Umeå University's logo

In cooperative human decision-making, agreements are often not total; a partial degree of agreement is sufficient to commit to a decision and move on, as long as one is somewhat confident that the involved parties are likely to stand by their commitment in the future, given no drastic unexpected changes. In this paper, we introduce the notion of agreement scenarios that allow artificial autonomous agents to reach such agreements, using formal models of argumentation, in particular abstract argumentation and value-based argumentation. We introduce the notions of degrees of satisfaction and (minimum, mean, and median) agreement, as well as a measure of the impact a value in a value-based argumentation framework has on these notions. We then analyze how degrees of agreement are affected when agreement scenarios are expanded with new information, to shed light on the reliability of partial agreements in dynamic scenarios. An implementation of the introduced concepts is provided as part of an argumentation-based reasoning software library.

In this article, we introduce a general framework for structured argumentation providing consistent and well-defined justification for conclusions that can and cannot be inferred and there is certainty about them, which we call semantic and NAF-arguments, respectively. We propose the so-called semantic argumentation guaranteeing well-known principles for quality in structured argumentation, with the ability to generate semantic and NAF-arguments, those where the conclusion atoms are semantically interpreted as true, and those where the conclusion is assumed to be false. This framework is defined on the set of all logic programs in terms of rewriting systems based on a confluent set of transformation rules, the so-called Confluent Logic Programming Systems, making this approach a general framework. We implement our framework named semantic argumentation solver available open source.

Interactive software agents, such as chatbots, are progressively being used in the area of health and well-being. In such applications, where agents engage with users in interpersonal conversations for, e.g., coaching, comfort or behavior-change interventions, there is an increased need for understanding agents’ empathic capabilities. In the current state-of-the-art, there are no tools to do that. In order to understand empathic capabilities in interactive software agents, we need a precise notion of empathy. The literature discusses a variety of definitions of empathy, but there is no consensus of a formal definition. Based on a systematic literature review and a qualitative analysis of recent approaches to empathy in interactive agents for health and well-being, a formal definition—an ontology—of empathy is developed. We present the potential of the formal definition in a controlled user-study by applying it as a tool for assessing empathy in two state-of-the-art health and well-being chatbots; Replika and Wysa. Our findings suggest that our definition captures necessary conditions for assessing empathy in interactive agents, and how it can uncover and explain trends in changing perceptions of empathy over time. The definition, implemented in Web Ontology Language (OWL), may serve as an automated tool, enabling systems to recognize empathy in interactions—be it an interactive agent evaluating its own empathic performance or an intelligent system assessing the empathic capability of its interlocutors.

In this paper, we propose a new computational model for affective knowledge representation that will be used for affective agents located in a multicultural environment. To this end, we present the results of two experiments, the first of which determines the most appropriate labels to define the pleasure-arousal dimensions in the culture and language of the agent's location. As an example, we use the Portuguese and Swedish languages. The second experiment identifies the most suitable values of pleasure-arousal dimensions for each emotion expressed in these example languages. The results obtained are compared with a previous model developed for agents interacting with European Spanish-speaking people. Results show significant differences in the values of pleasure and arousal associated with emotions across languages and cultures. The results also show no significant differences in gender or age when associating levels of pleasure-arousal to emotions. We propose two applications of these representation models, such as a model of an agent capable of adapting its affective behavior to different cultural environments and a human-aware planning scenario in which the agent uses this dimensional representation to recognize the user's affective state and select the best strategy to redirect that affective state to the target state.

Humans have evolved to seek social connections, extending beyond interactions with living beings. The digitization of society has led to interactions with non-living entities, such as digital companions, aimed at supporting mental well-being. This literature review surveys the latest developments in digital companions for mental health, employing a hybrid search strategy that identified 67 relevant articles from 2014 to 2022. We identified that by the nature of the digital companions’ purposes, it is important to consider person profiles for: a) to generate both person-oriented and empathetic responses from these virtual companions, b) to keep track of the person’s conversations, activities, therapy, and progress, and c) to allow portability and compatibility between digital companions. We established a taxonomy for digital companions in the scope of mental well-being. We also identified open challenges in the scope of digital companions related to ethical, technical, and socio-technical points of view. We provided documentation about what these issues mean, and discuss possible alternatives to approach them.

