Predictive Models of Malicious Behavior in Human Negotiations (bibtex)
by Zahra Nazari, Jonathan Gratch
Abstract:
Human and artificial negotiators must exchange information to find efficient negotiated agreements, but malicious actors could use deception to gain unfair advantage. The misrepresentation game is a game-theoretic formulation of how deceptive actors could gain disproportionate rewards while seeming honest and fair. Previous research proposed a solution to this game but this required restrictive assumptions that might render it inapplicable to realworld settings. Here we evaluate the formalism against a large corpus of human face-to-face negotiations. We confirm that the model captures how dishonest human negotiators win while seeming fair, even in unstructured negotiations. We also show that deceptive negotiators give-off signals of their malicious behavior, providing the opportunity for algorithms to detect and defeat this malicious tactic.
Reference:
Predictive Models of Malicious Behavior in Human Negotiations (Zahra Nazari, Jonathan Gratch), In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016.
Bibtex Entry:
@article{nazari_predictive_2016,
	title = {Predictive {Models} of {Malicious} {Behavior} in {Human} {Negotiations}},
	url = {http://www.ijcai.org/Proceedings/16/Papers/126.pdf},
	abstract = {Human and artificial negotiators must exchange information to find efficient negotiated agreements, but malicious actors could use deception to gain unfair advantage. The misrepresentation game is a game-theoretic formulation of how deceptive actors could gain disproportionate rewards while seeming honest and fair. Previous research proposed a solution to this game but this required restrictive assumptions that might render it inapplicable to realworld settings. Here we evaluate the formalism against a large corpus of human face-to-face negotiations. We confirm that the model captures how dishonest human negotiators win while seeming fair, even in unstructured negotiations. We also show that deceptive negotiators give-off signals of their malicious behavior, providing the opportunity for algorithms to detect and defeat this malicious tactic.},
	journal = {Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence},
	author = {Nazari, Zahra and Gratch, Jonathan},
	month = jul,
	year = {2016},
	keywords = {Social Simulation, Virtual Humans, UARC},
	pages = {855--861}
}
Powered by bibtexbrowser