Persuasion Dialogues Research Articles

Please Donate to Save a Life: Inducing Politeness to Handle Resistance in Persuasive Dialogue Agents

<i>Please Donate to Save a Life</i>: Inducing Politeness to Handle Resistance in Persuasive Dialogue Agents

THE ROLE OF PERSUASIVE DIALOGUE IN THE NEGOTIATION OF THE SALE OF GOODS AT SIMPUR CENTER, BANDAR LAMPUNG CITY

This study discusses the role of persuasive dialogue in negotiating the sale of goods at the Simpur Center in Bandar Lampung City. This shopping center has a significant role in meeting consumer needs and in the context of intense competition, the ability to conduct effective sales negotiations becomes important. This study uses a qualitative approach with the case study method to explore a deep understanding of how persuasive dialogue contributes to the outcome of sales negotiations. The main findings of this study include persuasive dialogue strategies used by sellers, customizing messages according to buyer profiles, managing rejection, and building customer relationships. This study shows that the seller's ability to use persuasive dialogue influences the success of sales negotiations. Tailoring messages based on local preferences and culture, as well as being able to overcome resistance with relevant solutions, also contribute to successful negotiations. Furthermore, this study emphasizes the importance of understanding local culture in persuasive dialogue, because adaptation to cultural values can strengthen communication. Persuasive dialogue plays a central role in negotiating the sale of goods at the Simpur Center in Bandar Lampung City. In a competitive environment, product knowledge, tailored persuasive dialogue strategies and the ability to manage rejection wisely are all important factors in achieving success in sales. In closing, suggestions are given to improve the seller's ability to apply effective persuasive dialogue in order to achieve success in the sales negotiation process.

Automatic knowledge generation for a persuasion dialogue system with enthymemes

Persuasion dialogues in multi-agent systems are required in situations in which agents debate to defend their viewpoint on a certain topic. In this work, we introduce a dialogue system for persuasion dialogues in which participants can exchange and complete enthymemes using structured argumentation as the underlying knowledge representation formalism. In our approach, the dialogue system provides the means to create arguments from enthymemes by generating assumptions based solely on the enthymeme's structure. Then, arguments are used to determine the dialectical status of the dialogue. We prove that under minimal restrictions, agents involved in a persuasion dialogue can reach an agreement successfully, and they can acquire knowledge such that their mental model is consistent with the outcome of the dialogue.

Strategic argumentation dialogues for persuasion: Framework and experiments based on modelling the beliefs and concerns of the persuadee

Persuasion is an important and yet complex aspect of human intelligence. When undertaken through dialogue, the deployment of good arguments, and therefore counterarguments, clearly has a significant effect on the ability to be successful in persuasion. Two key dimensions for determining whether an argument is “good” in a particular dialogue are the degree to which the intended audience believes the argument and counterarguments, and the impact that the argument has on the concerns of the intended audience. In this paper, we present a framework for modelling persuadees in terms of their beliefs and concerns, and for harnessing these models in optimizing the choice of move in persuasion dialogues. Our approach is based on the Monte Carlo Tree Search which allows optimization in real-time. We provide empirical results of a study with human participants that compares an automated persuasion system based on this technology with a baseline system that does not take the beliefs and concerns into account in its strategy.

Reinforcing personalized persuasion in task-oriented virtual sales assistant.

Existing task-oriented virtual agents can assist users with simple tasks like ticket booking, hotel reservations, etc. effectively and with high confidence. These virtual assistants, however, assume specific, predictable end-user behavior, such as predefined/servable objectives, which results in conversation failures in challenging situations, such as when goals are unavailable. Inspired by the practice and its efficacy, we propose an end-to-end framework for task-oriented persuasive dialogue generation that combines pre-training and reinforcement learning for generating context-aware persuasive responses. We utilize four novel rewards to improve consistency and repetitiveness in generated responses. Additionally, a meta-learning strategy has also been utilized to make the model parameters better for domain adaptation. Furthermore, we also curate a personalized persuasive dialogue (PPD) corpus, which contains utterance-level intent, slot, sentiment, and persuasion strategy annotation. The obtained results and detailed analysis firmly establish the effectiveness of the proposed persuasive virtual assistant over traditional task-oriented virtual assistants. The proposed framework considerably increases the quality of dialogue generation in terms of consistency and repetitiveness. Additionally, our experiment with a few shot and zero-shot settings proves that our meta-learned model learns to quickly adopt new domains with a few or even zero no. of training epochs. It outperforms the non-meta-learning-based approaches keeping the base model constant. To the best of our knowledge, this is the first effort to improve a task-oriented virtual agent's persuasiveness and domain adaptation.

