Fosca Giannotti

Nafis Irtiza Tripto, Adaku Uchendu, Thai Le et al.

Authorship Analysis, also known as stylometry, has been an essential aspect of Natural Language Processing (NLP) for a long time. Likewise, the recent advancement of Large Language Models (LLMs) has made authorship analysis increasingly crucial for distinguishing between human-written and AI-generated texts. However, these authorship analysis tasks have primarily been focused on written texts, not considering spoken texts. Thus, we introduce the largest benchmark for spoken texts - HANSEN (Human ANd ai Spoken tExt beNchmark). HANSEN encompasses meticulous curation of existing speech datasets accompanied by transcripts, alongside the creation of novel AI-generated spoken text datasets. Together, it comprises 17 human datasets, and AI-generated spoken texts created using 3 prominent LLMs: ChatGPT, PaLM2, and Vicuna13B. To evaluate and demonstrate the utility of HANSEN, we perform Authorship Attribution (AA) & Author Verification (AV) on human-spoken datasets and conducted Human vs. AI spoken text detection using state-of-the-art (SOTA) models. While SOTA methods, such as, character ngram or Transformer-based model, exhibit similar AA & AV performance in human-spoken datasets compared to written ones, there is much room for improvement in AI-generated spoken text detection. The HANSEN benchmark is available at: https://huggingface.co/datasets/HANSEN-REPO/HANSEN.

Dino Pedreschi, Luca Pappalardo, Emanuele Ferragina et al.

Human-AI coevolution, defined as a process in which humans and AI algorithms continuously influence each other, increasingly characterises our society, but is understudied in artificial intelligence and complexity science literature. Recommender systems and assistants play a prominent role in human-AI coevolution, as they permeate many facets of daily life and influence human choices on online platforms. The interaction between users and AI results in a potentially endless feedback loop, wherein users' choices generate data to train AI models, which, in turn, shape subsequent user preferences. This human-AI feedback loop has peculiar characteristics compared to traditional human-machine interaction and gives rise to complex and often ``unintended'' social outcomes. This paper introduces Coevolution AI as the cornerstone for a new field of study at the intersection between AI and complexity science focused on the theoretical, empirical, and mathematical investigation of the human-AI feedback loop. In doing so, we: (i) outline the pros and cons of existing methodologies and highlight shortcomings and potential ways for capturing feedback loop mechanisms; (ii) propose a reflection at the intersection between complexity science, AI and society; (iii) provide real-world examples for different human-AI ecosystems; and (iv) illustrate challenges to the creation of such a field of study, conceptualising them at increasing levels of abstraction, i.e., technical, epistemological, legal and socio-political.

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo et al.

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.

Martina Cinquini, Fosca Giannotti, Riccardo Guidotti

Synthetic data generation has been widely adopted in software testing, data privacy, imbalanced learning, and artificial intelligence explanation. In all such contexts, it is crucial to generate plausible data samples. A common assumption of approaches widely used for data generation is the independence of the features. However, typically, the variables of a dataset depend on one another, and these dependencies are not considered in data generation leading to the creation of implausible records. The main problem is that dependencies among variables are typically unknown. In this paper, we design a synthetic dataset generator for tabular data that can discover nonlinear causalities among the variables and use them at generation time. State-of-the-art methods for nonlinear causal discovery are typically inefficient. We boost them by restricting the causal discovery among the features appearing in the frequent patterns efficiently retrieved by a pattern mining algorithm. We design a framework for generating synthetic datasets with known causalities to validate our proposal. Broad experimentation on many synthetic and real datasets with known causalities shows the effectiveness of the proposed method.

Benedetta Muscato, Beiduo Chen, Gizem Gezici et al.

Human disagreement is ubiquitous and well-known in labeling. However, variation in explanations, captured through token-level human rationales, remains far less explored. At the same time, it is unclear how to best evaluate human labels and rationales -- or even how to best aggregate rationales beyond majority vote -- in light of this variation. Yet, rationales may provide additional insights into the richness of human reasoning, that may differ in style, values and interpretations -- especially in subjective NLP tasks like hate speech detection. In this work, we unify diverse models, training strategies, loss functions, and existing evaluation metrics under a single protocol by systematically re-implementing them across different label and rationale representation spaces. Classification metrics are organized around two key properties -- predictive and distributional -- while explainability metrics through three complementary dimensions: plausibility, faithfulness, and complexity. In this unified supervision framework, we evaluate model behavior across classification and explainability metrics, as well as metric sensitivity to the choice of label (hard and soft) and rationale representation space (hard, intermediate and soft). Results show that both hard and soft metrics favor softer representations, highlighting their effectiveness in capturing variation and the need to rethink evaluation in subjective NLP.

