Exploring Early Prediction of Buyer-Seller Negotiation Outcomes
This work addresses the need for more flexible language-based negotiation systems in pedagogy and conversational AI, though it is incremental as it builds on existing prediction tasks.
The paper tackles the problem of predicting buyer-seller negotiation outcomes early in language-based interactions, exploring methods like feature-based approaches and pretrained language models with task context, and finds that linguistic features such as trust and agreement improve prediction performance.
Agents that negotiate with humans find broad applications in pedagogy and conversational AI. Most efforts in human-agent negotiations rely on restrictive menu-driven interfaces for communication. To advance the research in language-based negotiation systems, we explore a novel task of early prediction of buyer-seller negotiation outcomes, by varying the fraction of utterances that the model can access. We explore the feasibility of early prediction by using traditional feature-based methods, as well as by incorporating the non-linguistic task context into a pretrained language model using sentence templates. We further quantify the extent to which linguistic features help in making better predictions apart from the task-specific price information. Finally, probing the pretrained model helps us to identify specific features, such as trust and agreement, that contribute to the prediction performance.