Towards personalized persuasive dialogue generation for adversarial task oriented dialogue setting

In recent years, task-oriented virtual assistants have gained huge popularity and demand in both research and industry communities. The primary aim of a task-oriented dialogue agent is to assist end-users in accomplishing a task successfully and satisfactorily. Existing virtual agents have acquired proficiency in assisting users in solving simple tasks such as restaurant bookings. However, they operate under the deterministic presumption that end-users will have a servable task objective, which makes them inadequate under adversarial situations such as goal unavailability. On the other hand, human agents accomplish users’ tasks even in many goal unavailability scenarios by persuading them towards a similar goal to the user’s proposed task. Motivated by the limitation, the current work proposes and builds a novel transformer-based context-aware personalized persuasive virtual assistant (CoPersUasive VA), which also serves end-users in task unavailability situations. The proposed CoPersUasive VA recognizes goal conflicts through user sentiment and identifies an appropriate persuasion strategy using ongoing dialogue context and user personality. Depending on users’ proposed goals, it finds a similar servable goal and persuades them with the identified persuasion strategy. The obtained experimental results and detailed post-analysis firmly establish that the proposed model effectively enhances the capability of task-oriented virtual assistants to deal with the task failures caused by goal unavailability. The obtained findings also suggest the crucial role of dialogue context in identifying an appropriate and appealing persuasion strategy. The proposed CoPersUasive model could easily be adapted to any other domain by fine-tuning the model on an underlying task. Furthermore, we developed a personalized persuasive multi-intent conversational dialogue corpus annotated with intent, slot, sentiment, and dialogue act for electronic domain.22The dataset and code will be made available to accelerate research towards the development of persuasive virtual sales assistants.

Peaceful Islam Persuasive Dialogue on The Family of Terrorists in the Middle of the Radical Islamic Movement

Efforts to deradicalize and counter radicalism based on terrorism have tended only to use an aggressive approach, even though a persuasive dialogical approach is far more significant than using a destructive path. At this point, the study in this article aims to identify in-depth the concepts and techniques offered by NU and Muhammadiyah to families exposed to radicalism. In addition, the analysis in this article also aims to analyze in-depth the strategies carried out by NU and Muhammadiyah based on radicalism in the Lamongan district. The research method used in this article is a descriptive qualitative approach using data collection techniques through in-depth interviews, observation, and documentation. The study results in this article show that, First, NU and Muhammadiyah, in their efforts to prevent radicalism, also apply several approaches, such as persuasive preventive measures mediated by formal educational institutions. Through these institutions, the roles of the two mass organizations intersubjectively convey the impact of the dangers of radicalism in the nation and state. In addition to formal efforts, non-formal and informal approaches are also carried out in preventive actions against the understanding and behavior of radicalism in religion. For example, in the activities of the dhikr assembly, religious lectures, and political activities. Furthermore, in this context, NU and Muhammadiyah, as the largest community organizations in Indonesia, have always been at the forefront of prominent patrons in conveying and warning about the dangers of radicalism, either in the form of brainwashing or in the form of materially beneficial offers. Second, NU and Muhammadiyah, as the largest mass organizations in Indonesia and Lamongan, must be recognized as playing a significant role in deradicalization and counter deradicalism, both of which synergize and join hands in knitting the realization of the theology of rahmatan lil 'alamiin in the terrorism base of Lamongan district. The strategy adopted by NU and Muhammadiyah is a persuasive dialogue with the families of former terrorists who isolate themselves more from the surrounding community. This approach is considered successful in neutralizing the ideologies of radicalism in Lamongan. The Fatayat NU and Nasyiatul Aisyiah institutions are deemed to have played a significant role in realizing this persuasive dialogue with mothers and women from terrorist families.

