arXiv subjects

Tiago Guerreiro

Publications and source records attributed to Tiago Guerreiro.

17 recordsLinked to original sources

arXiv2026

Verify, Offload, Extend & Recommend: Selective Complementarity in AI Support for Physical Activity Planning with Longitudinal Patient Data

Self-tracking technologies create longitudinal patient-generated health data, yet integrating these data into clinical decision-making can increase information-processing demands. Generative AI may support sensemaking, but its value depends on clinical context and expertise. We investigate AI augmentation of a clinical decision support system for physical-activity planning in cardiovascular disease. In a counterbalanced within-subjects study, 26 exercise physiologists developed plans for four real cardiovascular cases with and without AI support, followed by evaluation of an AI exercise-plan generator. AI did not significantly improve workload, usability, confidence, or plan quality overall; however, its effect on plan quality increased as visualization literacy decreased and its effect on workload increased as visualisation literacy increased. Interviews and 152 chatbot queries revealed three recurring uses: verifying, offloading, extend and generate. Our findings position AI support as a selective complement to professional expertise while highlighting validation challenges when clinicians seek support precisely where their own knowledge is limited.

cs.HC↗

arXiv2026

Shaping Scientific Explanations to Expert Perspectives with Persona-Conditioned Reinforcement Learning

Explainable AI is increasingly important to scientific discovery. However, existing methods largely ignore that explanation quality is not universal: experts differ in how they assess evidence, prioritize mechanisms, and construct explanatory narratives. We introduce perspective-conditioned explanations, a framework for adapting explanation generation to epistemic variation in expert judgment. Using knowledge graph reasoning paths in drug discovery, we show that preferences organize into coherent epistemic perspectives that can be captured by agentic personas, representations of how experts evaluate explanations. Persona-aligned rewards then guide reinforcement learning-based explanation generation without large-scale expert supervision. Expert user studies show that perspective-conditioned explanations are preferred over general-purpose explanations and improve perceived relevance and validity. Moreover, they match or exceed state-of-the-art predictive performance and reduce expert feedback time by two orders of magnitude. Together, these findings demonstrate that explanation quality is perspective-dependent and that modeling this variation enables scalable and human-aligned explanation generation for scientific discovery.

cs.AI↗

arXiv2026

Exploring the Role of Interaction Data to Empower End-User Decision-Making In UI Personalization

User interface personalization enhances digital efficiency, usability, and accessibility. However, in user-driven setups, limited support for identifying and evaluating worthwhile opportunities often leads to underuse. We explore a reflexive personalization approach where individuals engage with their digital interaction data to identify meaningful personalization opportunities and benefits. We interviewed 12 participants, using experimental vignettes as design probes to support reflection on different forms of using interaction data to empower decision-making in personalization and the preferred level of system support. We found that people can independently identify personalization opportunities but prefer system support through visual personalization suggestions. Interaction data can shape how users perceive and approach personalization by reinforcing the perceived value of change and data collection, helping them weigh benefits against effort, and increasing the transparency of system suggestions. We discuss opportunities for designing personalization software that raises end-users' agency over interfaces through reflective engagement with their interaction data.

cs.HC↗

arXiv2026

Exploring AI-Augmented Sensemaking of Patient-Generated Health Data: A Mixed-Method Study with Healthcare Professionals in Cardiac Risk Reduction

Individuals are increasingly generating substantial personal health and lifestyle data, e.g. through wearables and smartphones. While such data could transform preventative care, its integration into clinical practice is hindered by its scale, heterogeneity and the time pressure and data literacy of healthcare professionals (HCPs). We explore how large language models (LLMs) can support sensemaking of patient-generated health data (PGHD) with automated summaries and natural language data exploration. Using cardiovascular disease (CVD) risk reduction as a use case, 16 HCPs reviewed multimodal PGHD in a mixed-methods study with a prototype that integrated common charts, LLM-generated summaries, and a conversational interface. Findings show that AI summaries provided quick overviews that anchored exploration, while conversational interaction supported flexible analysis and bridged data-literacy gaps. However, HCPs raised concerns about transparency, privacy, and overreliance. We contribute empirical insights and sociotechnical design implications for integrating AI-driven summarization and conversation into clinical workflows to support PGHD sensemaking.