Gabriele Barlacchi, Margherita Lalli, Emanuele Ferragina et al.

Recommender systems shape individual choices through feedback loops in which user behavior and algorithmic recommendations coevolve over time. The systemic effects of these loops remain poorly understood, in part due to unrealistic assumptions in existing simulation studies. We propose a feedback-loop model that captures implicit feedback, periodic retraining, probabilistic adoption of recommendations, and heterogeneous recommender systems. We apply the framework on online retail and music streaming data and analyze systemic effects of the feedback loop. We find that increasing recommender adoption may lead to a progressive diversification of individual consumption, while collective demand is redistributed in model- and domain-dependent ways, often amplifying popularity concentration. Temporal analyses further reveal that apparent increases in individual diversity observed in static evaluations are illusory: when adoption is fixed and time unfolds, individual diversity consistently decreases across all models. Our results highlight the need to move beyond static evaluations and explicitly account for feedback-loop dynamics when designing recommender systems.

Martino Ciaperoni, Marzio Di Vece, Luca Pappalardo et al.

Large-scale foundation models exhibit behavioral shifts: intervention-induced behavioral changes that appear after scaling, fine-tuning, reinforcement learning or in-context learning. While investigating these phenomena have recently received attention, explaining their appearance is still overlooked. Classic explainable AI (XAI) methods can surface failures at a single checkpoint of a model, but they are structurally ill-suited to justify what changed internally across different checkpoints and which explanatory claims are warranted about that change. We take the position that behavioral shifts should be explained comparatively: the core target should be the intervention-induced shift between a reference model and an intervened model, rather than any single model in isolation. To this aim we formulate a Comparative XAI ($Δ$-XAI) framework with a set of desiderata to be taken into account when designing proper explaining methods. To highlight how $Δ$-XAI methods work, we introduce a set of possible pipelines, relate them to the desiderata, and provide a concrete $Δ$-XAI experiment.

Clara Punzi, Roberto Pellungrini, Mattia Setzu et al.

Everyday we increasingly rely on machine learning models to automate and support high-stake tasks and decisions. This growing presence means that humans are now constantly interacting with machine learning-based systems, training and using models everyday. Several different techniques in computer science literature account for the human interaction with machine learning systems, but their classification is sparse and the goals varied. This survey proposes a taxonomy of Hybrid Decision Making Systems, providing both a conceptual and technical framework for understanding how current computer science literature models interaction between humans and machines.

Chandana Sree Mala, Gizem Gezici, Fosca Giannotti

Large Language Models (LLMs) excel in language comprehension and generation but are prone to hallucinations, producing factually incorrect or unsupported outputs. Retrieval Augmented Generation (RAG) systems address this issue by grounding LLM responses with external knowledge. This study evaluates the relationship between retriever effectiveness and hallucination reduction in LLMs using three retrieval approaches: sparse retrieval based on BM25 keyword search, dense retrieval using semantic search with Sentence Transformers, and a proposed hybrid retrieval module. The hybrid module incorporates query expansion and combines the results of sparse and dense retrievers through a dynamically weighted Reciprocal Rank Fusion score. Using the HaluBench dataset, a benchmark for hallucinations in question answering tasks, we assess retrieval performance with metrics such as mean average precision and normalised discounted cumulative gain, focusing on the relevance of the top three retrieved documents. Results show that the hybrid retriever achieves better relevance scores, outperforming both sparse and dense retrievers. Further evaluation of LLM-generated answers against ground truth using metrics such as accuracy, hallucination rate, and rejection rate reveals that the hybrid retriever achieves the highest accuracy on fails, the lowest hallucination rate, and the lowest rejection rate. These findings highlight the hybrid retriever's ability to enhance retrieval relevance, reduce hallucination rates, and improve LLM reliability, emphasising the importance of advanced retrieval techniques in mitigating hallucinations and improving response accuracy.

