Safeguarding Crowdsourcing Surveys from ChatGPT through Prompt InjectionChatGPT and other large language models (LLMs) have proven useful in crowdsourcing tasks, where they can effectively annotate machine learning training data. However, this means that they also have the potential for misuse, specifically to automatically answer surveys. LLMs can potentially circumvent quality assurance measures, thereby threatening the integrity of methodologies that rely on crowdsourcing surveys. In this paper, we propose a mechanism to detect LLM-generated responses to surveys. The mechanism uses "prompt injection," such as directions that can mislead LLMs into giving predictable responses. We evaluate our technique against a range of question scenarios, types, and positions, and find that it can reliably detect LLM-generated responses with more than 98% effectiveness. We also provide an open-source software to help survey designers use our technique to detect LLM responses. Our work is a step in ensuring that survey methodologies remain rigorous vis-a-vis LLMs.2025CWChaofan Wang et al.Working with AICSCW
From Bodily Functions to Bodily Fun: Approaching Pleasure as a Process when Designing with Sexual ExperiencesThis paper presents a conceptual exploration of designing sexual pleasure as an evolving whole-body experience. It addresses the historically narrow focus of research and technology on functional outcomes such as reproduction and orgasm. This limited perspective overlooks diverse desires, emotional connection, and sensory engagement, reinforcing restrictive norms that shape how individuals conceptualise and experience sexuality. To inform our design inquiry, we conducted a qualitative survey (N=143) to generate how individuals understand and experience sexual pleasure. Reflexive thematic analysis of the responses reveals the influence of culture and technology on sexuality, alongside several experiential dimensions: emotional and embodied connection, play and sensory immersion, and vulnerability. These insights, together with a theoretical foundation, guide a design exploration communicated through two provocations. These provocations serve as reflections of an alternative design orientation; one that challenges normative assumptions, views pleasure as an ongoing process, supports bodily exploration, and facilitates richer, more inclusive sexual experiences.2025COCéline Offerman et al.Human-Nature Relationships (More-than-Human Design)Interactive Narrative & Immersive StorytellingDIS
Towards Effective Human Intervention in Algorithmic Decision-Making: Understanding the Effect of Decision-Makers' Configuration on Decision-Subjects' Fairness PerceptionsHuman intervention is claimed to safeguard decision-subjects' rights in algorithmic decision-making and contribute to their fairness perceptions. However, how decision subjects perceive hybrid decision-maker configurations (i.e., combining humans and algorithms) is unclear. We address this gap through a mixed-methods study in an algorithmic policy enforcement context. Through qualitative interviews (Study 1; N_1=21), we identify three characteristics (i.e., decision-maker's profile, model type, input data provenance) that affect how decision-subjects perceive decision-makers' ability, benevolence, and integrity (ABI). Through a quantitative study (Study 2; N_2=223), we then systematically evaluate the individual and combined effects of these characteristics on decision-subjects' perceptions towards decision-makers, and fairness perceptions. We found that only decision-maker’s profile contributes to perceived ability, benevolence, and integrity. Interestingly, the effect of decision-maker's profile on fairness perceptions was mediated by perceived ability and integrity. Our findings have design implications for ensuring effective human intervention as a protection against harmful algorithmic decisions.2025MYMireia Yurrita et al.Delft University of TechnologyAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasCHI
(Re)discovering Sexual Pleasure after Cancer: Understanding the Design SpaceCancer treatments often lead to sexual health challenges that greatly impact cancer survivors’ quality of life. Current interventions primarily address physiological aspects, like medication or vaginal care, overlooking psychological, social, and cultural dimensions. This paper explores how HCI can address this gap by supporting post-cancer sexual health with interventions for survivors and their partners, considering their lived experiences. Through reflexive thematic analysis of interviews with (N=6) medical sexologists, we identified five themes: perceiving the body as a medical object, the hot potato problem in oncology, sociotechnical sexploration, reuniting what treatment has divided, and designing interventions with openness in a highly situated context. These themes highlight cancer survivors’ experiences, the (in)effectiveness of current interventions, and provision of care. This research outlines the design space for post-cancer sexual health by providing specific design directions (“what”) and ways for designing them (“how”), while advancing the broader discourse on intimacy and design within HCI.2025COCéline Offerman et al.Delft University of Technology, Industrial Design EngineeringMental Health Apps & Online Support CommunitiesElderly Care & Dementia SupportCHI
