Cybersecurity breaches are often attributed to human behaviour, where individuals fail to integrate ethical principles in their decision-making. This empirical study investigates the effectiveness of the Ripple Down Rules (RDR) method, a knowledge acquisition and representation method, in enhancing ethical awareness and reasoning in cybersecurity contexts. The proposed approach combines rule-based reasoning, case-based learning, reflection, and situated cognition to bridge the gap between ethical knowledge and action by systematically connecting scenario elements to ethical principles. Participants, recruited from a cohort of first-year psychology students, were exposed to training incorporating five ethical principles—Beneficence, Non-Maleficence, Justice, Autonomy, and Explicability—applied to realistic cybersecurity scenarios. The study employed a randomised controlled design with two treatment and one control groups, using pre- and post-study assessments to evaluate improvements in ethical principle identification and reasoning. Participants rated RDR as a clear and helpful tool for understanding ethical reasoning, with sensibility and helpfulness scores ranging from moderate to high. Results demonstrate that RDR training significantly improved participants' ability to identify ethical principles compared to learning without RDR, particularly for principles like autonomy and explicability. However, challenges persisted in distinguishing overlapping principles, such as beneficence and non-maleficence. Implications and guidance for use of RDR for ethics training are discussed.

Validating claims and replicating findings on the impact of artificial social agents (ASA), such as virtual agents, conversational agents, and social robots, requires a standardised measurement instrument that researchers can employ in different settings and for various agents. Such an instrument would allow researchers to evaluate their agents and establish insights beyond their specific study context. Therefore, we present the long and short versions of the ASA questionnaire (ASAQ) for evaluating human-ASA interaction on 19 constructs, such as the agent’s believability, sociability, and coherence. It has been developed by an international workgroup with more than 100 ASA-researchers over multiple years who identified community-relevant constructs and associated questionnaire items and examined the questionnaire’s reliability, validity, and interpretability. The result is a questionnaire that can capture more than 80% of the constructs that studies in the intelligent virtual agent community investigate, with acceptable levels of reliability, content validity, construct validity, and cross-validity. We suggest that ASA-researchers use the ASAQ short version to report their agent’s psychographic information and the ASAQ long version to analyse any constructs in-depth that are specifically relevant to their agent or study. Finally, this paper gives instructions for practical use, such as sample size estimations, and how to interpret and present results. • The Artificial-Social-Agent Questionnaire (ASAQ) is a validated measure used to evaluate the human experience of interacting with an artificial social agent (ASA). • There are two versions of the ASAQ. The short version is used to report the ASAs psychographic information, while the long version allows for in-depth analysis of constructs relevant to a specific ASA. • More than 100 ASA researchers were involved in the development of ASAQ. • The 19 ASAQ constructs capture over 80% of the constructs investigated in the Intelligent Virtual Agent community between 2013-2018. • The ASAQ has demonstrated acceptable levels of reliability, content validity, construct validity, and cross-validity. • We present the ASAQ representative set 2024 of 29 agents. • Instructions for the practical use of ASAQ are given, including guidance on choosing the ASAQ version, estimating sample sizes, and interpreting and presenting the results (e.g., ASAQ chart).

Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to the best explanation' or abduction, where hypotheses about the agent's goals are generated as the most plausible explanations for observed behavior. Alternatively, some approaches enhance interpretability by ensuring that an agent's behavior aligns with an observer's expectations or by making the reasoning behind decisions more transparent. In this work, we tackle a different challenge: explaining the GR process in a way that is comprehensible to humans. We introduce and evaluate an explainable model for goal recognition (GR) agents, grounded in the theoretical framework and cognitive processes underlying human behavior explanation. Drawing on insights from two human-agent studies, we propose a conceptual framework for human-centered explanations of GR. Using this framework, we develop the eXplainable Goal Recognition (XGR) model, which generates explanations for both why and why not questions. We evaluate the model computationally across eight GR benchmarks and through three user studies. The first study assesses the efficiency of generating human-like explanations within the Sokoban game domain, the second examines perceived explainability in the same domain, and the third evaluates the model's effectiveness in aiding decision-making in illegal fishing detection. Results demonstrate that the XGR model significantly enhances user understanding, trust, and decision-making compared to baseline models, underscoring its potential to improve human-agent collaboration.

Interventions to improve health and well-being abound. Whether they are designed for prevention, maintenance or improvement, a key challenge is the motivation of the user to change their current behaviours, such as persisting or taking new actions. To encourage someone to change their behaviour requires persuading them to change their goals and/or their beliefs about the behaviour or their ability to perform it. Our embodied conversational agent (ECA) uses explanations based on the goals and beliefs of the user to promote a sense of personalisation and engagement with the treatment plan which could form a bond as the dyad develop shared goals and tasks together. To keep our message minimal and understand whether belief-based or goal-based explanations are more efficacious in changing behaviour intention, we collected data in the context of a scenario where the ECA seeks to change four behaviours recommended to help students manage their study stress. Our findings suggest that when the behaviour requires a change in desire, we need goal-based explanation, when adoption of the behaviour requires addressing a barrier we need belief-based explanation and warrant future investigation. Further, the stratified analysis suggested that more tailoring to the student’s context could provide more motivation to change.

