Massimo Zancanaro

Seyedehdelaram Esfahani, Giovanni De Toni, Bruno Lepri et al.

Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided interaction pattern aimed at both eliciting the users' preferences and heading them toward effective recourse interventions. In a fictional task of money lending, we compare this approach with an exploratory interaction pattern based on a combination of alternative plans and the possibility of freely changing the configurations by the users themselves. Our results suggest that users may recognize that the guided interaction paradigm improves efficiency. However, they also feel less freedom to experiment with "what-if" scenarios. Nevertheless, the time spent on the purely exploratory interface tends to be perceived as a lack of efficiency, which reduces attractiveness, perspicuity, and dependability. Conversely, for the guided interface, more time on the interface seems to increase its attractiveness, perspicuity, and dependability while not impacting the perceived efficiency. That might suggest that this type of interfaces should combine these two approaches by trying to support exploratory behavior while gently pushing toward a guided effective solution.

Pietro Giovanni Bizzaro, Elena Della Valentina, Maurizio Napolitano et al.

In this paper, we propose a new annotation scheme to classify different types of clauses in Terms-and-Conditions contracts with the ultimate goal of supporting legal experts to quickly identify and assess problematic issues in this type of legal documents. To this end, we built a small corpus of Terms-and-Conditions contracts and finalized an annotation scheme of 14 categories, eventually reaching an inter-annotator agreement of 0.92. Then, for 11 of them, we experimented with binary classification tasks using few-shot prompting with a multilingual T5 and two fine-tuned versions of two BERT-based LLMs for Italian. Our experiments showed the feasibility of automatic classification of our categories by reaching accuracies ranging from .79 to .95 on validation tasks.

Giuseppe Desolda, Francesco Greco, Francisco Guarnieri et al.

In this paper, we present the design and the evaluation of an authoring tool for End-User Development, which supports the definition of Trigger-Actions rules that combines events and states in the triggers. The possibility of using either states or events in triggers has already been discussed in the literature. However, it is recognized that the state/event distinction is difficult to manage for users. In this paper, we propose an authoring tool that provides explicit support for managing this distinction. We compare it with a state-of-the-art authoring tool that implements the classical event-event paradigm.

Ariel Caputo, Andrea Giachetti, Salwa Abkal et al.

In this paper, a study aimed at investigating the effects of real (using eye tracking to determine the fixation) and simulated foveated blurring in immersive Virtual Reality is presented. Techniques to reduce the optical flow perceived at the visual field margins are often employed in immersive Virtual Reality environments to alleviate discomfort experienced when the visual motion perception does not correspond to the body's acceleration. Although still preliminary, our results suggest that for participants with higher self-declared sensitivity to sickness, there might be an improvement for nausea when using blurring. The (perceived) difficulty of the task seems to improve when the real foveated method is used.

Eleonora Mencarini, Amon Rapp, Massimo Zancanaro

In this paper, we present a qualitative study on speleology that aims to widen the current understanding of people's practices in Nature and identify a design space for technology that supports such practices. Speleology is a practice based on the discovery, study, and dissemination of natural cavities. Speleologists are amateur experts who often collaborate with scientists and local institutions to understand the geology, hydrology, and biology of a territory. Their skills are at the same time physical, technical, and theoretical; this is why speleology is defined as a 'sporting science'. Being at the boundary between outdoor adventure sports and citizen science, speleology is an interesting case study for investigating the variety and complexity of activities carried out in the natural context. We interviewed 15 experienced speleologists to explore their goals, routines, vision of the outdoors, and attitude towards technology. From our study, it emerged that i) the excitement of discovery and the unpredictability of an explorative trip are the strongest motivations for people to engage in speleology; ii) physical skilfulness is a means for knowledge generation; iii) the practice is necessarily collective and requires group coordination. From these findings, an ambivalent attitude towards technology emerged: on the one hand, the scientific vocation of speleology welcomes technology supporting the development of knowledge; on the other hand, aspects typical of adventure sports lead to resistance to technology facilitating the physical performance. We conclude the article by presenting design considerations for devices supporting speleology, as well as a few reflections on how communities of speleologists can inspire citizen science projects.

Gianluca Schiavo, Nadia Mana, Ornella Mich et al.

The paper presents the design of an assistive reading tool that integrates read-aloud technology with eye-tracking to regulate the speed of reading and support struggling readers in following the text while listening to it. The paper describes the design rationale of this approach, following the theory of auditory-visual integration, in terms of an automatic self-adaptable technique based on the reader's gaze that provides an individualized interaction experience. This tool has been assessed in a controlled experiment with 20 children (aged 8-10 years) with a diagnosis of dyslexia and a control group of 20 children with typical reading abilities. The results show that children with reading difficulties improved their comprehension scores by 24% measured on a standardized instrument for the assessment of reading comprehension, and that children with more inaccurate reading (N=9) tended to benefit more. The findings are discussed in terms of a better integration between audio and visual text information, paving the way to improve standard read-aloud technology with gaze-contingency and self-adaptable techniques to personalize the reading experience.

Massimo Zancanaro, Oliviero Stock, Gianluca Schiavo et al.

Joint narratives are often used in the context of reconciliation interventions for people in social conflict situations, which arise, for example, due to ethnic or religious differences. The interventions aim to encourage a change in attitudes of the participants towards each other. Typically, a human mediator is fundamental for achieving a successful intervention. In this work, we present an automated approach to support remote interactions between pairs of participants as they contribute to a shared story in their own language. A key component is an automated cognitive tutor that guides the participants through a controlled escalation/de-escalation process during the development of a joint narrative. We performed a controlled study comparing a trained human mediator to the automated mediator. The results demonstrate that an automated mediator, although simple at this stage, effectively supports interactions and helps to achieve positive outcomes comparable to those attained by the trained human mediator.

Felipe Ortega, Gregorio Convertino, Massimo Zancanaro et al.

Question-&-Answer (QA) websites have emerged as efficient platforms for knowledge sharing and problem solving. In particular, the Stack Exchange platform includes some of the most popular QA communities to date, such as Stack Overflow. Initial metrics used to assess the performance of these communities include summative statistics like the percentage of resolved questions or the average time to receive and validate correct answers. However, more advanced methods for longitudinal data analysis can provide further insights on the QA process, by enabling identification of key predictive factors and systematic comparison of performance across different QA communities. In this paper, we apply survival analysis to a selection of communities from the Stack Exchange platform. We illustrate the advantages of using the proposed methodology to characterize and evaluate the performance of QA communities, and then point to some implications for the design and management of QA platforms.