Digital Phenotyping as Felt Informatics: Designing AI-Based Mental Health Diagnostic Tools Through AestheticsWith psychiatry lagging behind other medical fields in terms of innovation in instruments and methods, AI provides it an opportunity to catch up. Advocates of digital phenotyping promise to provide an objective tool that detects symptoms by analysing data from personal devices. We argue that digital phenotyping requires a more reflexive and critical approach to its design and an alignment of the clinicians' interests in generating relevant evidence with the needs of service users who seek tools to manage their condition. We propose a felt informatics approach, situating digital phenotyping design within the problem space of pragmatist aesthetics. Within this perspective, felt life becomes a central object and a site for digital phenotyping design. This paper reveals the ways diagnostic data mediates mental ill health experience, emphasises the cultivation of aesthetic sensibility as a fundamental element of digital phenotyping and includes design considerations for practitioners and researchers.2025KBKarin Bogdanova et al.TU Delft, AI DeMoS Lab; Faculty of Industrial Design EngineeringAlgorithmic Transparency & AuditabilityMental Health Apps & Online Support CommunitiesSleep & Stress MonitoringCHI
Why does Automation Adoption in Organizations Remain a Fallacy?: Scrutinizing Practitioners' Imaginaries in an International AirportIn organizations, the interest in automation is long-standing. However, adopting automated processes remains challenging, even in environments that appear highly standardized and technically suitable for it. Through a case study in Amsterdam Airport Schiphol, this paper investigates automation as a broader sociotechnical system influenced by a complex network of actors and contextual factors. We study practitioners' collective understandings of automation and subsequent efforts taken to implement it. Using imaginaries as a lens, we report findings from a qualitative interview study with 16 practitioners involved in airside automation projects. Our findings illustrate the organizational dynamics and complexities surrounding automation adoption, as reflected in the captured problem formulations, conceptions of the technology, envisioned human roles in autonomous operations, and perspectives on automation fit in the airside ecosystem. Ultimately, we advocate for contextual automation design, which carefully considers human roles, accounts for existing organizational politics, and avoids techno-solutionist approaches.2025GGGaroa Gomez-Beldarrain et al.Delft University of TechnologyAI-Assisted Decision-Making & AutomationPrivacy by Design & User ControlImpact of Automation on WorkCHI
Policy Sandboxing: Empathy as an Enabler Towards Inclusive Policy-MakingDigitally-supported participatory methods are often used in policy-making to develop inclusive policies by collecting and integrating citizen's opinions. However, these methods fail to capture the complexity and nuances in citizen's needs, i.e., citizens are generally unaware of other's needs, perspectives, and experiences. Consequently, policies developed with this underlying gap tend to overlook the alignment of multistakeholder perspectives, and design policies based on the optimization of high-level demographic features. In our contribution, we propose a method to enable citizens understand other's perspectives and calibrate their positions. First, we collected requirements and design principles to develop our approach by involving stakeholders and experts in policymaking in a series of workshops. Then, we conducted a crowdsourcing study with 420 participants to compare the effect of different text and images, on people’s initial and final motivations and their willingness to change opinions. We observed that both influence participant's opinion change, however, the effect is more pronounced for textual modality. Finally, we discuss overarching implications of designing with empathy to mediate alignment of citizen's perspectives.2024AMAndrea Mauri et al.Session 3c: Speculative Design and Emerging TechnologiesCSCW
Faulty or Ready? Handling Failures in Deep-Learning Computer Vision Models until Deployment: A Study of Practices, Challenges, and NeedsHandling failures in computer vision systems that rely on deep learning models remains a challenge. While an increasing number of methods for bug identification and correction are proposed, little is known about how practitioners actually search for failures in these models. We perform an empirical study to understand the goals and needs of practitioners, the workflows and artifacts they use, and the challenges and limitations in their process. We interview 18 practitioners by probing them with a carefully crafted failure handling scenario. We observe that there is a great diversity of failure handling workflows in which cooperations are often necessary, that practitioners overlook certain types of failures and bugs, and that they generally do not rely on potentially relevant approaches and tools originally stemming from research. These insights allow to draw a list of research opportunities, such as creating a library of best practices and more representative formalisations of practitioners' goals, developing interfaces to exploit failure handling artifacts, as well as providing specialized training2023ABAgathe Balayn et al.Delft University of TechnologyExplainable AI (XAI)AI-Assisted Decision-Making & AutomationComputational Methods in HCICHI
