Artificial intelligence (AI) systems are increasingly adopted in high‐stakes domains such as healthcare and finance, so the demand for transparency and interpretability has grown substantially. EXplainable AI (XAI) methods have emerged to address this challenge, but individual techniques often offer limited, fragmented insights. This paper introduces Meta‐explainers, a novel ensemble‐based XAI framework that integrates multiple explanation types—specifically relevance‐based and counterfactual methods—into unified, multifaceted and complementary meta‐explanations. Inspired by meta‐classification principles, our approach structures the explanation process into five stages: generation, grouping, evaluation, aggregation, and visualization. Each stage is designed to preserve the unique strengths of individual XAI techniques while enhancing their interpretability and coherence when combined. Experimental results on both image (MNIST) and tabular (Breast Cancer) datasets show that Meta‐explainers consistently outperform individual and state‐of‐the‐art ensemble explanation methods in terms of explanation quality, as measured by established metrics. This work paves the way toward more holistic and user‐centered AI explainability with a flexible methodology that can be extended to incorporate additional explanation paradigms.

Although deep learning models can solve complex prediction problems, they have been criticized for being ‘black boxes’. This implies that their decisions are difficult, if not impossible, to explain by simply inspecting their internal knowledge structures. Explainable Artificial Intelligence has attempted to open the black-box through model-specific and agnostic post-hoc methods that generate visualizations or derive associations between the problem features and the model predictions. This paper proposes a new method, termed REPROT, that explains the decisions of complex deep learning architectures based on local reducts of an image. A ‘reduct’ is a set of sufficiently descriptive features that can fully characterize the acquired knowledge. The created reducts are used to build a ‘prototype image’ that visually explains the inference obtained by a black-box model for an image. We focus on deep learning architectures whose complexity and internal particularities demand adapting existing model-specific explanation methods, making the explanation process more difficult. Experimental results show that the black-box model can detect an object using the prototype image generated from the reduct. Hence, the explanations will be given by “the minimum set of features sufficient for the neural model to detect an object”. The confidence scores obtained by architectures such as Inception, Yolo, and Mask R-CNN are higher for prototype images built from the reduct than those built from the most important superpixels according to the LIME method. Moreover, the target object is not detected on several occasions through the LIME output, thus supporting the superiority of the proposed explanation method.

Age estimation is a fundamental task in forensic anthropology for both the living and the dead. The procedure consists of analyzing properties such as appearance, ossification patterns, and morphology in different skeletonized remains. The pubic symphysis is extensively used to assess adults’ age-at-death due to its reliability. Nevertheless, most methods currently used for skeleton-based age estimation are carried out manually, even though their automation has the potential to lead to a considerable improvement in terms of economic resources, effectiveness, and execution time. In particular, explainable machine learning emerges as a promising means of addressing this challenge by engaging forensic experts to refine and audit the extracted knowledge and discover unknown patterns hidden in the complex and uncertain available data. In this contribution we address the automation of the decision making process of Todd’s pioneering age assessment method to assist the forensic practitioner in its application. To do so, we make use of the pubic bone data base available at the Physical Anthropology lab of the University of Granada. The machine learning task is significantly complex as it becomes an imbalanced ordinal classification problem with a small sample size and a high dimension. We tackle it with the combination of an ordinal classification method and oversampling techniques through an extensive experimental setup. Two forensic anthropologists refine and validate the derived rule base according to their own expertise and the knowledge available in the area. The resulting automatic system, finally composed of 34 interpretable rules, outperforms the state-of-the-art accuracy. In addition, and more importantly, it allows the forensic experts to uncover novel and interesting insights about how Todd’s method works, in particular, and the guidelines to estimate age-at-death from pubic symphysis characteristics, generally.

In the bounded confidence framework, agents’ opinions evolve as a result of interactions with other agents having similar opinions. Thus, consensus or fragmentation of opinions can be reached, but not extremization (the evolution of opinions towards an extreme value). In contrast, when repulsion mechanisms are at work, agents with distant opinions interact and repel each other, leading to extremization. This work proposes a general opinion dynamics framework of bounded confidence and repulsion, which includes social network interactions and agent-independent time-varying rationality. We extensively analyze the performance of our model to show that the degree of extremization among a population can be controlled by the repulsion rule, and social networks promote extreme opinions. Agent-based rationality and time-varying adaptation also bear a strong impact on opinion dynamics. The high accuracy of our model is determined in a real-world social network well referenced in the literature, the Zachary Karate Club (with a known ground truth). Finally, we use our model to analyze the extremization of opinions in a real-world scenario, in Spain: a marketing action for the Netflix series “Narcos”.

