Search

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.

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., Comment: LREC-COLING 2024. https://aclanthology.org/2024.lrec-main.108

This work compares three locomotion techniques for an immersive VR environment: two different types of teleporting (with and without animation) and a manual (joystick-based) technique. We tested the effect of these techniques on visual motion sickness, spatial awareness, presence, subjective pleasantness, and perceived difficulty of operating the navigation. We collected eye tracking and head and body orientation data to investigate the relationships between motion, vection, and sickness. Our study confirms some results already discussed in the literature regarding the reduced invasiveness and the high usability of instant teleport while increasing the evidence against the hypothesis of reduced spatial awareness induced by this technique. We reinforce the evidence about the issues of extending teleporting with animation. Furthermore, we offer some new evidence of a benefit to the user experience of the manual technique and the correlation of the sickness felt in this condition with head movements. The findings of this study contribute to the ongoing debate on the development of guidelines on navigation interfaces in specific VR environments.

With the recent success of artificial intelligence in neuroscience, a number of deep learning (DL) models were proposed for classification, anomaly detection, and pattern recognition tasks in electroencephalography (EEG). EEG is a multi-channel time-series that provides information about the individual brain activity for diagnostics, neuro-rehabilitation, and other applications (including emotions recognition). Two main issues challenge the existing DL-based modeling methods for EEG: the high variability between subjects and the low signal-to-noise ratio making it difficult to ensure a good quality in the EEG data. In this paper, we propose two variational autoencoder models, namely vEEGNet-ver3 and hvEEGNet, to target the problem of high-fidelity EEG reconstruction. We properly designed their architectures using the blocks of the well-known EEGNet as the encoder, and proposed a loss function based on dynamic time warping. We tested the models on the public Dataset 2a - BCI Competition IV, where EEG was collected from 9 subjects and 22 channels. hvEEGNet was found to reconstruct the EEG data with very high-fidelity, outperforming most previous solutions (including our vEEGNet-ver3 ). Furthermore, this was consistent across all subjects. Interestingly, hvEEGNet made it possible to discover that this popular dataset includes a number of corrupted EEG recordings that might have influenced previous literature results. We also investigated the training behaviour of our models and related it with the quality and the size of the input EEG dataset, aiming at opening a new research debate on this relationship. In the future, hvEEGNet could be used as anomaly (e.g., artefact) detector in large EEG datasets to support the domain experts, but also the latent representations it provides could be used in other classification problems and EEG data generation.

Electroencephalografic (EEG) data are complex multi-dimensional time-series that are very useful in many applications, from diagnostics to driving brain-computer interface systems. Their classification is still a challenging task, due to the inherent within- and between-subject variability and their low signal-to-noise ratio. On the other hand, the reconstruction of raw EEG data is even more difficult because of the high temporal resolution of these signals. Recent literature has proposed numerous machine and deep learning models that could classify, e.g., different types of movements, with an accuracy in the range 70% to 80% (with 4 classes). On the other hand, a limited number of works targeted the reconstruction problem, with very limited results. In this work, we propose vEEGNet, a DL architecture with two modules, i.e., an unsupervised module based on variational autoencoders to extract a latent representation of the data, and a supervised module based on a feed-forward neural network to classify different movements. To build the encoder and the decoder of VAE we exploited the well-known EEGNet network. We implemented two slightly different architectures of vEEGNet, thus showing state-of-the-art classification performance, and the ability to reconstruct both low-frequency and middle-range components of the raw EEG. Although preliminary, this work is promising as we found out that the low-frequency reconstructed signals are consistent with the so-called motor-related cortical potentials, well-known motor-related EEG patterns and we could improve over previous literature by reconstructing faster EEG components, too. Further investigations are needed to explore the potentialities of vEEGNet in reconstructing the full EEG data, generating new samples, and studying the relationship between classification and reconstruction performance.

