Carlos Duarte

Sérgio Alves, Carlos Duarte, Kyle Montague et al.

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.

Xia Chen, Guoquan Lv, Xinwei Zhuang et al.

Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering domains. This study explores the application of KAN in building physics, focusing on predictive modeling, knowledge discovery, and continuous learning. Through four case studies, we demonstrate KAN's ability to rediscover fundamental equations, approximate complex formulas, and capture time-dependent dynamics in heat transfer. While there are challenges in extrapolation and interpretability, we highlight KAN's potential to combine advanced modeling methods for knowledge augmentation, which benefits energy efficiency, system optimization, and sustainability assessments beyond the personal knowledge constraints of the modelers. Additionally, we propose a model selection decision tree to guide practitioners in appropriate applications for building physics.

Letícia Seixas Pereira, José Coelho, André Rodrigues et al.

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.