A persona aware persuasive dialogue policy for dynamic and co-operative goal setting

Contextualization:In recent years, the popularity of virtual agents particularly task-oriented dialogue agents has increased immensely due to their effectiveness and simplicity in various domains such as industry, e-commerce, and health. Problem:In real-world, users do not have always a predefined and immutable goal, i.e., they may upgrade/downgrade/update their task goal dynamically depending upon their utility and the serving capability of the assisting agent. However, the existing Virtual Agents (VAs) in the dialogue literature relinquish and yield dialogue failure if they find any dynamic goal setting or goal unavailability scenarios. Contributions and methodology:Motivated by these inabilities of existing VAs, we propose some intelligent and expert Dialogue Agents (A Unified Dialogue Agent and Multi-agent Dialogue system) that can deal with dynamic and goal unavailability situations to elevate both user satisfaction and the agent’s utility particularly task success rate. The proposed architecture incorporates a goal guiding module namely Dynamic and Co-Operative Goal Driven Module (DyCoGDM), which traces goal status and resolves goal discrepancy through dynamic goal setting (Goal Formulator) and personalized persuasion (Goal Persuader) mechanisms. We also created and annotated a dialogue corpus because of unavailability of such corpus featured with dynamic and goal unavailability scenarios. Findings and implications:Our proposed method outperforms several baselines and state of the art methods in all evaluation metrics. The proposed VA is capable of dealing with dynamic goals and goal unavailability scenarios effectively. The study found that the persona aware persuasive dialogue agent outperforms generalized persuasive dialogue agent by a large margin. Furthermore, we also observed that the task oriented reward is the most essential reward for training a reinforcement learning based agent and agents trained without task based reward do not even converge.

EVA 2.0: Emotional and rational multimodal argumentation between virtual agents

Abstract Persuasive argumentation depends on multiple aspects, which include not only the content of the individual arguments, but also the way they are presented. The presentation of arguments is crucial – in particular in the context of dialogical argumentation. However, the effects of different discussion styles on the listener are hard to isolate in human dialogues. In order to demonstrate and investigate various styles of argumentation, we propose a multi-agent system in which different aspects of persuasion can be modelled and investigated separately. Our system utilizes argument structures extracted from text-based reviews for which a minimal bias of the user can be assumed. The persuasive dialogue is modelled as a dialogue game for argumentation that was motivated by the objective to enable both natural and flexible interactions between the agents. In order to support a comparison of factual against affective persuasion approaches, we implemented two fundamentally different strategies for both agents: The logical policy utilizes deep Reinforcement Learning in a multi-agent setup to optimize the strategy with respect to the game formalism and the available argument. In contrast, the emotional policy selects the next move in compliance with an agent emotion that is adapted to user feedback to persuade on an emotional level. The resulting interaction is presented to the user via virtual avatars and can be rated through an intuitive interface.

Persuasive dialogue understanding: The baselines and negative results

Persuasion aims at forming one’s opinion and action via a series of persuasive messages containing persuader’s strategies. Due to its potential application in persuasive dialogue systems, the task of persuasive strategy recognition has gained much attention lately. Previous methods on user intent recognition in dialogue systems adopt recurrent neural network (RNN) or convolutional neural network (CNN) to model context in conversational history, neglecting the tactic history and intra-speaker relation. In this paper, we demonstrate the limitations of a Transformer-based approach coupled with Conditional Random Field (CRF) for the task of persuasive strategy recognition. In this model, we leverage inter- and intra-speaker contextual semantic features, as well as label dependencies to improve the recognition. Despite extensive hyper-parameter optimizations, this architecture fails to outperform the baseline methods. We observe two negative results. Firstly, CRF cannot capture persuasive label dependencies, possibly as strategies in persuasive dialogues do not follow any strict grammar or rules as the cases in Named Entity Recognition (NER) or part-of-speech (POS) tagging. Secondly, the Transformer encoder trained from scratch is less capable of capturing sequential information in persuasive dialogues than Long Short-Term Memory (LSTM). We attribute this to the reason that the vanilla Transformer encoder does not efficiently consider relative position information of sequence elements.