This work aims to utilize quantitative bipolar argumentation to detect deception in machine learning models. We explore the concept of deception in the context of interactions of a party developing a machine learning model with potentially malformed data sources. The objective is to identify deceptive or adversarial data and assess the effectiveness of comparative analysis during different stages of model training. By modeling disagreement and agreement between data points as arguments and utilizing quantitative measures, this work proposes techniques for detecting outliers in data. We discuss further applications in clustering and uncertainty modelling.

We consider a type of information-seeking dialogue between a seeker agent and a respondent agent, where the seeker estimates the respondent to not be willing to share a particular set of sought-after information. Hence, the seeker postpones (hides) its goal topic, related to the respondent's sensitive information, until the respondent is perceived as willing to talk about it. In the intermediate process, the seeker opens other topics to steer the dialogue tactfully towards the goal. Such dialogue strategies, which we refer to as goal-hiding strategies, are common in diverse contexts such as criminal interrogations and medical assessments, involving sensitive topics. Conversely, in malicious online interactions like social media extortion, similar strategies might aim to manipulate individuals into revealing information or agreeing to unfavorable terms. This paper proposes a formal dialogue framework for understanding goal-hiding strategies. The dialogue framework uses Quantitative Bipolar Argumentation Frameworks (QBAFs) to assign willingness scores to topics. An initial willingness for each topic is modified by considering how topics promote (support) or demote (attack) other topics. We introduce a method to identify relations among topics by considering a respondent's shared information. Finally, we introduce a gradual semantics to estimate changes in willingness as new topics are opened. Our formal analysis and empirical evaluation show the system's compliance with privacy-preserving safety properties. A formal understanding of goal-hiding strategies opens up a range of practical applications; For instance, a seeker agent may plan with goal-hiding to enhance privacy in human-agent interactions. Similarly, an observer agent (third-party) may be designed to enhance social media security by detecting goal-hiding strategies employed by users' interlocutors.

In recent years, the European Union has advanced towards responsible and sustainable Artificial Intelligence (AI) research, development and innovation. While the Ethics Guidelines for Trustworthy AI released in 2019 and the AI Act in 2021 set the starting point for a European Ethical AI, there are still several challenges to translate such advances into the public debate, education and practical learning. This paper contributes towards closing this gap by reviewing the approaches that can be found in the existing literature and by interviewing 11 experts across five countries to help define educational strategies, competencies and resources needed for the successful implementation of Trustworthy AI in Higher Education (HE) and to reach students from all disciplines. The findings are presented in the form of recommendations both for educators and policy incentives, translating the guidelines into HE teaching and practice, so that the next generation of young people can contribute to an ethical, safe and cutting-edge AI made in Europe.

Indoor interventions are among the most dangerous situations police officers have to deal with, mostly due to a lack of situational awareness. This work describes a planner that determines when to provide information, implemented in DLV^K. It is based on the General Tactical Explanation Model, used by Swedish police during tactical interventions. The planner is envisioned to be integrated in an augmented reality tool to enhance officers’ situational awareness.

There is evidence that a user’s subjective confidence in an Artificial Intelligence (AI)-based system is crucial in its use, even more decisive than the objective effectiveness and efficiency of the system.Therefore, different methods have been proposed for analyzing confidence in AI. In our research, we set out to evaluate how the degree of perceived trust in an AI system could affect a user’s final decision to follow AI recommendations. To this end, we established trustworthy criteria that such an evaluation should meet by following a co-creation approach with a multidisciplinary group of 10 experts. After a systematic review of3,204 articles, we found that none of the tools met the inclusion criteria. Thus, we introduce the so-called "Perceived Operational Trust Degree in AI” (POTDAI) tool that is based on the findings from the expert group and the literature analysis, with a methodology that adds rigor to that employed previously to create similar evaluation tools. We propose a short questionnaire for quick and easy application, inspired by the original version of the Technology Acceptance Model (TAM) with six Likert-type items. In this way, we also respond to the need pointed out by authors such as Vorm and Combs to extend the TAM to address questions related to user perception in systems with an AI component. Thus, POTDAI can be used alone or in combination with TAM to obtain additional information on its usefulness and ease of use.