Strategical Argumentative Agent for Human Persuasion

Automated agents should be able to persuade people in the same way people persuade each other via dialogs. Today, automated persuasion modeling and research use unnatural assumptions regarding persuasive interaction, which creates doubt regarding their applicability for real-world deployment with people. In this work we present a novel methodology for persuading people through argumentative dialogs. Our methodology combines theoretical argumentation modeling, machine learning and Markovian optimization techniques that together result in an innovative agent named SPA. Two extensive field experiments, with more than 100 human subjects, show that SPA is able to persuade people significantly more often than a baseline agent and no worse than people are able to persuade each other.

[1]  C. Cayrol,et al.  On the Acceptability of Arguments in Bipolar Argumentation Frameworks , 2005, ECSQARU.

[2]  Sarit Kraus,et al.  Reaching Agreements Through Argumentation: A Logical Model and Implementation , 1998, Artif. Intell..

[3]  Iyad Rahwan,et al.  Behavioral Experiments for Assessing the Abstract Argumentation Semantics of Reinstatement , 2010, Cogn. Sci..

[4]  E. Sklar,et al.  An Argumentation Engine : ArgTrust , 2012 .

[5]  Sarit Kraus,et al.  Providing Arguments in Discussions Based on the Prediction of Human Argumentative Behavior , 2015, AAAI.

[6]  Ariel Rubinstein,et al.  A study in the pragmatics of persuasion: a game theoretical approach , 2006 .

[7]  Stuart M. Shieber,et al.  Agent decision-making in open mixed networks , 2010, Artif. Intell..

[8]  Alun D. Preece,et al.  Information Based Argumentation Heuristics , 2006, ArgMAS.

[9]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[10]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[11]  Avi Rosenfeld,et al.  NegoChat-A: a chat-based negotiation agent with bounded rationality , 2015, Autonomous Agents and Multi-Agent Systems.

[12]  Marie-Francine Moens,et al.  Argumentation Mining: Where are we now, where do we want to be and how do we get there? , 2013, FIRE.

[13]  F. Scholz.  Maximum Likelihood Estimation , 2006 .

[14]  Michael Wooldridge,et al.  Weighted argument systems: Basic definitions, algorithms, and complexity results , 2011, Artif. Intell..

[15]  Cristian Danescu-Niculescu-Mizil,et al.  Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions , 2016, WWW.

[16]  Sarit Kraus,et al.  Principles of Automated Negotiation , 2014 .

[17]  Henry Prakken,et al.  Formal systems for persuasion dialogue , 2006, The Knowledge Engineering Review.

[18]  Chunyan Miao,et al.  An Adaptive Computational Model for Personalized Persuasion , 2015, IJCAI.

[19]  Iyad Rahwan,et al.  Experimental Assessment of Aggregation Rules in Argumentation-enabled Collective Intelligence , 2016, ArXiv.

[20]  Yang Gao,et al.  An Overview of Argumentation Frameworks for Decision Support , 2015, GKR.

[21]  Pietro Baroni,et al.  Automatic evaluation of design alternatives with quantitative argumentation , 2015, Argument Comput..

[22]  Magdalena Kacprzak,et al.  Perseus. Software for Analyzing Persuasion Process , 2009, Fundam. Informaticae.

[23]  Christian Stab,et al.  Detecting Argument Components and Structures , 2015 .

[24]  Iryna Gurevych,et al.  Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM , 2016, ACL.

[25]  Chris Reed,et al.  Strategic Argumentation in Rigorous Persuasion Dialogue , 2009, ArgMAS.

[26]  Nicolas Maudet,et al.  Optimization of Probabilistic Argumentation with Markov Decision Models , 2015, IJCAI.

[27]  Sarit Kraus,et al.  Providing Arguments in Discussions on the Basis of the Prediction of Human Argumentative Behavior , 2016, ACM Trans. Interact. Intell. Syst..

[28]  David Silver,et al.  Smooth UCT Search in Computer Poker , 2015, IJCAI.

[29]  David Konopnicki,et al.  Claims on demand – an initial demonstration of a system for automatic detection and polarity identification of context dependent claims in massive corpora , 2014, COLING.

[30]  Bernard W. Silverman,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[31]  Nava Tintarev,et al.  Formal Arguments, Preferences, and Natural Language Interfaces to Humans: an Empirical Evaluation , 2014, ECAI.

[32]  B. J. Fogg,et al.  Persuasive technology: using computers to change what we think and do , 2002, UBIQ.

[33]  Anthony Hunter,et al.  Modelling the Persuadee in Asymmetric Argumentation Dialogues for Persuasion , 2015, IJCAI.

[34]  Guillermo Ricardo Simari,et al.  The Added Value of Argumentation , 2013 .

[35]  Viðar Svansson,et al.  A computer game for abstract argumentation , 2006 .

[36]  Stefan Woltran,et al.  Generalizations of Dung Frameworks and Their Role in Formal Argumentation , 2014, IEEE Intelligent Systems.

[37]  Trevor J. M. Bench-Capon.  Persuasion in Practical Argument Using Value-based Argumentation Frameworks , 2003, J. Log. Comput..

[38]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[39]  Ehud Reiter,et al.  Lessons from a failure: Generating tailored smoking cessation letters , 2003, Artif. Intell..

[40]  J. Cleary,et al.  \self-organized Language Modeling for Speech Recognition". In , 1997 .

[41]  Matthias Thimm,et al.  Strategic Argumentation in Multi-Agent Systems , 2014, KI - Künstliche Intelligenz.

[42]  Joel Veness,et al.  Monte-Carlo Planning in Large POMDPs , 2010, NIPS.

[43]  Claudette Cayrol,et al.  On bipolarity in argumentation frameworks , 2008, NMR.

[44]  Sarit Kraus,et al.  Facing the challenge of human-agent negotiations via effective general opponent modeling , 2009, AAMAS.

[45]  Sarit Kraus,et al.  GENIE: A decision support system for crisis negotiations , 1995, Decis. Support Syst..

[46]  Peter McBurney,et al.  Opponent Modelling in Persuasion Dialogues , 2013, IJCAI.

[47]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[48]  Ya'akov Gal,et al.  The Effects of Goal Revelation on Computer-Mediated Negotiation , 2009 .

[49]  Sarit Kraus,et al.  Argumentation Theory in the Field: An Empirical Study of Fundamental Notions , 2014, ArgNLP.

[50]  Nir Oren,et al.  Opponent Models with Uncertainty for Strategic Argumentation , 2013, IJCAI.