Skip to main content

Advertisement

SpringerLink
Log in

NegoChat-A: a chat-based negotiation agent with bounded rationality

  • Published:
Autonomous Agents and Multi-Agent Systems Aims and scope Submit manuscript

Abstract

To date, a variety of automated negotiation agents have been created. While each of these agents has been shown to be effective in negotiating with people in specific environments, they typically lack the natural language processing support required to enable real-world types of interactions. To address this limitation, we present NegoChat-A, an agent that incorporates several significant research contributions. First, we found that simply modifying existing agents to include an natural language processing module is insufficient to create these agents. Instead, agents that support natural language must have strategies that allow for partial agreements and issue-by-issue interactions. Second, we present NegoChat-A’s negotiation algorithm. This algorithm is based on bounded rationality, and specifically anchoring and aspiration adaptation theory. The agent begins each negotiation interaction by proposing a full offer, which serves as its anchor. Assuming this offer is not accepted, the agent then proceeds to negotiate via partial agreements, proposing the next issue for negotiation based on people’s typical urgency, or order of importance. We present a rigorous evaluation of NegoChat-A, showing its effectiveness in two different negotiation roles.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. The GENIUS and ANAC websites can be reached though http://mmi.tudelft.nl/negotiation/index.php/Genius.

  2. We intentionally use the term score instead of utility because the score is the number of points the player can attain from a game’s outcome. While our agent maximizes the scoring function, this is not necessarily the case for human players. People’s utility functions may be based on factors not encapsulated by the scoring function. As we cannot model these unknowns, we refer to score and not utility.

  3. www.json.org.

  4. The state-of-the-art in NLU for dialog systems is sequence classification [32]. We decided against this option because it requires too much labeling effort: while in multi-label classification you only need to label each sentence, in sequence classification you must label each fraction of a sentence. After deciding to use MLC, we did preliminary experiments in which we tried various state-of-the-art approaches to MLC [33–37]. We also tried several kinds of base binary classifiers (Support Vector Machines, Bayesian Classifiers and Random Decision Forests), a classifier based on language models [38] and a spell-checker. We found out that the combination of HOMER with Modified Balanced Winnow, described above, had the best performance in terms of both classification accuracy and run-time.

  5. We tried more sophisticated features, such as pairs of non-adjacent words, but this didn’t improve performance.

  6. We used Amazon Turk as a convenient way to get sentences for training the NLU component. We could have used other ways, such as letting experts invent sentences and tag them. However, based on past experience we decided that using Turk is much cheaper. The total cost of gathering data from 22 people was only approximately $30 dollars.

  7. Sentence-level accuracy is the number of sentences whose classification was exactly correct (i.e. the set of dialog acts returned by the MLC is identical to the correct set), divided by the total number of sentences. The 72 % accuracy was calculated using fivefold cross-validation on the set of 775 tagged sentences. Sentence-level accuracy is the strictest possible performance measure. In other measures, such as precision and recall, the performance of our NLU was higher.

  8. A copy of the KBAgent and NegoChat-A agents are found at: http://biu-ai.com:4014/demo.

References

  1. Hoppman, P. T. (1996). The negotiation process and the resolution of international conflicts. Columbia: University of South Carolina Press.

    Google Scholar 

  2. Byde, A., Yearworth, M., Chen, K.-Y., Bartolini, C., Aut ONA. (2003). A system for automated multiple 1–1 negotiation. In International Conference on Electronic Commerce.

  3. Jonker, C. M., Robu, V., & Treur, J. (2007). An agent architecture for multi-attribute negotiation using incomplete preference information. Autonomous Agents and Multi-Agent Systems, 15(2), 221–252.

    Article  Google Scholar 

  4. Lin, R., & Kraus, S. (2010). Can automated agents proficiently negotiate with humans? Communications of the ACM, 53(1), 78–88.

    Article  Google Scholar 

  5. Lin, R., Kraus, S., Wilkenfeld, J., & Barry, J. (2008). Negotiating with bounded rational agents in environments with incomplete information using an automated agent. Artificial Intelligence, 172(6–7), 823–851.

    Article  MATH  MathSciNet  Google Scholar 

  6. Oshrat, Y., Lin, R., Kraus, S. (2009). Facing the challenge of human-agent negotiations via effective general opponent modeling, In AAMAS.

  7. Peled, N., Gal, Y. K., Kraus, S. (2011). A study of computational and human strategies in revelation games. In AAMAS.

  8. Peled, N., Gal, Y. K., Kraus, S. (2014). A study of computational and human strategies in revelation games. Autonomous Agents and Multi-Agent Systems 1–25.

