Design a manipulative mediator
Create a model that includes incentives and penalties Decide how to make decisions
The big question: Can the authority be utilized to assist the parties?
9
Social science aspect The research is a collaborative work with
political science and psychology groups
We had to negotiate over the settings Should we allow the participants to speak freely?
Or, restrict them to a closed-list of sentences? Should our interface act as a DSS?
utilities calculator history of actions
How can we force participants to use the interface?
10
Experiments setting Natural negotiations:
participants negotiate via video-conferencing a realistic scenario (neighbors’ dispute) very simple computerized system
only an interface to exchange offers no utility calculator a mediator agent can participate as a third party GENIUS environment [Koen et al., 2009]
11
12
Agent Design
13
Pilot Tested the system and the scenario
Tested AutoMed in the new settings
Problems: AutoMed sent very few suggestions AutoMed’s suggestions were often not relevant
14
Modifications to AutoMed Choose suggestions similar to last offers
Treat close ranks as same utility
Treat partial offers as 60% of their maximal score
15
Experiments
16
Experiment 1 Two groups
Control/Baseline: without mediator Treatment/Tested: with mediator
Comparison between groups tested parameters:
dur – negotiation’s duration (seconds) score – each parties’ score diff – difference between parties’ scores sat – parties’ satisfaction from result (questionnaire) aid – measure of mediator’s assistance (questionnaire)
17
Experiment 1 – ResultsN dur sum diff satA aidA satB aidB
1. No mediator 15 09:33 1224 188 4.2 4.2
2. Simple mediator 14 10:57 1192 74 4 1.7 4.0 1.5
Hypothesis: diff1 – diff2 = 0
Unpaired two-tailed T-Test t = 2.0904, df = 27 p = 0.044 < 0.05
Conclusion: diff1 != diff2
21
11
21
NNs
xxt
18
Experiment 1 – Results (cont.) Only one significant advantage for the mediator
diff was lower with a mediator
Many participants disregarded the mediator
How can we make them consider the mediator?
19
20
Experiment 2 We implemented an animated avatar
face appearing on the interface text-to-speech capabilities opening statement accompanying text to suggestions
Intended to draw the participants’ attention
How did it affect the outcomes?
21
Experiment 2 – ResultsN dur sum diff sat aid
1. No mediator 15 09:33 1224 188 4.23
2. Simple mediator 14 10:57 1193 74 4.04 1.62
3. Animated mediator 12 13:31 1245 103 4.17 2.70
Hypothesis: aid2 – aid3 = 0
Unpaired two-tailed T-Test p = 0.003 < 0.01
Coclusion: aid2 != aid3
22
Experiment 2 – Results (cont.)Correlations:
Hypothesis: aid is uncorrelated with score (r = 0) Pearson correlation: r = 0.43 for N = 24: t = 2.234 Using T-test: p = 0.035 < 0.05
But pairs of samples are dependant (really, N < 24) besides, we cannot tell the direction of the influence
Maybe a different sig. test would work (Fisher trans.)
score age sat aid score 1 age -0.22 1 sat 0.30 0.16 1 aid 0.43 -0.24 0.01 1
21
2
r
Nrt
23
Experiment 2 – Results (cont.) The participants paid more attention
aid was higher with the avatar
Those who paid attention got higher scores significant correlation between aid and score however, aid and sat were not correlated
But, they still didn’t fully utilize the suggestions average score didn’t improve significantly
What should be done next?
24
Conclusions
25
Difficulties Current problems:
participants disregard the mediator offers they are involved in the video discussion they cannot see the high utility of the mediator’s offers solution?: more persuading mediator / a utility calculator
almost all participants reach agreement what would be the role of the manipulator?
experiments with human participants are expensive solution?: use peer-designed agents (PDA) to test the
mediator before experimenting with humans [Lin et al., 2010]
26
What’s next? Search for a setting that can exploit the mediator
Model incentives and penalties
Design a manipulator in that model
More experiments…
27
Summary Even generic agents are restricted by their model
Humans are not fully rational don’t calculate their expected score higher scores don’t mean higher satisfaction
The environment affect the mediator’s influence
28
Thank you…