This paper presents a qualitative study that investigates the effects of some language choices in expressing the trigger part of a trigger-action rule on the users' mental models. Specifically, we explored how 11 non-programmer participants articulated the definition of trigger-action rules in different contexts by choosing among alternative conjunctions, verbal structures, and order of primitives. Our study shed some new light on how lexical choices influence the users' mental models in End-User Development tasks. Specifically, the conjunction "as soon as" clearly supports the idea of instantaneousness, and the conjunction "while" the idea of protractedness of an event; the most commonly used "if" and "when", instead, are prone to create ambiguity in the mental representation of events. The order of rule elements helps participants to construct accurate mental models. Usually, individuals are facilitated in comprehension when the trigger is displayed at the beginning of the rule, even though sometimes the reverse order (with the action first) is preferred as it conveys the central element of the rule., Comment: This version did not undergo peer-review. A corrected version is published by Springer Nature in the Proceedings of 9th International Syposium on End-User Development (IS-EUD 2023)

Personality traits such as Need for Cognition, Locus of Control, Mindset and Self-efficacy could impact the perception, acceptance and appreciation of recommendations provided to support configuration tasks in the End User Development (EUD) context. In this paper we describe the user model services we have developed to measure such traits. These services can be accessed by users through a simple web interface and can be queried by EUD applications by means of REST API.

This article provides a reduced-order modelling framework for turbulent compressible flows discretized by the use of finite volume approaches. The basic idea behind this work is the construction of a reduced-order model capable of providing closely accurate solutions with respect to the high fidelity flow fields. Full-order solutions are often obtained through the use of segregated solvers (solution variables are solved one after another), employing slightly modified conservation laws so that they can be decoupled and then solved one at a time. Classical reduction architectures, on the contrary, rely on the Galerkin projection of a complete Navier-Stokes system to be projected all at once, causing a mild discrepancy with the high order solutions. This article relies on segregated reduced-order algorithms for the resolution of turbulent and compressible flows in the context of physical and geometrical parameters. At the full-order level turbulence is modeled using an eddy viscosity approach. Since there is a variety of different turbulence models for the approximation of this supplementary viscosity, one of the aims of this work is to provide a reduced-order model which is independent on this selection. This goal is reached by the application of hybrid methods where Navier-Stokes equations are projected in a standard way while the viscosity field is approximated by the use of data-driven interpolation methods or by the evaluation of a properly trained neural network. By exploiting the aforementioned expedients it is possible to predict accurate solutions with respect to the full-order problems characterized by high Reynolds numbers and elevated Mach numbers.

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., Comment: 11 pages, 2 figures, 1 table, published in proceedings of the 18th International Conference promoted by the IFIP Technical Committee 13 on Human Computer Interaction, INTERACT 2021. August 30th September 3rd, 2021, Bari, Italy

Geometrically parametrized Partial Differential Equations are nowadays widely used in many different fields as, for example, shape optimization processes or patient specific surgery studies. The focus of this work is on some advances for this topic, capable of increasing the accuracy with respect to previous approaches while relying on a high cost-benefit ratio performance. The main scope of this paper is the introduction of a new technique mixing up a classical Galerkin-projection approach together with a data-driven method to obtain a versatile and accurate algorithm for the resolution of geometrically parametrized incompressible turbulent Navier-Stokes problems. The effectiveness of this procedure is demonstrated on two different test cases: a classical academic back step problem and a shape deformation Ahmed body application. The results show into details the properties of the architecture we developed while exposing possible future perspectives for this work.

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., Comment: 9 pages, 2 figures, 1 table, to be published in proceedings of the 18th International Conference promoted by the IFIP Technical Committee 13 on Human Computer Interaction, INTERACT 2021. August 30th September 3rd, 2021, Bari, Italy

Motor imagery (MI)-based brain-computer interface (BCI) systems are being increasingly employed to provide alternative means of communication and control for people suffering from neuro-motor impairments, with a special effort to bring these systems out of the controlled lab environments. Hence, accurately classifying MI from brain signals, e.g., from electroencephalography (EEG), is essential to obtain reliable BCI systems. However, MI classification is still a challenging task, because the signals are characterized by poor SNR, high intra-subject and cross-subject variability. Deep learning approaches have started to emerge as valid alternatives to standard machine learning techniques, e.g., filter bank common spatial pattern (FBCSP), to extract subject-independent features and to increase the cross-subject classification performance of MI BCI systems. In this paper, we first present a review of the most recent studies using deep learning for MI classification, with particular attention to their cross-subject performance. Second, we propose DynamicNet, a Python-based tool for quick and flexible implementations of deep learning models based on convolutional neural networks. We show-case the potentiality of DynamicNet by implementing EEGNet, a well-established architecture for effective EEG classification. Finally, we compare its performance with FBCSP in a 4-class MI classification over public datasets. To explore its cross-subject classification ability, we applied three different cross-validation schemes. From our results, we demonstrate that DynamicNet-implemented EEGNet outperforms FBCSP by about 25%, with a statistically significant difference when cross-subject validation schemes are applied.

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., Comment: 27 pages, 3 images, 3 tables

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.