Formal dialogue models for argumentation in education and linguistics

This paper offers a very short introduction to formal dialogue systems of the kind currently used in artificial intelligence and argumentation theory and applies them to some types of dialogue that are especially important in education. Persuasion dialogue is contrasted with deliberation dialogue. The fundamental problem of how to define relevance in such systems is briefly explained and discussed.

Measuring the strength of threats, rewards, and appeals in persuasive negotiation dialogues

AbstractThe aim of this article is to propose a model for the measurement of the strength of rhetorical arguments (i.e., threats, rewards, and appeals), which are used in persuasive negotiation dialogues when a proponent agent tries to convince his opponent to accept a proposal. Related articles propose a calculation based on the components of the rhetorical arguments, that is, the importance of the goal of the opponent and the certainty level of the beliefs that make up the argument. Our proposed model is based on the pre-conditions of credibility and preferability stated by Guerini and Castelfranchi. Thus, we suggest the use of two new criteria for the strength calculation: the credibility of the proponent and the status of the goal of the opponent in the goal processing cycle. We use three scenarios in order to illustrate our proposal. Besides, the model is empirically evaluated and the results demonstrate that the proposed model is more efficient than previous works of the state of the art in terms of numbers of negotiation cycles, number of exchanged arguments, and number of reached agreements.

Two Images of Russia in the British Political Mass Media Discourse of 1991 – 1993 and 2013 – 2019: Pragmastylistic Aspect

The paper considers political mass media discourse as a persuasive dialogue in which a journalist makes his interlocutors accept a certain point of view. The desired mental reaction on the part of interlocutors can only be achieved through careful choice of ways of persuasion and especially linguistic means often influencing effectively the emotional sphere. The persuasion can be subject to ideological aims thus representing a definite object as positive or negative. The paper claims that such object as the image of state can have opposite assessment in different periods of time and focuses on linguistic means of persuasion aimed at the creation of two contrasting images of Russia in the British mass media discourse of 1991 – 1993 and 2013 – 2019.

Pressure and Argumentation in Public Controversies

When can exerting pressure in a public controversy promote reasonable outcomes, and when is it rather a hindrance? We show how negotiation and persuasion dialogue can be intertwined. Then, we examine in what ways one can in a public controversy exert pressure on others through sanctions or rewards. Finally, we discuss from the viewpoints of persuasion and negotiation whether and, if so, how pressure hinders the achievement of a reasonable outcome.

On the calculation of the strength of threats

Threats are used in persuasive negotiation dialogues when a proponent agent tries to persuade an opponent of him to accept a proposal. Depending on the information the proponent has modeled about his opponent(s), he may generate more than one threat, in which case he has to evaluate them in order to select the most adequate to be sent. One way to evaluate the generated threats is by calculating their strengths, i.e., the persuasive force of each threat. Related work considers mainly two criteria to do such evaluation: the certainty level of the beliefs that compose the threat and the importance of the goal of the opponent. This article aims to study the components of threats and propose further criteria that lead to improve their evaluation and to select more effective threats during the dialogue. Thus, the contribution of this paper is a model for calculating the strength of threats that is mainly based on the status of the goal of the opponent and the credibility of the proponent. The model is empirically evaluated and the results demonstrate that the proposed model is more efficient than previous works in terms of the number of exchanged arguments, and the number of reached agreements.