cs.HC↗

arXiv2025

Exploring Human-AI Interaction with Patient-Generated Health Data Sensemaking for Cardiac Risk Reduction

Patient-generated health data (PGHD) allows healthcare professionals to have a holistic and objective view of their patients. However, its integration in cardiac risk reduction remains unexplored. Through co-design with experienced healthcare professionals (n=5) in cardiac rehabilitation, we designed a dashboard, INSIGHT (INvestigating the potentialS of PatIent Generated Health data for CVD Prevention and ReHabiliTation), integrating multi-modal PGHD to support healthcare professionals in physical activity planning in cardiac risk reduction. To further augment healthcare professionals' (HCPs') data sensemaking and exploration capabilities, we integrate large language models (LLMs) for generating summaries and insights and for using natural language interaction to perform personalized data analysis. The aim of this integration is to explore the potential of AI in augmenting HCPs' data sensemaking and analysis capabilities.

cs.HC↗

arXiv2025

Expectations, Explanations, and Embodiment: Attempts at Robot Failure Recovery

Expectations critically shape how people form judgments about robots, influencing whether they view failures as minor technical glitches or deal-breaking flaws. This work explores how high and low expectations, induced through brief video priming, affect user perceptions of robot failures and the utility of explanations in HRI. We conducted two online studies ($N=600$ total participants); each replicated two robots with different embodiments, Furhat and Pepper. In our first study, grounded in expectation theory, participants were divided into two groups, one primed with positive and the other with negative expectations regarding the robot's performance, establishing distinct expectation frameworks. This validation study aimed to verify whether the videos could reliably establish low and high-expectation profiles. In the second study, participants were primed using the validated videos and then viewed a new scenario in which the robot failed at a task. Half viewed a version where the robot explained its failure, while the other half received no explanation. We found that explanations significantly improved user perceptions of Furhat, especially when participants were primed to have lower expectations. Explanations boosted satisfaction and enhanced the robot's perceived expressiveness, indicating that effectively communicating the cause of errors can help repair user trust. By contrast, Pepper's explanations produced minimal impact on user attitudes, suggesting that a robot's embodiment and style of interaction could determine whether explanations can successfully offset negative impressions. Together, these findings underscore the need to consider users' expectations when tailoring explanation strategies in HRI. When expectations are initially low, a cogent explanation can make the difference between dismissing a failure and appreciating the robot's transparency and effort to communicate.

cs.RO↗

arXiv2024

Citizen-Led Personalization of User Interfaces: Investigating How People Customize Interfaces for Themselves and Others

User interface (UI) personalization can improve usability and user experience. However, current systems offer limited opportunities for customization, and third-party solutions often require significant effort and technical skills beyond the reach of most users, impeding the future adoption of interface personalization. In our research, we explore the concept of UI customization for the self and others. We performed a two-week study where nine participants used a custom-designed tool that allows websites' UI customization for oneself and to create and reply to customization assistance requests from others. Results suggest that people enjoy customizing for others more than for themselves. They see requests as challenges to solve and are motivated by the positive feeling of helping others. To customize for themselves, people need help with the creative process. We discuss challenges and opportunities for future research seeking to democratize access to personalized UIs, particularly through community-based approaches.

cs.HC↗

arXiv2022

Snooping on Snoopers: Logging as a Security Response to Physical Attacks on Mobile Devices

When users leave their mobile devices unattended, or let others use them momentarily, they are susceptible to privacy breaches. Existing technological defenses, such as unlock authentication or account switching, have proven to be unpopular. We conducted interviews to uncover practices users currently engage in to cope with the threat, and found that it is common for users to try to keep their devices under close supervision at all times. One obstacle to this strategy is that displaying such protective behavior can be detrimental to social relationships. To address these concerns, we built a software tool that gathers activity logs in the background. Logs can later be reviewed as a timeline of opened apps and the actions performed within each, with events decorated with pictures captured inconspicuously with the front-facing camera. We evaluated this approach in a user study, and found participants to be generally eager to adopt the technology, although in different ways. Most users foresaw using it as a deterrent, or to check if they were snooped on, if that suspicion were ever to arise. Yet, some voiced the intention of creating "honey traps". The results highlight both the opportunities and the potential dangers of the logging approach.