  9. Reyhan, A., & Pinar, Y. (2012). Learning opponents preferences for effective negotiation: An approach based on concept learning. Journal of Autonomous Agents and Multi-Agent Systems, 24(1), 104–140.

  10. Rosenfeld, A., Zuckerman, I., Segal-Halevi, E., Drein, O., Kraus, S. (2014). Negochat: a chat-based negotiation agent. In International conference on Autonomous Agents and Multi-Agent Systems, AAMAS ’14 (pp. 525–532).

  11. Kahneman, D. (1992). Reference points, anchors, norms, and mixed feelings. Organizational Behavior and Human Decision Processes, 51(2), 296–312.

    Article  Google Scholar 

  12. Kristensen, H., & Garling, T. (1997). The effects of anchor points and reference points on negotiation process and outcome. Organizational Behavior and Human Decision Processes, 71(1), 85–94.

    Article  Google Scholar 

  13. Selten, R. (1998). Aspiration adaptation theory. Journal of Mathematical Psychology, 42, 1910–214.

    Article  Google Scholar 

  14. Coen, M.H. (1998). Design principles for intelligent environments. In AAAI/IAAI.

  15. Cohen, P. R. (1992). The role of natural language in a multimodal interface. In UIST.

  16. Kenny, P., Hartholt, A., Gratch, J., Swartout, W., Traum, D., Marsella, S., Piepol, D. (2007). Building interactive virtual humans for training environments. In I/ITSEC.

  17. Shneiderman, B., & Plaisant, C. (2004). Designing the user interface: Strategies for effective human-computer interaction. Noida: Pearson Education India.

    Google Scholar 

  18. Traum, D., Marsella, S., Gratch, J., Lee, J., Hartholt, A. (2008). Multi-party, multi-issue, multi-strategy negotiation for multi-modal virtual agents. In Intelligent Virtual Agents (pp. 117–130).

  19. Baarslag, T., Fujita, K., Gerding, E. H., Hindriks, K. V., Ito, T., Jennings, N. R., et al. (2011). Evaluating practical negotiating agents: Results and analysis of the 2011 international competition. Artificial Intelligence, 198(2013), 73–103.

    Google Scholar 

  20. Lin, R., Kraus, S., Baarslag, T., Tykhonov, D., Hindriks, K. V., & Jonker, C. M. (2014). Genius: An integrated environment for supporting the design of generic automated negotiators. Computational Intelligence, 30(1), 48–70.

    Article  MathSciNet  Google Scholar 

  21. Zuckerman, I., Rosenfeld, A., Segal-Halevi, E., Drein, O., Kraus, S. (2013). Towards automated negotiation agents that use chat interfaces. In ANAC.

  22. Bac, M., & Raff, H. (1996). Issue-by-issue negotiations: The role of information and time preference. Games and Economic Behavior, 13(1), 125–134.

    Article  MATH  MathSciNet  Google Scholar 

  23. Busch, L.-A., & Horstmann, I. (1997). A comment on issue-by-issue negotiations. Games and Economic Behavior, 19(1), 144–148.

    Article  MATH  MathSciNet  Google Scholar 

  24. Chen, M. K. (2002). Agendas in multi-issue bargaining: When to sweat the small stuff. Cambridge: Tech. rep Harvard Department of Economics.

    Google Scholar 

  25. Sofer, I., Sarne, D., Hassidim, A. (2012). Negotiation in exploration-based environment. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence.

  26. Rosenfeld, A., & Kraus, S. (2012). Modeling agents based on aspiration adaptation theory. Autonomous Agents and Multi-Agent Systems, 24(2), 221–254.

    Article  Google Scholar 

  27. Simon, H. A. (1957). Models of Man. New York: Wiley.

    MATH  Google Scholar 

  28. Osborne, M. J., & Rubinstein, A. (1994). A course in game theory. Cambridge: MIT Press.

    MATH  Google Scholar 

  29. Jurafsky, D., & Martin, J. H. (2008). Speech and language processing (2nd ed.). Upper Saddle River: Prentice Hall.

    Google Scholar 

  30. Tsoumakas, G., Katakis, I., Vlahavas, I. (2008). Effective and efficient multilabel classification in domains with large number of labels. In Proceedings of the ECML/PKDD 2008 Workshop on Mining Multidimensional Data (MMD’08).

  31. Carvalho, V. R., Cohen, W. W. (2006). In KDD (pp. 548–553).

  32. Hahn, S., Dinarelli, M., Raymond, C., Lefevre, F., Lehnen, P., de Mori, R., et al. (2011). IEEE Transactions on Audio, Speech, and Language Processing, 19(6), 1569–1583.

  33. Crammer, K., Dekel, O., Keshet, J., Shalev-Shwartz, S., & Singer, Y. (2006). Online passive-aggressive algorithms. Journal of Machine Learning Research, 7, 551–585.