Delegated updates in epistemic graphs for opponent modelling

In an epistemic graph, belief in arguments is represented by probability distributions. Furthermore, the influence that belief in arguments can have on the belief in other arguments is represented by constraints on the probability distributions. Different agents may choose different constraints to describe their reasoning, thus making epistemic graphs extremely flexible tools. A key application for epistemic graphs is modelling participants in persuasion dialogues, with the aim of modelling the change in beliefs as each move in the dialogue is made. This requires mechanisms for updating the model throughout the dialogue. In this paper, we introduce the class of delegated update methods, which harness existing, simpler update methods in order to produce more realistic outputs. In particular, we focus on hypothesized updates, which capture agent's reluctance or susceptibility to belief updates that can be caused by certain factors, such as time of the day, fatigue, dialogue length, and more. We provide a comprehensive range of options for modelling different kinds of agents and we explore a range of properties for categorising the options.

Pressie en argumentatie in maatschappelijke discussies

Abstract Pressure and argumentation in public controversiesDiscussants in a public controversy are also players in a social arena. Under what circumstances can means of exerting pressure promote reasonable outcomes, and when are they rather hindrances to their achievement? We discuss the use of persuasion dialogues and negotiation dialogues by those who aim at a reasonable outcome. We show how in a public controversy both types of dialogue can be intertwined. Then, we examine in what ways participants in a public controversy can exert pressure on others. Finally, we discuss whether these means of pressure hinder the achievement of a reasonable outcome, both from the viewpoint of the pursuit of a resolution as well as from that of the pursuit of a compromise. We conclude that exerting pressure need not degenerate into committing a fallacy of either the type argumentum ad baculum or the type argumentum ad carotam.

The Functions of Integration and Confrontation in Internal Dialogues

AbstractWhile integrative and confrontational internal dialogues (IDs) are often treated as opposing and numerous positive functions are ascribed to the former, this paper assumes that integration and confrontation are not mutually exclusive but independent processes. When exploring IDs that simulate social relationships and are described by different configurations of integrative and confrontational characteristics, canonical correlation analysis revealed that in competitive dialogue, the strong confrontational attitude of the dialogue's author is accompanied by the weak integrative attitudes of both ID parties. The more the ID is based on a rivalry between the parties, the lower the levels of bond, support, and insight functions are and the higher the level of substitution is. In persuasive dialogue, the confrontational attitude of the dialogue's author is combined with the integrative attitudes of both parties. The more the ID is based on persuasion, the higher the intensity of substitution, insight, bond, support, and self‐guiding is. The findings suggest a synergistic effect of co‐occurring integrative and confrontational attitudes in one ID.

The Role of Argument in Negotiation

The purpose of this paper is to show the pervasive, though often implicit, role of arguments in negotiation dialogue. This holds even for negotiations that start from a difference of interest such as mere bargaining through offers and counteroffers. But it certainly holds for negotiations that try to settle a difference of opinion on policy issues. It will be demonstrated how a series of offers and counteroffers in a negotiation dialogue contains a reconstructible series of implicit persuasion dialogues. The paper is a sequel to van Laar and Krabbe (2017), in which we showed that for some differences of opinion it may be reasonable to shift from persuasion dialogue, aimed at a resolution of the difference on the merits, to negotiation dialogue, aimed at compromise, whereas in the present paper we show that such a shift need not amount to the abandonment of argumentation. Our main aim in this paper as well as in the previous one is to contribute to the theory of argumentation within the context of negotiation and compromise formation.

A Formal Model of an Argumentative Dialogue in the Management of Emotions

In this research, we focus on designing an interactive tool which will be used as an aid in learning how to manage emotions during argumentative dialogues. To this end, a collection of examples illustrating the typical human’s reactions was collated and used to explain mechanisms that appear in dialogues. We present a theoretical background of the project, i.e., a formal system to represent the change of intensity of emotions in argumentative dialogues. We rely here on persuasive dialogue games. A formal language for expressing properties of protocols for dialogues with emotional reasoning is proposed. We suggest that awareness of emotions improves communication between parents and children, and that it is an important element of both raising communication skills in adults and development of communication skills in children.