An Expert-Model & Machine Learning Hybrid Approach to Predicting Human-Agent Negotiation Outcomes (bibtex)
by Johnathan Mell, Markus Beissinger, Jonathan Gratch
Abstract:
We present the results of a machine-learning approach to the analysis of several human-agent negotiation studies. By combining expert knowledge of negotiating behavior compiled over a series of empirical studies with neural networks, we show that a hybrid approach to parameter selection yields promise for designing -more effective and socially intelligent agents. Specifically, we show that a deep feedforward neural network using a theory-driven three-parameter model can be effective in predicting negotiation outcomes. Furthermore, it outperforms other expert-designed models that use more parameters, as well as those using other, more limited techniques (such as linear regression models or boosted decision trees). We anticipate these results will have impact for those seeking to combine extensive domain knowledge with more automated approaches in human-computer negotiation.
Reference:
An Expert-Model & Machine Learning Hybrid Approach to Predicting Human-Agent Negotiation Outcomes (Johnathan Mell, Markus Beissinger, Jonathan Gratch), In Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents - IVA '19, ACM Press, 2019.
Bibtex Entry:
@inproceedings{mell_expert-model_2019,
	address = {Paris, France},
	title = {An {Expert}-{Model} \& {Machine} {Learning} {Hybrid} {Approach} to {Predicting} {Human}-{Agent} {Negotiation} {Outcomes}},
	isbn = {978-1-4503-6672-4},
	url = {http://dl.acm.org/citation.cfm?doid=3308532.3329433},
	doi = {10.1145/3308532.3329433},
	abstract = {We present the results of a machine-learning approach to the analysis of several human-agent negotiation studies. By combining expert knowledge of negotiating behavior compiled over a series of empirical studies with neural networks, we show that a hybrid approach to parameter selection yields promise for designing -more effective and socially intelligent agents. Specifically, we show that a deep feedforward neural network using a theory-driven three-parameter model can be effective in predicting negotiation outcomes. Furthermore, it outperforms other expert-designed models that use more parameters, as well as those using other, more limited techniques (such as linear regression models or boosted decision trees). We anticipate these results will have impact for those seeking to combine extensive domain knowledge with more automated approaches in human-computer negotiation.},
	booktitle = {Proceedings of the 19th {ACM} {International} {Conference} on {Intelligent} {Virtual} {Agents}  - {IVA} '19},
	publisher = {ACM Press},
	author = {Mell, Johnathan and Beissinger, Markus and Gratch, Jonathan},
	month = jul,
	year = {2019},
	keywords = {Virtual Humans, UARC},
	pages = {212--214}
}
Powered by bibtexbrowser