Designing an Automatic Agent for Repeated Language based Persuasion Games
This addresses the challenge of applying AI to persuasion with rich language in economics and AI, though it is incremental by extending existing methods to natural language contexts.
The paper tackled the problem of designing an automatic agent for repeated persuasion games using natural language, where a sender aims to persuade a receiver to accept deals by sending reviews, and demonstrated its superiority over strong baselines with adaptability to different decision makers.
Persuasion games are fundamental in economics and AI research and serve as the basis for important applications. However, work on this setup assumes communication with stylized messages that do not consist of rich human language. In this paper we consider a repeated sender (expert) -- receiver (decision maker) game, where the sender is fully informed about the state of the world and aims to persuade the receiver to accept a deal by sending one of several possible natural language reviews. We design an automatic expert that plays this repeated game, aiming to achieve the maximal payoff. Our expert is implemented within the Monte Carlo Tree Search (MCTS) algorithm, with deep learning models that exploit behavioral and linguistic signals in order to predict the next action of the decision maker, and the future payoff of the expert given the state of the game and a candidate review. We demonstrate the superiority of our expert over strong baselines, its adaptability to different decision makers, and that its selected reviews are nicely adapted to the proposed deal.