Disentangling Fairness Perceptions in Algorithmic Decision-Making: the Effects of Explanations, Human Oversight, and Contestability.Recent research claims that information cues and system attributes of algorithmic decision-making processes affect decision subjects’ fairness perceptions. However, little is still known about how these factors interact. This paper presents a user study (N = 267) investigating the individual and combined effects of explanations, human oversight, and contestability on informational and procedural fairness perceptions for high- and low-stakes decisions in a loan approval scenario. We find that explanations and contestability contribute to informational and procedural fairness perceptions, respectively, but we find no evidence for an effect of human oversight. Our results further show that both informational and procedural fairness perceptions contribute positively to overall fairness perceptions but we do not find an interaction effect between them. A qualitative analysis exposes tensions between information overload and understanding, human involvement and timely decision-making, and accounting for personal circumstances while maintaining procedural consistency. Our results have important design implications for algorithmic decision-making processes that meet decision subjects’ standards of justice.2023MYMireia Yurrita et al.Delft University of TechnologyAI Ethics, Fairness & AccountabilityAlgorithmic Transparency & AuditabilityAlgorithmic Fairness & BiasCHI
How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?Deep learning models for image classification suffer from dangerous issues often discovered after deployment. The process of identifying bugs that cause these issues remains limited and understudied. Especially, explainability methods are often presented as obvious tools for bug identification. Yet, the current practice lacks an understanding of what kind of explanations can best support the different steps of the bug identification process, and how practitioners could interact with those explanations. Through a formative study and an iterative co-creation process, we build an interactive design probe providing various potentially relevant explainability functionalities, integrated into interfaces that allow for flexible workflows. Using the probe, we perform 18 user-studies with a diverse set of machine learning practitioners. Two-thirds of the practitioners engage in successful bug identification. They use multiple types of explanations, e.g. visual and textual ones, through non-standardized sequences of interactions including queries and exploration. Our results highlight the need for interactive, guiding, interfaces with diverse explanations, shedding light on future research directions.2022ABAgathe Balayn et al.Delft University of TechnologyExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
Great Chain of Agents: The Role of Metaphorical Representation of Agents in Conversational CrowdsourcingConversational agents are being widely adopted across several domains to serve a variety of purposes ranging from providing intelligent assistance to companionship. Recent literature has shown that users develop intuitive folk theories and a metaphorical understanding of conversational agents (CAs) due to the lack of a mental model of the agents. However, investigation of metaphorical agent representation in the HCI community has mainly focused on the human level, despite non-human metaphors for agents being prevalent in the real world. We adopted Lakoff and Turner's `Great Chain of Being' framework to systematically investigate the impact of using non-human metaphors to represent conversational agents on worker engagement in crowdsourcing marketplaces. We designed a text-based conversational agent that assists crowd workers in task execution. Through a between-subjects experimental study (N=341), we explored how different human and non-human metaphors affect worker engagement, the perceived cognitive load of workers, intrinsic motivation, and their trust in the agents. Our findings bridge the gap of how users experience CAs with non-human metaphors in the context of conversational crowdsourcing.2022JJJi-Youn Jung et al.Delft University of TechnologyConversational ChatbotsAgent Personality & AnthropomorphismCHI
