Towards Emotion-Aware Agents For Negotiation Dialogues

2006

We introduce an emotional agent model that shows how emotions affect an agent's negotiation strategy. By adding emotions, we add the effects of these indirectly related features to the negotiation, features that are ignored in most models. Our new method, the PAD Emotional Negotiation Model, maps a nonemotional agent's strategy during negotiation to the strategy used by an emotional agent. Our evaluations show this model can be used to implement agents with various emotional states that mimic human emotions during negotiation.

arXiv: Human-Computer Interaction, 2020

This document describes our agent Pilot, winner of the Human-Agent Negotiation Challenge at ANAC, IJCAI 2020. Pilot is a virtual human that participates in a sequence of three negotiations with a human partner. Our system is based on the Interactive Arbitration Guide Online (IAGO) negotiation framework. We leverage prior Affective Computing and Psychology research in negotiations to guide various key principles that define the behavior and personality of our agent.

2019

The recognition of emotion and dialogue acts enrich conversational analysis and help to build natural dialogue systems. Emotion makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion datasets contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with or without context. These neural models annotate the emotion corpus with dialogue act labels and an ensemble annotator extracts the final dialogue act label. We annotated two popular multi-modal emotion datasets: IEMOCAP and MELD. We analysed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Act (EDA) corpus pub...

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Automated systems that negotiate with humans have broad applications in pedagogy and conversational AI. To advance the development of practical negotiation systems, we present CaSiNo: a novel corpus of over a thousand negotiation dialogues in English. Participants take the role of campsite neighbors and negotiate for food, water, and firewood packages for their upcoming trip. Our design results in diverse and linguistically rich negotiations while maintaining a tractable, closeddomain environment. Inspired by the literature in human-human negotiations, we annotate persuasion strategies and perform correlation analysis to understand how the dialogue behaviors are associated with the negotiation performance. We further propose and evaluate a multi-task framework to recognize these strategies in a given utterance. We find that multi-task learning substantially improves the performance for all strategy labels, especially for the ones that are the most skewed. We release the dataset, annotations, and the code to propel future work in human-machine negotiations: https:// github.com/kushalchawla/CaSiNo.

2020

The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion corpora contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with and without context. These neural models annotate the emotion corpora with dialogue act labels, and an ensemble annotator extracts the final dialogue act label. We annotated two accessible multi-modal emotion corpora: IEMOCAP and MELD. We analyzed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Acts (EDA) corpus publicly available to the research community for further study and analysis.

2020

The task of building automatic agents that can negotiate with humans in free-form natural language has gained recent interest in the literature. Although there have been initial attempts, combining linguistic understanding with strategy effectively still remains a challenge. Towards this end, we aim to understand the role of natural language in negotiations from a data-driven perspective by attempting to predict a negotiation's outcome, well before the negotiation is complete. Building on the recent advancements in pre-trained language encoders, our model is able to predict correctly within 10% for more than 70% of the cases, by looking at just 60% of the negotiation. These results suggest that rather than just being a way to realize a negotiation, natural language should be incorporated in the negotiation planning as well. Such a framework can be directly used to get feedback for training an automatically negotiating agent.

Proceedings of the …, 2009

Negotiation is a daily occurring process at all levels of society. Emotion plays an important role in negotiation between humans. In this paper we discuss to what extent and in which form ICT techniques can be used to get a grip on the emotional processes that play a role during negotiations. We focus on emotion recognition and measurement. Our analysis shows that current emotion recognition & measurement technology is mainly usable in the preparation for negotiations (including training sessions) and during offline moments of the negotiation (e.g., time-outs). The main arguments for this conclusion are: (1) valid and reliable emotion recognition and measurement techniques are usually invasive, and, (2) it is unclear if participants in a negotiation accept the technology.

Findings of the Association for Computational Linguistics: NAACL 2022

Opponent modeling is the task of inferring another party's mental state within the context of social interactions. In a multi-issue negotiation, it involves inferring the relative importance that the opponent assigns to each issue under discussion, which is crucial for finding high-value deals. A practical model for this task needs to infer these priorities of the opponent on the fly based on partial dialogues as input, without needing additional annotations for training. In this work, we propose a ranker for identifying these priorities from negotiation dialogues. The model takes in a partial dialogue as input and predicts the priority order of the opponent. We further devise ways to adapt related data sources for this task to provide more explicit supervision for incorporating the opponent's preferences and offers, as a proxy to relying on granular utterancelevel annotations. We show the utility of our proposed approach through extensive experiments based on two dialogue datasets. We find that the proposed data adaptations lead to strong performance in zero-shot and fewshot scenarios. Moreover, they allow the model to perform better than baselines while accessing fewer utterances from the opponent. We release our code to support future work in this direction: https://github.com/ kushalchawla/opponent-modeling.

Lecture Notes in Computer Science, 2017

We present a natural language processing model that allows automatic classification and prediction of the user's negotiation style during the interaction with virtual humans in a 3D game. We collected the sentences used in the interactions of the users with virtual artificial agents and their associated negotiation style as measured by ROCI-II test. We analyzed the documents containing the sentences for each style applying text mining techniques and found statistical differences among the styles in agreement with their theoretical definitions. Finally, we trained two machine learning classifiers on the two datasets using pre-trained Word2Vec embeddings.

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 lack natural language processing (NLP) methods required to enable real-world types of interactions. In this paper we study how existing agents must be modified to address this limitation. After performing an extensive study of agents' negotiation with human subjects, we found that simply modifying existing agents to include an NLP module is insufficient to create these agents. Instead the agents' strategies must be modified to address partial agreements and issue-by-issue interactions.