Benedetta Muscato, Praveen Bushipaka, Gizem Gezici et al.

Prior studies show that adopting the annotation diversity shaped by different backgrounds and life experiences and incorporating them into the model learning, i.e. multi-perspective approach, contribute to the development of more responsible models. Thus, in this paper we propose a new framework for designing and further evaluating perspective-aware models on stance detection task,in which multiple annotators assign stances based on a controversial topic. We also share a new dataset established through obtaining both human and LLM annotations. Results show that the multi-perspective approach yields better classification performance (higher F1-scores), outperforming the traditional approaches that use a single ground-truth, while displaying lower model confidence scores, probably due to the high level of subjectivity of the stance detection task.

Jacopo Joy Colombini, Filippo Bonchi, Francesco Giannini et al.

This paper introduces a rigorous mathematical framework for neural network explainability, and more broadly for the explainability of equivariant operators called Group Equivariant Operators (GEOs) based on Group Equivariant Non-Expansive Operators (GENEOs) transformations. The central concept involves quantifying the distance between GEOs by measuring the non-commutativity of specific diagrams. Additionally, the paper proposes a definition of interpretability of GEOs according to a complexity measure that can be defined according to each user preferences. Moreover, we explore the formal properties of this framework and show how it can be applied in classical machine learning scenarios, like image classification with convolutional neural networks.

Andrea Pugnana, Riccardo Massidda, Francesco Giannini et al.

Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted interventions in their decision-making process. However, when intervened on, CBMs assume the availability of humans that can identify the need to intervene and always provide correct interventions. Both assumptions are unrealistic and impractical, considering labor costs and human error-proneness. In contrast, Learning to Defer (L2D) extends supervised learning by allowing machine learning models to identify cases where a human is more likely to be correct than the model, thus leading to deferring systems with improved performance. In this work, we gain inspiration from L2D and propose Deferring CBMs (DCBMs), a novel framework that allows CBMs to learn when an intervention is needed. To this end, we model DCBMs as a composition of deferring systems and derive a consistent L2D loss to train them. Moreover, by relying on a CBM architecture, DCBMs can explain why defer occurs on the final task. Our results show that DCBMs achieve high predictive performance and interpretability at the cost of deferring more to humans.

Benedetta Muscato, Lucia Passaro, Gizem Gezici et al.

In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual opinions can lead can lead to the side effect of underrepresenting minority perspectives, especially in subjective tasks, where annotators may systematically disagree because of their preferences. Recognizing that labels reflect the diverse backgrounds, life experiences, and values of individuals, this study proposes a new multi-perspective approach using soft labels to encourage the development of the next generation of perspective aware models, more inclusive and pluralistic. We conduct an extensive analysis across diverse subjective text classification tasks, including hate speech, irony, abusive language, and stance detection, to highlight the importance of capturing human disagreements, often overlooked by traditional aggregation methods. Results show that the multi-perspective approach not only better approximates human label distributions, as measured by Jensen-Shannon Divergence (JSD), but also achieves superior classification performance (higher F1 scores), outperforming traditional approaches. However, our approach exhibits lower confidence in tasks like irony and stance detection, likely due to the inherent subjectivity present in the texts. Lastly, leveraging Explainable AI (XAI), we explore model uncertainty and uncover meaningful insights into model predictions.

Daphne Lenders, Andrea Pugnana, Roberto Pellungrini et al.

Abstaining classifiers have the option to refrain from providing a prediction for instances that are difficult to classify. The abstention mechanism is designed to trade off the classifier's performance on the accepted data while ensuring a minimum number of predictions. In this setting, often fairness concerns arise when the abstention mechanism solely reduces errors for the majority groups of the data, resulting in increased performance differences across demographic groups. While there exist a bunch of methods that aim to reduce discrimination when abstaining, there is no mechanism that can do so in an explainable way. In this paper, we fill this gap by introducing Interpretable and Fair Abstaining Classifier IFAC, an algorithm that can reject predictions both based on their uncertainty and their unfairness. By rejecting possibly unfair predictions, our method reduces error and positive decision rate differences across demographic groups of the non-rejected data. Since the unfairness-based rejections are based on an interpretable-by-design method, i.e., rule-based fairness checks and situation testing, we create a transparent process that can empower human decision-makers to review the unfair predictions and make more just decisions for them. This explainable aspect is especially important in light of recent AI regulations, mandating that any high-risk decision task should be overseen by human experts to reduce discrimination risks.

