Abstract
In an automatic music playlist generator, such as an automated online radio channel, how should the system react when a user hits the skip button? Can we use this type of negative feedback to improve the list of songs we will playback for the user next? We propose SkipAwareRec, a next-item recommendation system based on reinforcement learning. SkipAwareRec recommends the best next music categories, considering positive feedback consisting of normal listening behaviour, and negative feedback in the form of song skips. Since SkipAwareRec recommends broad categories, it needs to be coupled with a model able to choose the best individual items. To do this, we propose Hybrid SkipAwareRec. This hybrid model combines the SkipAwareRec with an incremental Matrix Factorisation (MF) algorithm that selects specific songs within the recommended categories. Our experiments with Spotify's Sequential Skip Prediction Challenge dataset show that Hybrid SkipAwareRec has the potential to improve recommendations by a considerable amount with respect to the skip-agnostic MF algorithm. This strongly suggests that reformulating the next recommendations based on skips improves the quality of automatic playlists. Although in this work we focus on sequential music recommendation, our proposal can be applied to other sequential content recommendation domains, such as health for user engagement.

Abstract

Abstract
Concerns with the interpretability of ML models are growing as the technology is used in increasingly sensitive domains (e.g., health and public administration). Synthetic data can be used to understand models better, for instance, if the examples are generated close to the frontier between classes. However, data augmentation techniques, such as Generative Adversarial Networks (GAN), have been mostly used to generate training data that leads to better models. We propose a variation of GANs that, given a model, generates realistic data that is classified with low confidence by a given classifier. The generated examples can be used in order to gain insights on the frontier between classes. We empirically evaluate our approach on two well-known image classification benchmark datasets, MNIST and Fashion MNIST. Results show that the approach is able to generate images that are closer to the frontier when compared to the original ones, but still realistic. Manual inspection confirms that some of those images are confusing even for humans.

Abstract
The integration of explanation techniques promotes the comprehension of a model's output and contributes to its interpretation e.g. by generating heat maps highlighting the most decisive regions for that prediction. However, there are several drawbacks to the current heat map-generating methods. Probability by itself is not indicative of the model's conviction in a prediction, as it is influenced by multiple factors, such as class imbalance. Consequently, it is possible that a model yields two true positive predictions - one with an accurate explanation map, and the other with an inaccurate one. Current state-of-the-art explanations are not able to distinguish both scenarios and alert the user to dubious explanations. The goal of this work is to represent these maps more intuitively based on how confident the model is regarding the diagnosis, by adding an extra validation step over the state-of-the-art results that indicates whether the user should trust the initial explanation or not. The proposed method, Confident-CAM, facilitates the interpretation of the results by measuring the distance between the output probability and the corresponding class threshold, using a confidence score to generate nearly null maps when the initial explanations are most likely incorrect. This study implements and validates the proposed algorithm on a multi-label chest X-ray classification exercise, targeting 14 radiological findings in the ChestX-Ray14 dataset with significant class imbalance. Results indicate that confidence scores can distinguish likely accurate and inaccurate explanations. Code available via GitHub.

Abstract
PurposeTo identify psychoeducational interventions that target parents of children with congenital abnormalities (CA) and evaluate their impact on quality of life (QoL).MethodsThe search was conducted in six electronic databases, complemented by references of the studies found, studies of evidence synthesis, a manual search of relevant scientific meetings' abstracts and contact with experts. We included primary studies on parents of children with CA that studied psychoeducational interventions versus standard care. We assessed the risk of bias using Cochrane Collaboration's tool.ResultsWe included six studies focusing on congenital heart defects (CHD). They described four different psychoeducational strategies. In four studies, statistically significant differences were found. For clinical practice, we considered three interventions as more feasible: the Educational program for mothers, with a group format of four sessions weekly; CHIP-Family intervention, which includes a parental group workshop followed by an individual follow-up booster session; and WeChat educational health program with an online format.ConclusionsThis review is the first that assesses the impact of psychoeducational interventions targeted at parents of children with CA on their QoL. The best approach to intervention is multiple group sessions. Two essential strategies were to give support material, enabling parents to review, and the possibility of an online program application, increasing accessibility. However, because all included studies focus on CHD, generalizations should be made carefully. These findings are crucial to guide future research to promote and improve comprehensive and structured support for families and integrate them into daily practice.

Abstract
(1) Background: In this study on Robotic Process Automation (RPA), the feasibility of sustainable RPA implementation was investigated, considering user requirements in the context of this technology’s stakeholders, with a strong emphasis on sustainability. (2) Methods: A multi-objective mathematical model was developed and the Weighted Sum and Tchebycheff methods were used to evaluate the efficiency of the implementation. An enterprise case study was utilized for data collection, employing investigation hypotheses, questionnaires, and brainstorming sessions with company stakeholders. (3) Results: The results underscore the significance of user requirements within the RPA landscape and demonstrate that integrating these requirements into the multi-objective model enhances the implementation assessment. Practical guidelines for RPA planning and management with a sustainability focus are provided. The analysis reveals a solution that reduces initial costs by 21.10% and allows for an efficient and equitable allocation of available resources. (4) Conclusion: This study advances our understanding of the interplay between user requirements and RPA feasibility, offering viable guidelines for the sustainable implementation of this technology.