Explainable Artificial Intelligence (XAI) aims to provide insights into the inner workings and the outputs of AI systems. Recently, there’s been growing recognition that explainability is inherently human-centric, tied to how people perceive explanations. Despite this, there is no consensus in the research community on whether user evaluation is crucial in XAI, and if so, what exactly needs to be evaluated and how. This systematic literature review addresses this gap by providing a detailed overview of the current state of affairs in human-centered XAI evaluation. We reviewed 73 papers across various domains where XAI was evaluated with users. These studies assessed what makes an explanation “good” from a user’s perspective, i.e., what makes an explanation meaningful to a user of an AI system. We identified 30 components of meaningful explanations that were evaluated in the reviewed papers and categorized them into a taxonomy of human-centered XAI evaluation, based on: (a) the contextualized quality of the explanation, (b) the contribution of the explanation to human-AI interaction, and (c) the contribution of the explanation to human- AI performance. Our analysis also revealed a lack of standardization in the methodologies applied in XAI user studies, with only 19 of the 73 papers applying an evaluation framework used by at least one other study in the sample. These inconsistencies hinder cross-study comparisons and broader insights. Our findings contribute to understanding what makes explanations meaningful to users and how to measure this, guiding the XAI community toward a more unified approach in human-centered explainability.
MULTIFILE
This paper introduces the design principle of legibility as means to examine the epistemic and ethical conditions of sensing technologies. Emerging sensing technologies create new possibilities regarding what to measure, as well as how to analyze, interpret, and communicate said measurements. In doing so, they create ethical challenges for designers to navigate, specifically how the interpretation and communication of complex data affect moral values such as (user) autonomy. Contemporary sensing technologies require layers of mediation and exposition to render what they sense as intelligible and constructive to the end user, which is a value-laden design act. Legibility is positioned as both an evaluative lens and a design criterion, making it complimentary to existing frameworks such as value sensitive design. To concretize the notion of legibility, and understand how it could be utilized in both evaluative and anticipatory contexts, the case study of a vest embedded with sensors and an accompanying app for patients with chronic obstructive pulmonary disease is analyzed.
DOCUMENT
Technology in general, and assistive technology in particular, is considered to be a promising opportunity to address the challenges of an aging population. Nevertheless, in health care, technology is not as widely used as could be expected. In this chapter, an overview is given of theories and models that help to understand this phenomenon. First, the design of (assistive) technologies will be addressed and the importance of human-centered design in the development of new assistive devices will be discussed. Also theories and models are addressed about technology acceptance in general. Specific attention will be given to technology acceptance in healthcare professionals, and the implementation of technology within healthcare organizations. The chapter will be based on the state of the art of scientific literature and will be illustrated with examples from our research in daily practice considering the different perspectives of involved stakeholders.
LINK
In today's world, understanding different viewpoints is key for societal cohesion and progress. Robots have the potential to provide aid in discussing tough topics like ethnicity and gender. However, comparably to humans, the appearance of a robot can trigger inherent prejudices. This study delves into the interplay between robot appearance and decision-making in ethical dilemmas. Employing a Furhat robot that can change faces in an instant, we looked at how robot appearance affects decision-making and the perception of the robot itself. Pairs of participants were invited to discuss a dilemma presented by a robot, covering sensitive topics of ethnicity or gender. The robot either adopted a first-person or third-person perspective and altered its appearance accordingly. Following the explanation, participants were encouraged to discuss their choice of action in the dilemma situation. We did not find significant influences of robot appearance or dilemma topic on perceived anthropomorphism, animacy, likeability, or intelligence of the robot, partly in line with previous research. However, several participants hearing the dilemma from a first-person perspective changed their opinion because of the robot's appearance. Future work can expand with different measures such as engagement, in order to shed light on the intricate dynamics of human-robot interaction, emphasizing the need for thoughtful consideration in designing robot appearances to promote unbiased engagement in discussions of societal significance
DOCUMENT
We investigate whether the automatic generation of questions from an ontology leads to a trustworthy determination of a situation. With our Situation Awareness Question Generator (SAQG) we automatically generate questions from an ontology. The experiment shows that people with no previous experience can characterize hectic situations rather fast and trustworthy. When humans are participating as a sensor to gather information it is important to use basic concepts of perception and thought.