Benedetta Muscato, Praveen Bushipaka, Gizem Gezici et al.

Subjective NLP tasks usually rely on human annotations provided by multiple annotators, whose judgments may vary due to their diverse backgrounds and life experiences. Traditional methods often aggregate multiple annotations into a single ground truth, disregarding the diversity in perspectives that arises from annotator disagreement. In this preliminary study, we examine the effect of including multiple annotations on model accuracy in classification. Our methodology investigates the performance of perspective-aware classification models in stance detection task and further inspects if annotator disagreement affects the model confidence. The results show that multi-perspective approach yields better classification performance outperforming the baseline which uses the single label. This entails that designing more inclusive perspective-aware AI models is not only an essential first step in implementing responsible and ethical AI, but it can also achieve superior results than using the traditional approaches.

Daniele Gambetta, Gizem Gezici, Fosca Giannotti et al.

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across generations. Recent studies have examined the emergence of model collapse across various generative AI models and data types, and have proposed mitigation strategies that rely on incorporating human-authored content. However, current characterizations of model collapse remain limited, and existing mitigation methods assume reliable knowledge of whether training data is human-authored or AI-generated. In this paper, we address these gaps by introducing new measures that characterise collapse directly from a model's next-token probability distributions, rather than from properties of AI-generated text. Using these measures, we show that the degree of collapse depends on the complexity of the initial training set, as well as on the extent of autophagy. Our experiments prompt a new suggestion: that model collapse occurs when a model trains on data that does not "surprise" it. We express this hypothesis in terms of the well-known Free Energy Principle in cognitive science. Building on this insight, we propose a practical mitigation strategy: filtering training items by high surplexity, maximising the surprise of the model. Unlike existing methods, this approach does not require distinguishing between human- and AI-generated data. Experiments across datasets and models demonstrate that our strategy is at least as effective as human-data baselines, and even more effective in reducing distributional skewedness. Our results provide a richer understanding of model collapse and point toward more resilient approaches for training generative AI systems in environments increasingly saturated with synthetic data.

Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti et al.

Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanations but have significant limitations. Local surrogates capture non-linearities but are computationally expensive and sensitive to parameters, while global surrogates are more efficient but struggle with complex local behaviors. In this paper, we present ILLUME, a flexible and interpretable framework grounded in representation learning, that can be integrated with various surrogate models to provide explanations for any black-box classifier. Specifically, our approach combines a globally trained surrogate with instance-specific linear transformations learned with a meta-encoder to generate both local and global explanations. Through extensive empirical evaluations, we demonstrate the effectiveness of ILLUME in producing feature attributions and decision rules that are not only accurate but also robust and faithful to the black-box, thus providing a unified explanation framework that effectively addresses the limitations of traditional surrogate methods.

Luca Pappalardo, Salvatore Citraro, Giuliano Cornacchia et al.

Recommendation systems and assistants (in short, recommenders) influence through online platforms most actions of our daily lives, suggesting items or providing solutions based on users' preferences or requests. This survey systematically reviews, categories, and discusses the impact of recommenders in four human-AI ecosystems -- social media, online retail, urban mapping and generative AI ecosystems. Its scope is to systematise a fast-growing field in which terminologies employed to classify methodologies and outcomes are fragmented and unsystematic. This is a crucial contribution to the literature because terminologies vary substantially across disciplines and ecosystems, hindering comparison and accumulation of knowledge in the field. We follow the customary steps of qualitative systematic review, gathering 154 articles from different disciplines to develop a parsimonious taxonomy of methodologies employed (empirical, simulation, observational, controlled), outcomes observed (concentration, content degradation, discrimination, diversity, echo chamber, filter bubble, homogenisation, polarisation, radicalisation, volume), and their level of analysis (individual, item, and ecosystem). We systematically discuss substantive and methodological commonalities across ecosystems, and highlight potential avenues for future research. The survey is addressed to scholars and practitioners interested in different human-AI ecosystems, policymakers and institutional stakeholders who want to understand better the measurable outcomes of recommenders, and tech companies who wish to obtain a systematic view of the impact of their recommenders.