cs.HC↗

arXiv2021

WildKey: A Privacy-Aware Keyboard Toolkit for Data Collection In-The-Wild

Touch data, and in particular text-entry data, has been mostly collected in the laboratory, under controlled conditions. While touch and text-entry data have consistently shown its potential for monitoring and detecting a variety of conditions and impairments, its deployment in-the-wild remains a challenge. In this paper, we present WildKey, an Android keyboard toolkit that allows for the usable deployment of in-the-wild user studies. WildKey is able to analyze text-entry behaviors through implicit and explicit text-entry data collection while ensuring user privacy. We detail each of the WildKey's components and features, all of the metrics collected, and discuss the steps taken to ensure user privacy and promote compliance.

cs.HC↗

arXiv2021

Barriers and Opportunities to Accessible Social Media Content Authoring

User-generated content plays a key role in social networking, allowing a more active participation, socialisation, and collaboration among users. In particular, media content has been gaining a lot of ground, allowing users to express themselves through different types of formats such as images, GIFs and videos. The majority of this growing type of online content remains inaccessible to a part of the population, despite available tools to mitigate this source of exclusion. We sought to understand how people are perceiving these online contents in their networks and how to support tools are being used. To do so, we performed an online survey of 258 social network users and a follow-up interview conducted with 20 of them - 7 of them self-reporting blind and 13 sighted users without a disability. Results show how the different approaches being employed by major platforms are still not sufficient to properly address this issue. Our findings reveal that mainstream users are not aware of the possibility and the benefits of adopting accessible practices. From the general perspectives of end-users experiencing accessible practices, concerning barriers encountered, and motivational factors, we also discuss further approaches to create more user engagement and awareness.

cs.HC↗

arXiv2021

Promoting Self-Efficacy Through an Effective Human-Powered Nonvisual Smartphone Task Assistant

Accessibility assessments typically focus on determining a binary measurement of task performance success/failure; and often neglect to acknowledge the nuances of those interactions. Although a large population of blind people find smartphone interactions possible, many experiences take a significant toll and can have a lasting negative impact on the individual and their willingness to step out of technological comfort zones. There is a need to assist and support individuals with the adoption and learning process of new tasks to mitigate these negative experiences. We contribute with a human-powered nonvisual task assistant for smartphones to provide pervasive assistance. We argue, in addition to success, one must carefully consider promoting and evaluating factors such as self-efficacy and the belief in one's own abilities to control and learn to use technology. In this paper, we show effective assistant positively affects self-efficacy when performing new tasks with smartphones, affects perceptions of accessibility and enables systemic task-based learning.

cs.HC↗

arXiv2021

Exploring Asymmetric Roles in Mixed-Ability Gaming

The landscape of digital games is segregated by player ability. For example, sighted players have a multitude of highly visual games at their disposal, while blind players may choose from a variety of audio games. Attempts at improving cross-ability access to any of those are often limited in the experience they provide, or disregard multiplayer experiences. We explore ability-based asymmetric roles as a design approach to create engaging and challenging mixed-ability play. Our team designed and developed two collaborative testbed games exploring asymmetric interdependent roles. In a remote study with 13 mixed-visual-ability pairs we assessed how roles affected perceptions of engagement, competence, and autonomy, using a mixed-methods approach. The games provided an engaging and challenging experience, in which differences in visual ability were not limiting. Our results underline how experiences unequal by design can give rise to an equitable joint experience.

cs.HC↗

arXiv2019

Open Challenges of Blind People using Smartphones

Blind people face significant challenges when using smartphones. The focus on improving non-visual mobile accessibility has been at the level of touchscreen access. Our research investigates the challenges faced by blind people in their everyday usage of mobile phones. In this paper, we present a set of studies performed with the target population, novices and experts, using a variety of methods, targeted at identifying and verifying challenges; and coping mechanisms. Through a multiple methods approach we identify and validate challenges locally with a diverse set of user expertise and devices, and at scale through the analyses of the largest Android and iOS dedicate forums for blind people. We contribute with a prioritized corpus of smartphone challenges for blind people, and a discussion on a set of directions for future research that tackle the open and often overlooked challenges.