DOCUMENT
Ecocentrism has roots in environmental philosophy, which questions the conceptual dichotomy between humans and the environment, acknowledging nonhuman species' right to flourish independently of human interest (Naess 1973). Generally, ecocentrism refers to a planet- and nature-centered as opposed to the human-centered (anthropocentric) system of values. Inspired by this philosophy, ecocentric education focuses on intrinsic values of the ecosystem, environment, and individual living beings and habitats in environmental education (EE) and education for sustainable development (ESD). https://rd.springer.com/referencework/10.1007/978-3-319-63951-2 LinkedIn: https://www.linkedin.com/in/helenkopnina/
MULTIFILE
One aspect of a responsible application of Artificial Intelligence (AI) is ensuring that the operation and outputs of an AI system are understandable for non-technical users, who need to consider its recommendations in their decision making. The importance of explainable AI (XAI) is widely acknowledged; however, its practical implementation is not straightforward. In particular, it is still unclear what the requirements are of non-technical users from explanations, i.e. what makes an explanation meaningful. In this paper, we synthesize insights on meaningful explanations from a literature study and two use cases in the financial sector. We identified 30 components of meaningfulness in XAI literature. In addition, we report three themes associated with explanation needs that were central to the users in our use cases, but are not prominently described in literature: actionability, coherent narratives and context. Our results highlight the importance of narrowing the gap between theoretical and applied responsible AI.
MULTIFILE
Traditional information systems for crisis response and management are centralized systems with a rigid hierarchical structure. Here we propose a decentralized system, which allows citizens to play a significant role as information source and/or as helpers during the initial stages of a crisis. In our approach different roles are assigned to citizens. To be able to designate the different roles automatically our system needs to generate appropriate questions. On the basis of information theory and a restricted role ontology we formalized the process of question generation. Three consecutive experiments were conducted with human users to evaluate to what extent the questioning process resulted in appropriate role determination. The result showed that the mental model of human users does not always comply with the formal model underpinning the questions generation process.
DOCUMENT
The evolution of emerging technologies that use Radio Frequency Electromagnetic Field (RF-EMF) has increased the interest of the scientific community and society regarding the possible adverse effects on human health and the environment. This article provides NextGEM’s vision to assure safety for EU citizens when employing existing and future EMF-based telecommunication technologies. This is accomplished by generating relevant knowledge that ascertains appropriate prevention and control/actuation actions regarding RF-EMF exposure in residential, public, and occupational settings. Fulfilling this vision, NextGEM commits to the need for a healthy living and working environment under safe RF-EMF exposure conditions that can be trusted by people and be in line with the regulations and laws developed by public authorities. NextGEM provides a framework for generating health-relevant scientific knowledge and data on new scenarios of exposure to RF-EMF in multiple frequency bands and developing and validating tools for evidence-based risk assessment. Finally, NextGEM’s Innovation and Knowledge Hub (NIKH) will offer a standardized way for European regulatory authorities and the scientific community to store and assess project outcomes and provide access to findable, accessible, interoperable, and reusable (FAIR) data.
DOCUMENT
Office well-being aims to explore and support a healthy, balanced and active work style in office environments. Recent work on tangible user interfaces has started to explore the role of physical, tangible interfaces as active interventions to explore how to tackle problems such as inactive work and lifestyles, and increasingly sedentary behaviours. We identify a fragmented research landscape on tangible Office well-being interventions, missing the relationship between interventions, data, design strategies, and outcomes, and behaviour change techniques. Based on the analysis of 40 papers, we identify 7 classifications in tangible Office well-being interventions and analyse the intervention based on their role and foundation in behaviour change. Based on the analysis, we present design considerations for the development of future tangible Office well-being design interventions and present an overview of the current field and future research into tangible Office well-being interventions to design for a healthier and active office environment.
DOCUMENT