    MATH  MathSciNet  Google Scholar 

  34. Tang, L., Rajan, S., Narayanan, V. K. (2009). Large scale multi-label classification via metalabeler. In Proceedings of the 18th international conference on World wide web, WWW ’09, ACM (pp. 211–220).

  35. Morbini, F., Sagae, K. (2011). Joint identification and segmentation of domain-specific dialogue acts for conversational dialogue systems. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics (pp. 95–100).

  36. Madjarov, G., Kocev, D., Gjorgjevikj, D., & Džeroski, S. (2012). An extensive experimental comparison of methods for multi-label learning. Pattern Recognition, 45(9), 3084–3104.

    Article  Google Scholar 

  37. Kocev, D., Vens, C., Struyf, J., & Džeroski, S. (2013). Tree ensembles for predicting structured outputs. Pattern Recognition, 46(3), 817–833.

    Article  Google Scholar 

  38. Leuski, A., & Traum, D. (2008). A statistical approach for text processing in virtual humans. Tech. rep, University of Southern California, Institute for Creative Technologies.

  39. Dagan, I., Roth, D., Sammons, M., & Zanzotto, F. M. (2013). Recognizing textual entailment: Models and applications. Synthesis Lectures on Human Language Technologies, 6(4), 1–220.

    Article  Google Scholar 

  40. Baarslag, T., Hindriks, K., & Jonker, C. M. (2014). Effective acceptance conditions in real-time automated negotiation. Decision Support Systems, 60, 68–77.

    Article  Google Scholar 

  41. Jonker, C.M., Robu, V., Treur, J. An agent architecture for multi-attribute negotiation using incomplete preference information. Autonomous Agents and Multi-Agent Systems Journal 15.

  42. Visser, W., Aydogan, R., Hindriks, K., Jonker, C. M. (2012). A framework for qualitative multi-criteria preferences. In 4th International Conference on Agents and Artificial Intelligence.

  43. Azaria, A., Rabinovich, Z., Kraus, S., Goldman, C. V., Gal, Y. (2012). Strategic advice provision in repeated human-agent interactions. In AAAI.

  44. Wilkenfeld, J., Kraus, S., Holley, K. M., & Harris, M. A. (1995). Genie: A decision support system for crisis negotiations. Decision Support Systems, 14(4), 369–391.

    Article  Google Scholar 

  45. Pommeranz, A., Wiggers, P., Brinkman, W. P., Jonker, C. M. Social acceptance of negotiation support systems: Scenario-based exploration with focus groups and online survey, Cognition, Technology and Work.

  46. Lin, R., Gev, Y., & Kraus, S. (2011). Bridging the gap: Face-to-face negotiations with an automated mediator. IEEE Intelligent Systems, 26(6), 40–47.

    Article  Google Scholar 

  47. Chalamish, M., & Kraus, S. (2012). Automed: An automated mediator for multi-issue bilateral negotiations. Autonomous Agents and Multi-Agent Systems, 24(3), 536–564.

    Article  Google Scholar 

  48. Rahwan, I., Ramchurn, S. D., Jennings, N. R., Mcburney, P., Parsons, S., & Sonenberg, L. (2003). Argumentation-based negotiation. The Knowledge Engineering Review, 18(4), 343–375.

    Article  Google Scholar 

  49. Rosenfeld, A., Kraus, S. (2012). Providing arguments in discussions based on the prediction of human argumentative behavior. In AAAI.

Download references

Acknowledgments

This work was supported in part by ERC Grant #267523, J-FBI-10-009 and MURI Grant #W911NF-08-1-0144. Sarit Kraus is also affiliated with UMIACS.

Author information

Authors and Affiliations

  1. Department of Industrial Engineering, Jerusalem College of Technology, 91160, Jerusalem, Israel

    Avi Rosenfeld

  2. Department of Industrial Engineering and Management, Ariel University, 40700, Ariel, Israel

    Inon Zuckerman

  3. Department of Computer Science, Bar-Ilan University, 52900, Ramat Gan, Israel

    Erel Segal-Halevi, Osnat Drein & Sarit Kraus

Authors
  1. Avi Rosenfeld
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Inon Zuckerman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Erel Segal-Halevi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Osnat Drein
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sarit Kraus
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Avi Rosenfeld.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rosenfeld, A., Zuckerman, I., Segal-Halevi, E. et al. NegoChat-A: a chat-based negotiation agent with bounded rationality. Auton Agent Multi-Agent Syst 30, 60–81 (2016). https://doi.org/10.1007/s10458-015-9281-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10458-015-9281-9

Keywords

Search

Navigation