cs.HC↗

arXiv2015

Assessing Inconspicuous Smartphone Authentication for Blind People

As people store more personal data in their smartphones, the consequences of having it stolen or lost become an increasing concern. A typical counter-measure to avoid this risk is to set up a secret code that has to be entered to unlock the device after a period of inactivity. However, for blind users, PINs and passwords are inadequate, since entry 1) consumes a non-trivial amount of time, e.g. using screen readers, 2) is susceptible to observation, where nearby people can see or hear the secret code, and 3) might collide with social norms, e.g. disrupting personal interactions. Tap-based authentication methods have been presented and allow unlocking to be performed in a short time and support naturally occurring inconspicuous behavior (e.g. concealing the device inside a jacket) by being usable with a single hand. This paper presents a study with blind users (N = 16) where an authentication method based on tap phrases is evaluated. Results showed the method to be usable and to support the desired inconspicuity.

cs.HC↗

arXiv2014

Stressing the Boundaries of Mobile Accessibility

Mobile devices gather the communication capabilities as no other gadget. Plus, they now comprise a wider set of applications while still maintaining reduced size and weight. They have started to include accessibility features that enable the inclusion of disabled people. However, these inclusive efforts still fall short considering the possibilities of such devices. This is mainly due to the lack of interoperability and extensibility of current mobile operating systems (OS). In this paper, we present a case study of a multi-impaired person where access to basic mobile applications was provided in an applicational basis. We outline the main flaws in current mobile OS and suggest how these could further empower developers to provide accessibility components. These could then be compounded to provide system-wide inclusion to a wider range of (multi)-impairments.

cs.HC↗

arXiv2014

User-Sensitive Mobile Interfaces: Accounting for Individual Differences amongst the Blind

Mobile phones pervade our daily lives and play ever expanding roles in many contexts. Their ubiquitousness makes them pivotal in empowering disabled people. However, if no inclusive approaches are provided, it becomes a strong vehicle of exclusion. Even though current solutions try to compensate for the lack of sight, not all information reaches the blind user. Good spatial ability is still required to make sense of the device and its interface, as well as the need to memorize positions on screen or keys and associated actions in a keypad. Those problems are compounded by many individual attributes such as age, age of blindness onset or tactile sensitivity which often are forgotten by designers. Worse, the entire blind population is recurrently thought of as homogeneous (often stereotypically so). Thus all users face the same solutions, ignoring their specific capabilities and needs. We usually ignore this diversity as we have the ability to adapt and become experts in interfaces that were probably maladjusted to begin with. This adaptation is not always within reach. Interaction with mobile devices is highly visually demanding which widens this gap amongst blind people. It is paramount to understand the impact of individual differences and their relationship with demands to enable the deployment of more inclusive solutions. We explore individual differences among blind people and assess how they are related with mobile interface demands, both at low (e.g. performing an on-screen gesture) and high level (text-entry) tasks. Results confirmed that different ability levels have significant impact on the performance attained by a blind person. Particularly, otherwise ignored attributes like tactile acuity, pressure sensitivity, spatial ability or verbal IQ have shown to be matched with specific mobile demands and parametrizations.

cs.HC↗

arXiv2014

Understanding Individual Differences: Towards Effective Mobile Interface Design and Adaptation for the Blind

No two people are alike. We usually ignore this diversity as we have the capability to adapt and, without noticing, become experts in interfaces that were probably misadjusted to begin with. This adaptation is not always at the user's reach. One neglected group is the blind. Spatial ability, memory, and tactile sensitivity are some characteristics that diverge between users. Regardless, all are presented with the same methods ignoring their capabilities and needs. Interaction with mobile devices is highly visually demanding which widens the gap between blind people. Our research goal is to identify the individual attributes that influence mobile interaction, considering the blind, and match them with mobile interaction modalities in a comprehensive and extensible design space. We aim to provide knowledge both for device design, device prescription and interface adaptation.

cs.HC↗