We present the ASA Questionnaire, an instrument for evaluating human interaction with an artificial social agent (ASA), resulting from multi-year efforts involving more than 100 Intelligent Virtual Agent (IVA) researchers worldwide. It has 19 measurement constructs constituted by 90 items, which capture more than 80% of the constructs identified in empirical studies published in the IVA conference 2013--2018. This paper reports on construct validity analysis, specifically convergent and discriminant validity of initial 131 instrument items that involved 532 crowd-workers who were asked to rate human interaction with 14 different ASAs. The analysis included several factor analysis models and resulted in the selection of 90 items for inclusion in the long version of the ASA questionnaire. In addition, a representative item of each construct or dimension was selected to create a 24-item short version of the ASA questionnaire. Whereas the long version is suitable for a comprehensive evaluation of human-ASA interaction, the short version allows quick analysis and description of the interaction with the ASA. To support reporting ASA questionnaire results, we also put forward an ASA chart. The chart provides a quick overview of the agent profile.

Virtual advisors (VAs) are being utilised almost in every service nowadays from entertainment to healthcare. To increase the user's trust in these VAs and encourage the users to follow their advice, they should have the capability of explaining their decisions, particularly, when the decision is vital such as health advice. However, the role of an explainable VA in health behaviour change is understudied. There is evidence that people tend to change their intentions towards health behaviour when the persuasion message is linked to their mental state. Thus, this study explores this link by introducing an explainable VA that provides explanation according to the user's mental state (beliefs and goals) rather than the agent's mental state as commonly utilised in explainable agents. It further explores the influence of different explanation patterns that refer to beliefs, goals, or beliefs&goals on the user's behaviour change. An explainable VA was designed to advise undergraduate students how to manage their study-related stress by motivating them to change certain behaviours. With 91 participants, the VA was evaluated and the results revealed that user-specific explanation could significantly encourage behaviour change intentions and build good user-agent relationship. Small differences were found between the three types of explanation patterns.

Non-adherence to a treatment plan recommended by the therapist is a key cause of the increasing rate of chronic medical conditions globally. The therapist-patient therapeutic alliance is regarded as a successful intervention and a good predictor of treatment adherence. Similar to the human scenario, embodied conversational agents (ECAs) showed evidence of their ability to build an agent-patient therapeutic alliance, which motivates the effort to advance ECAs as a potential solution to improve treatment adherence and consequently the health outcome. Building therapeutic alliance implies the need for a positive environment where the ECA and the patient can share their knowledge and discuss their goals, preferences and tasks towards building a shared plan, which is commonly done using explanations. However, explainable agents commonly rely on their own knowledge and goals in providing explanations, rather than the beliefs, plans or goals of the user. It is not clear whether such explanations, in individual-specific contexts such as personal health assistance, are perceived by the user as relevant in decision-making towards their own behavior change. Therefore, in this research, we are developing a user-aware explainable ECA by embedding the cognitive agent architecture with a user model, explanation engine and modified planner to implement the concept of SharedPlans. The developed agent will be deployed and evaluated with real patients and the therapeutic alliance will be measured using standard measurements.

Explainable? virtual agents provide insight into the agent's decision-making process, which aims to improve the user's acceptance of the agent's actions or recommendations. However, explainable agents commonly rely on their own knowledge and goals in providing explanations, rather than the beliefs, plans or goals of the user. Little is known about the user perception of such tailored explanations and their impact on their behaviour change. In this paper, we explore the role of belief-based explanation by proposing a user-aware explainable agent by embedding the cognitive agent architecture with a user model and explanation engine to provide a tailored explanation. To make a clear conclusion on the role of explanation in behaviour change intentions, we investigated whether the level of behaviour change intentions is due to building agent-user rapport through the use of empathic language or due to trusting the agent's understanding through providing explanation. Hence, we designed two versions of a virtual advisor agent, empathic and neutral, to reduce study stress among university students and measured students' rapport levels and intentions to change their behaviour. Our results showed that the agent could build a trusted relationship with the user with the help of the explanation regardless of the level of rapport. The results, further, showed that nearly all the recommendations provided by the agent highly significantly increased the intention of the user to change their behavior.

Research into artificial social agents aims at constructing these agents and at establishing an empirically grounded understanding of them, their interaction with humans, and how they can ultimately deliver certain outcomes in areas such as health, entertainment, and education. Key for establishing such understanding is the community's ability to describe and replicate their observations on how users perceive and interact with their agents. In this paper, we address this ability by examining questionnaires and their constructs used in empirical studies reported in the intelligent virtual agent conference proceedings from 2013 to 2018. The literature survey shows the identification of 189 constructs used in 89 questionnaires that were reported across 81 papers. We found unexpectedly little repeated use of questionnaires as the vast majority of questionnaires (more than 76%) were only reported in a single paper. We expect that this finding will motivate joint effort by the IVA community towards creating a unified measurement instrument.

This study investigates the influence of a virtual human (VH) with recorded human voice vs VH with a machine-generated voice (text-to-speech) on building trust and working alliance. We measured the co-presence perception to understand the impact of VH's perception on building the human-VH relationship. The results revealed no differences between the two types of voices on co-presence perception, trust or working alliance.

Treatment non-adherence is a major worldwide problem that results in poor health outcomes among patients with various medical conditions. A good therapist-patient therapeutic alliance and face-to-face communication are regarded as key factors in improving adherence. In this research, we propose the extension of the existing agent architecture FAtiMA to design an embodied conversational agent that plays the role of the therapist by incorporating a shared mental model (SMM) and hybrid state-based and task-based dialogue engine.