WhatsApp emerged as a major communication platform in many countries in the recent years. Despite offering only one-to-one and small group conversations, WhatsApp has been shown to enable the formation of a rich underlying network, crossing the boundaries of existing groups, and with structural properties that favor information dissemination at large. Indeed, WhatsApp has reportedly been used as a forum of misinformation campaigns with significant social, political and economic consequences in several countries. In this article, we aim at complementing recent studies on misinformation spread on WhatsApp, mostly focused on content properties and propagation dynamics, by looking into the network that connects users sharing the same piece of content. Specifically, we present a hierarchical network-oriented characterization of the users engaged in misinformation spread by focusing on three perspectives: individuals, WhatsApp groups and user communities, i.e., groupings of users who, intentionally or not, share the same content disproportionately often. By analyzing sharing and network topological properties, our study offers valuable insights into how WhatsApp users leverage the underlying network connecting different groups to gain large reach in the spread of misinformation on the platform.

The recent advancements in artificial intelligence (AI) combined with the extensive amount of data generated by today's clinical systems, has led to the development of imaging AI solutions across the whole value chain of medical imaging, including image reconstruction, medical image segmentation, image-based diagnosis and treatment planning. Notwithstanding the successes and future potential of AI in medical imaging, many stakeholders are concerned of the potential risks and ethical implications of imaging AI solutions, which are perceived as complex, opaque, and difficult to comprehend, utilise, and trust in critical clinical applications. Despite these concerns and risks, there are currently no concrete guidelines and best practices for guiding future AI developments in medical imaging towards increased trust, safety and adoption. To bridge this gap, this paper introduces a careful selection of guiding principles drawn from the accumulated experiences, consensus, and best practices from five large European projects on AI in Health Imaging. These guiding principles are named FUTURE-AI and its building blocks consist of (i) Fairness, (ii) Universality, (iii) Traceability, (iv) Usability, (v) Robustness and (vi) Explainability. In a step-by-step approach, these guidelines are further translated into a framework of concrete recommendations for specifying, developing, evaluating, and deploying technically, clinically and ethically trustworthy AI solutions into clinical practice.

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal behaviors to generate a meaningful representation of the conversation. In this work, we propose to dissect SLU into three representative properties:conversational (disfluency, pause, overtalk), channel (speaker-type, turn-tasks) and ASR (insertion, deletion,substitution). We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues. Empirical results indicate that LM is surprisingly good at capturing conversational properties such as pause prediction and overtalk detection from lexical tokens. On the downsides, the LM scores low on turn-tasks and ASR errors predictions. Additionally, pre-training the LM on spoken transcripts restrain its linguistic understanding. Finally, we establish the efficacy and transferability of the mentioned properties on two benchmark datasets: Switchboard Dialog Act and Disfluency datasets.

We develop a subseasonal forecasting toolkit of simple learned benchmark models that outperform both operational practice and state-of-the-art machine learning and deep learning methods. Our new models include (a) Climatology++, an adaptive alternative to climatology that, for precipitation, is 9% more accurate and 250% more skillful than the United States operational Climate Forecasting System (CFSv2); (b) CFSv2++, a learned CFSv2 correction that improves temperature and precipitation accuracy by 7-8% and skill by 50-275%; and (c) Persistence++, an augmented persistence model that combines CFSv2 forecasts with lagged measurements to improve temperature and precipitation accuracy by 6-9% and skill by 40-130%. Across the contiguous U.S., our Climatology++, CFSv2++, and Persistence++ toolkit consistently outperforms standard meteorological baselines, state-of-the-art machine and deep learning methods, and the European Centre for Medium-Range Weather Forecasts ensemble. Overall, we find that augmenting traditional forecasting approaches with learned enhancements yields an effective and computationally inexpensive strategy for building the next generation of subseasonal forecasting benchmarks.

AI is becoming more and more prevalent in society, with many people wondering how it will affect the law. How artificial intelligence is impacting our laws and what we can expect for future technology/legal interactions. The conversation surrounding the relationship between AI and law also touches quite clearly on the ability to rely on Artificial Intelligence to deliver fair decisions and to enhance the legal system's delivery of equity and justice. In this article, I share insights from my conversations on this topic with Joilson Melo, a Brazilian law expert, and programmer whose devotion to equity and fairness led to a historic change in the Brazilian legal system in 2019, this change mainly affected the system that controls all processes processed digitally in Brazil, the PJe (Electronic Judicial Process). As a law student, Melo filed a request for action in the National Council of Justice (CNJ) against the Court of Justice of Mato Grosso, resulting in a decision allowing citizens to file applications in court electronically without a lawyer and within the Special Court, observing the value of the case, so that it does not exceed 20 minimum wages.