Understanding consumer behaviors and how consumers react to marketing campaigns and viral word-of-mouth processes is crucial for marketers. Classical approaches try to infer this information from a global top-down perspective. However, a more suitable and natural approach is to model consumer behaviors in a heterogeneous and decentralized bottom-up approach. In this case, each virtual consumer has her own mental state and decision-making strategies to simulate her purchase decisions. The system of virtual consumers generates the global sales and a marketer can understand the rules that govern the market. A well-known paradigm to model these systems is agent-based modeling (ABM). In this manuscript we present an ABM where the brand preferences of the consumer agents are modeled using 2-tuple fuzzy linguistic variables. These variables represent the perceptions these consumers have on the different aspects or drivers every product available in the market has (e.g., price or quality). The product selection process of the agents is based on those perceptions and a utility maximization rule. This rule requires a fuzzy aggregation of the fuzzy linguistic perceptions about the products. Our proposal employs an ordered weighted average (OWA) to aggregate them. Our experiments show this approach does not suffer any loss of information when applied on data from real markets. Hence it is a suitable representation of the products preferences, normally represented by qualitative values in marketing surveys. To the best of our knowledge, this is the first work integrating a marketing ABM with fuzzy linguistic modeling.

Marketing professionals face challenges of increasing complexity to adapt classic marketing strategies to the phenomenon of social networks. Companies are currently trying to take advantage of the useful collective knowledge available on social networks to support different types of marketing decisions. The appropriate analysis of this information can offer marketing professionals with important competitive advantages. This work proposes a new methodology to extract the social collective behavior of Twitter users concerning a group of brands based on the users’ temporal activity. Time series of mentions made by individual users to each company's Twitter account are aggregated to obtain collective activity data for the companies, which is a consequence of both the company's and other users’ actions. These data are processed using classical unsupervised machine learning techniques, such as temporal clustering and hidden Markov models, to extract collective temporal behavior patterns and models of the dynamics of customers over time for a single brand and groups of brands. The derived knowledge can be used for different tasks, such as identifying the impact of a marketing campaign on Twitter and comparatively assessing the social behaviors of different brands and groups of brands to assist in making marketing decisions. Our methodology is validated in a case study from the wine market. Twitter data were gathered from four regions of different countries around the world with important wineries (Italy: Veneto, Portugal: Porto and Douro Valley, Spain: La Rioja, and United States: Napa Valley), and comparative behavior analysis was carried out from the perspective of the use of Twitter as a communication channel for marketing campaigns.

Abstract Network scaling algorithms such as the Pathfinder algorithm are used to prune many different kinds of networks, including citation networks, random networks, and social networks. However, this algorithm suffers from run time problems for large networks and online processing due to its O(n4) time complexity. In this article, we introduce a new alternative, the MST‐Pathfinder algorithm, which will allow us to prune the original network to get its PFNET(∞, n − 1) in just O(n2 · log n) time. The underlying idea comes from the fact that the union (superposition) of all the Minimum Spanning Trees extracted from a given network is equivalent to the PFNET resulting from the Pathfinder algorithm parameterized by a specific set of values (r = ∞ and q = n − 1), those usually considered in many different applications. Although this property is well‐known in the literature, it seems that no algorithm based on it has been proposed, up to now, to decrease the high computational cost of the original Pathfinder algorithm. We also present a mathematical proof of the correctness of this new alternative and test its good efficiency in two different case studies: one dedicated to the post‐processing of large random graphs, and the other one to a real world case in which medium networks obtained by a cocitation analysis of the scientific domains in different countries are pruned.

This work presents the use of local fuzzy prototypes as a new idea to obtain accurate local semantics-based Takagi–Sugeno–Kang (TSK) rules. This allow us to start from prototypes considering the interaction between input and output variables and taking into account the fuzzy nature of the TSK rules. To do so, a two-stage evolutionary algorithm based on MOGUL (a methodology to obtain Genetic Fuzzy Rule-Based Systems under the Iterative Rule Learning approach) has been developed to consider the interaction between input and output variables. The first stage performs a local identification of prototypes to obtain a set of initial local semantics-based TSK rules, following the Iterative Rule Learning approach and based on an evolutionary generation process within MOGUL (taking as a base some initial linguistic fuzzy partitions). Because this generation method induces competition among the fuzzy rules, a postprocessing stage to improve the global system performance is needed. Two different processes are considered at this stage, a genetic niching-based selection process to remove redundant rules and a genetic tuning process to refine the fuzzy model parameters. The proposal has been tested with two real-world problems, achieving good results. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 909–941, 2007.

The main aim of this paper is to present MOGUL, a Methodology to Obtain Genetic fuzzy rule-based systems Under the iterative rule Learning approach. MOGUL will consist of some design guidelines that allow us to obtain different genetic fuzzy rule-based systems, i.e., evolutionary algorithm-based processes to automatically design fuzzy rule-based systems by learning and/or tuning the fuzzy rule base, following the same generic structure and able to cope with problems of a different nature. A specific evolutionary learning process obtained from the paradigm proposed to design unconstrained approximate Mamdani-type fuzzy rule-based systems will be introduced, and its accuracy in the solving of a real-world electrical engineering problem will be analyzed. ©1999 John Wiley & Sons, Inc.

In this paper, we present a multistage genetic learning process for obtaining linguistic fuzzy rule-based classification systems that integrates fuzzy reasoning methods cooperating with the fuzzy rule base and learns the best set of linguistic hedges for the linguistic variable terms. We show the application of the genetic learning process to two well known sample bases, and compare the results with those obtained from different learning algorithms. The results show the good behavior of the proposed method, which maintains the linguistic description of the fuzzy rules. © 1998 John Wiley & Sons, Inc.