Carlo Metta, Andrea Beretta, Riccardo Guidotti et al.

A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificial Intelligence (XAI) is trying to solve this issue. However, often XAI approaches are only tested on generalist classifier and do not represent realistic problems such as those of medical diagnosis. In this paper, we analyze a case study on skin lesion images where we customize an existing XAI approach for explaining a deep learning model able to recognize different types of skin lesions. The explanation is formed by synthetic exemplar and counter-exemplar images of skin lesion and offers the practitioner a way to highlight the crucial traits responsible for the classification decision. A survey conducted with domain experts, beginners and unskilled people proof that the usage of explanations increases the trust and confidence in the automatic decision system. Also, an analysis of the latent space adopted by the explainer unveils that some of the most frequent skin lesion classes are distinctly separated. This phenomenon could derive from the intrinsic characteristics of each class and, hopefully, can provide support in the resolution of the most frequent misclassifications by human experts.

Vasiliki Voukelatou, Ioanna Miliou, Fosca Giannotti et al.

Peacefulness is a principal dimension of well-being and is the way out of inequity and violence. Thus, its measurement has drawn the attention of researchers, policymakers, and peacekeepers. During the last years, novel digital data streams have drastically changed the research in this field. The current study exploits information extracted from a new digital database called Global Data on Events, Location, and Tone (GDELT) to capture peacefulness through the Global Peace Index (GPI). Applying predictive machine learning models, we demonstrate that news media attention from GDELT can be used as a proxy for measuring GPI at a monthly level. Additionally, we use explainable AI techniques to obtain the most important variables that drive the predictions. This analysis highlights each country's profile and provides explanations for the predictions, and particularly for the errors and the events that drive these errors. We believe that digital data exploited by researchers, policymakers, and peacekeepers, with data science tools as powerful as machine learning, could contribute to maximizing the societal benefits and minimizing the risks to peacefulness.

Francesco Bodria, Fosca Giannotti, Riccardo Guidotti et al.

The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.

Jisu Kim, Alina Sîrbu, Giulio Rossetti et al.

The cultural integration of immigrants conditions their overall socio-economic integration as well as natives' attitudes towards globalisation in general and immigration in particular. At the same time, excessive integration -- or acculturation -- can be detrimental in that it implies forfeiting one's ties to the home country and eventually translates into a loss of diversity (from the viewpoint of host countries) and of global connections (from the viewpoint of both host and home countries). Cultural integration can be described using two dimensions: the preservation of links to the home country and culture, which we call home attachment, and the creation of new links together with the adoption of cultural traits from the new residence country, which we call destination attachment. In this paper we introduce a means to quantify these two aspects based on Twitter data. We build home and destination attachment indexes and analyse their possible determinants (e.g., language proximity, distance between countries), also in relation to Hofstede's cultural dimension scores. The results stress the importance of host language proficiency to explain destination attachment, but also the link between language and home attachment. In particular, the common language between home and destination countries corresponds to increased home attachment, as does low proficiency in the host language. Common geographical borders also seem to increase both home and destination attachment. Regarding cultural dimensions, larger differences among home and destination country in terms of Individualism, Masculinity and Uncertainty appear to correspond to larger destination attachment and lower home attachment.

Mattia Setzu, Riccardo Guidotti, Anna Monreale et al.

Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and highly nonlinear machine learning models such as ensemble models, deep neural networks, and Support Vector Machines have consistently shown remarkable accuracy in solving complex tasks. Although accurate, AI models often are "black boxes" which we are not able to understand. Relying on these models has a multifaceted impact and raises significant concerns about their transparency. Applications in sensitive and critical domains are a strong motivational factor in trying to understand the behavior of black boxes. We propose to address this issue by providing an interpretable layer on top of black box models by aggregating "local" explanations. We present GLocalX, a "local-first" model agnostic explanation method. Starting from local explanations expressed in form of local decision rules, GLocalX iteratively generalizes them into global explanations by hierarchically aggregating them. Our goal is to learn accurate yet simple interpretable models to emulate the given black box, and, if possible, replace it entirely. We validate GLocalX in a set of experiments in standard and constrained settings with limited or no access to either data or local explanations. Experiments show that GLocalX is able to accurately emulate several models with simple and small models, reaching state-of-the-art performance against natively global solutions. Our findings show how it is often possible to achieve a high level of both accuracy and comprehensibility of classification models, even in complex domains with high-dimensional data, without necessarily trading one property for the other. This is a key requirement for a trustworthy AI, necessary for adoption in high-stakes decision making applications.

