TY - GEN
T1 - Strategical Argumentative Agent for Human Persuasion: A Preliminary Report
AU - Rosenfeld, Ariel
AU - Kraus, S.
N1 - Place of conference:Germany
PY - 2016
Y1 - 2016
N2 - Automated agents should be able to persuade people in the same way people persuade each other, namely via dialog. Today, automated persuasion modeling and investigation use unnatural assumptions in persuasive interactions which create doubt regarding their applicability in real world deployment with people. In this work we present a novel methodology for persuading people through argumentative dialog. Our methodology combines theoretical argumentation modeling, machine learning and Markovian optimization techniques, which together form an innovative agent named SPA. Preliminary field experiments indicate that SPA provides higher levels of attitude change among subjects compared to two baseline agents.
AB - Automated agents should be able to persuade people in the same way people persuade each other, namely via dialog. Today, automated persuasion modeling and investigation use unnatural assumptions in persuasive interactions which create doubt regarding their applicability in real world deployment with people. In this work we present a novel methodology for persuading people through argumentative dialog. Our methodology combines theoretical argumentation modeling, machine learning and Markovian optimization techniques, which together form an innovative agent named SPA. Preliminary field experiments indicate that SPA provides higher levels of attitude change among subjects compared to two baseline agents.
UR - https://scholar.google.co.il/scholar?q=Strategical+Argumentative+Agent+for+Human+Persuasion%3A+A+Preliminary+Report&btnG=&hl=en&as_sdt=0%2C5https://scholar.google.co.il/scholar?q=Strategical+Argumentative+Agent+for+Human+Persuasion%3A+A+Preliminary+Report
M3 - Conference contribution
BT - Workshop on Frontiers and Connections between Argumentation Theory and Natural Language Processing
ER -