This specific morphology gives rise to several catchments with steep slopes and limited extension [1]. Autumn events, when deep Atlantic troughs more easily enter the Mediterranean area and activate very moist and unstable flow lifted by the mountain range, may determine catastrophic flood on these coastal areas characterized by a high population density (see [2, 3] for a review of climatology and typical atmospheric configurations of extreme precipitations over the Mediterranean area). Just as an example, the November 4th 2011 flood in Genoa determined six deaths and economic damages up to 100 million euros [4, 5, 6, 7]). A common feature in these extreme events are the presence of a quasi-stationary convective system with a spatial extension of few kilometers [8, 9, 10, 11, 12] Medium and long range either deterministic or ensemble Numerical Weather Prediction (NWP) models still struggle to correctly predict both the intensity and the location of these events, which can be triggered and enhanced by very small-scale features. High resolution convection-permitting NWP models manage to partly return a more realistic description of the dynamics of severe thunderstorms. Many studies addressed the role played by different components or settings of NWP models in order to better describe severe convective systems over the Liguria area, such as model resolution, initial conditions, microphysics schemes or small-scale patterns of the sea surface temperature ([6, 13, 14, 15, 16, 17, 18, 17, 19]).

Configuration is a successful application area of Artificial Intelligence. In the majority of the cases, configuration systems focus on configuring one solution (configuration) that satisfies the preferences of a single user or a group of users. In this paper, we introduce a new configuration approach - multi-configuration - that focuses on scenarios where the outcome of a configuration process is a set of configurations. Example applications thereof are the configuration of personalized exams for individual students, the configuration of project teams, reviewer-to-paper assignment, and hotel room assignments including individualized city trips for tourist groups. For multi-configuration scenarios, we exemplify a constraint satisfaction problem representation in the context of configuring exams. The paper is concluded with a discussion of open issues for future work.

The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. Demand response aggregation and load control will enable greater grid stability and greater penetration of renewable energies into the grid. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises with the objective of estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. This predicted duration feeds the energy management system that will allocate the power over the duration reducing the overall peak electricity demand. We structure our experiments inspired by two research questions aiming to discover the accuracy of the proposed machine learning approach and the most relevant features for the prediction models. We experiment different algorithms and features combination for 4 datasets from 2 different campus facilities in Italy and Brazil. Using both contextual and time of the day features, the overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems

We investigate causal inference in the asymptotic regime as the number of variables approaches infinity using an information-theoretic framework. We define structural entropy of a causal model in terms of its description complexity measured by the logarithmic growth rate, measured in bits, of all directed acyclic graphs (DAGs), parameterized by the edge density d. Structural entropy yields non-intuitive predictions. If we randomly sample a DAG from the space of all models, in the range d = (0, 1/8), almost surely the model is a two-layer DAG! Semantic entropy quantifies the reduction in entropy where edges are removed by causal intervention. Semantic causal entropy is defined as the f-divergence between the observational distribution and the interventional distribution P', where a subset S of edges are intervened on to determine their causal influence. We compare the decomposability properties of semantic entropy for different choices of f-divergences, including KL-divergence, squared Hellinger distance, and total variation distance. We apply our framework to generalize a recently popular bipartite experimental design for studying causal inference on large datasets, where interventions are carried out on one set of variables (e.g., power plants, items in an online store), but outcomes are measured on a disjoint set of variables (residents near power plants, or shoppers). We generalize bipartite designs to k-partite designs, and describe an optimization framework for finding the optimal k-level DAG architecture for any value of d \in (0, 1/2). As edge density increases, a sequence of phase transitions occur over disjoint intervals of d, with deeper DAG architectures emerging for larger values of d. We also give a quantitative bound on the number of samples needed to reliably test for average causal influence for a k-partite design.

Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both humans and software systems (aka machines). This paper documents efforts and findings from a comprehensive experimental study on the impact of deep-learning based speech synthesis attacks on both human listeners and machines such as speaker recognition and voice-signin systems. We find that both humans and machines can be reliably fooled by synthetic speech and that existing defenses against synthesized speech fall short. These findings highlight the need to raise awareness and develop new protections against synthetic speech for both humans and machines.