Ioanna Miliou, Xinyue Xiong, Salvatore Rinzivillo et al.

Increased availability of epidemiological data, novel digital data streams, and the rise of powerful machine learning approaches have generated a surge of research activity on real-time epidemic forecast systems. In this paper, we propose the use of a novel data source, namely retail market data to improve seasonal influenza forecasting. Specifically, we consider supermarket retail data as a proxy signal for influenza, through the identification of sentinel baskets, i.e., products bought together by a population of selected customers. We develop a nowcasting and forecasting framework that provides estimates for influenza incidence in Italy up to 4 weeks ahead. We make use of the Support Vector Regression (SVR) model to produce the predictions of seasonal flu incidence. Our predictions outperform both a baseline autoregressive model and a second baseline based on product purchases. The results show quantitatively the value of incorporating retail market data in forecasting models, acting as a proxy that can be used for the real-time analysis of epidemics.

Dino Pedreschi, Fosca Giannotti, Riccardo Guidotti et al.

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but also for possible biases hidden in the algorithms, due to human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of the many local explanations into simple global ones, with algorithms that optimize the quality and comprehensibility of explanations.

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri et al.

The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of explanations for the decisions of black box systems is a key ethical issue, and a limitation to the adoption of machine learning components in socially sensitive and safety-critical contexts. %Therefore, we need explanations that reveals the reasons why a predictor takes a certain decision. In this paper we focus on the problem of black box outcome explanation, i.e., explaining the reasons of the decision taken on a specific instance. We propose LORE, an agnostic method able to provide interpretable and faithful explanations. LORE first leans a local interpretable predictor on a synthetic neighborhood generated by a genetic algorithm. Then it derives from the logic of the local interpretable predictor a meaningful explanation consisting of: a decision rule, which explains the reasons of the decision; and a set of counterfactual rules, suggesting the changes in the instance's features that lead to a different outcome. Wide experiments show that LORE outperforms existing methods and baselines both in the quality of explanations and in the accuracy in mimicking the black box.

Luca Pappalardo, Paolo Cintia, Paolo Ferragina et al.

The problem of evaluating the performance of soccer players is attracting the interest of many companies and the scientific community, thanks to the availability of massive data capturing all the events generated during a match (e.g., tackles, passes, shots, etc.). Unfortunately, there is no consolidated and widely accepted metric for measuring performance quality in all of its facets. In this paper, we design and implement PlayeRank, a data-driven framework that offers a principled multi-dimensional and role-aware evaluation of the performance of soccer players. We build our framework by deploying a massive dataset of soccer-logs and consisting of millions of match events pertaining to four seasons of 18 prominent soccer competitions. By comparing PlayeRank to known algorithms for performance evaluation in soccer, and by exploiting a dataset of players' evaluations made by professional soccer scouts, we show that PlayeRank significantly outperforms the competitors. We also explore the ratings produced by {\sf PlayeRank} and discover interesting patterns about the nature of excellent performances and what distinguishes the top players from the others. At the end, we explore some applications of PlayeRank -- i.e. searching players and player versatility --- showing its flexibility and efficiency, which makes it worth to be used in the design of a scalable platform for soccer analytics.

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri et al.

In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness sometimes at the cost of scarifying accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, delineating explicitly or implicitly its own definition of interpretability and explanation. The aim of this paper is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

Luca Pappalardo, Paolo Cintia, Dino Pedreschi et al.

Humans are routinely asked to evaluate the performance of other individuals, separating success from failure and affecting outcomes from science to education and sports. Yet, in many contexts, the metrics driving the human evaluation process remain unclear. Here we analyse a massive dataset capturing players' evaluations by human judges to explore human perception of performance in soccer, the world's most popular sport. We use machine learning to design an artificial judge which accurately reproduces human evaluation, allowing us to demonstrate how human observers are biased towards diverse contextual features. By investigating the structure of the artificial judge, we uncover the aspects of the players' behavior which attract the attention of human judges, demonstrating that human evaluation is based on a noticeability heuristic where only feature values far from the norm are considered to rate an individual's performance.