Using Worker Avatars to Improve Microtask CrowdsourcingThe future of crowd work has been identified to depend on worker satisfaction, but we lack a thorough understanding of how worker satisfaction can be increased in microtask crowdsourcing. Prior work has shown that one solution is to build tasks that are engaging. To facilitate engagement, two methods that have received attention in recent HCI literature are the use of video games and conversational interfaces. While these are largely different techniques, they aim for the same goal of reducing worker burden and increasing engagement in a task. On one hand, video games have huge motivation potential and translating game design elements for motivational purposes has shown positive effects. Recent work in games research has shown that the use of player avatars is effective in fostering interest, enjoyment, and other aspects pertaining to intrinsic motivation. On the other hand, conversational interfaces have been argued to have advantages over traditional GUIs due to facilitating a more human-like interaction. `Conversational' microtasking has recently been proposed to improve worker engagement in microtask marketplaces. The contexts of games and crowd work are underlined by the need to motivate and engage participants, yet the potential of using worker avatars to promote self-identification and improve worker satisfaction in microtask crowdsourcing has remained unexplored. Addressing this knowledge gap, we carried out a between-subjects study involving 360 crowd workers. We investigated how worker avatars influence quality related outcomes of workers and their perceived experience, in conventional web and novel conversational interfaces. We equipped workers with the functionality of customizing their avatars, and selecting characterizations for their avatars, to understand whether identifying with an avatar can increase the motivation of workers. We found evidence that using worker avatars can significantly reduce workers' perceived task difficulty in information findings tasks across both web and conversational interfaces. We also found that using worker avatars with conversational interfaces can effectively reduce cognitive workload, increase worker intrinsic motivation, and increase worker retention. Our findings have important implications in alleviating workers' perceived workload, building their self-confidence, and on the design of crowdsourcing microtasks.2021SQSihang Qiu et al.Crowds and Data WorkCSCW
Estimating Conversational Styles in Conversational Microtask CrowdsourcingCrowdsourcing marketplaces have provided a large number of opportunities for online workers to earn a living. To improve satisfaction and engagement of such workers, who are vital for the sustainability of the marketplaces, recent works have used conversational interfaces to support the execution of a variety of crowdsourcing tasks. The rationale behind using conversational interfaces stems from the potential engagement that conversation can stimulate. Prior works in psychology have also shown that conversational styles can play an important role in communication. There are unexplored opportunities to estimate a worker's conversational style with an end goal of improving worker satisfaction, engagement and quality. Addressing this knowledge gap, we investigate the role of conversational styles in conversational microtask crowdsourcing. To this end, we design a conversational interface which supports task execution, and we propose methods to estimate the conversational style of a worker. Our experimental setup was designed to empirically observe how conversational styles of workers relate with quality-related outcomes. Results show that even a naive supervised classifier can predict the conversation style with high accuracy (80%), and crowd workers with an Involvement conversational style provided a significantly higher output quality, exhibited a higher user engagement and perceived less cognitive task load in comparison to their counterparts. Our findings have important implications on task design with respect to improving worker performance and their engagement in microtask crowdsourcing.2020SQSihang Qiu et al.Conversation and CommunicationCSCW
Improving Worker Engagement Through Conversational Microtask CrowdsourcingThe rise in popularity of conversational agents has enabled humans to interact with machines more naturally. Recent work has shown that crowd workers in microtask marketplaces can complete a variety of human intelligence tasks (HITs) using conversational interfaces with similar output quality compared to the traditional Web interfaces. In this paper, we investigate the effectiveness of using conversational interfaces to improve worker engagement in microtask crowdsourcing. We designed a text-based conversational agent that assists workers in task execution, and tested the performance of workers when interacting with agents having different conversational styles. We conducted a rigorous experimental study on Amazon Mechanical Turk with 800 unique workers, to explore whether the output quality, worker engagement and the perceived cognitive load of workers can be affected by the conversational agent and its conversational styles. Our results show that conversational interfaces can be effective in engaging workers, and a suitable conversational style has potential to improve worker engagement.2020SQSihang Qiu et al.Delft University of TechnologyConversational ChatbotsCrowdsourcing Task Design & Quality ControlCHI