One of the main lines of research in the discipline of mobility mining is the development of predictors able to anticipate human travel behaviour in great detail. However, access to the high-resolution spatio-temporal data on which most existing solutions are based is rather limited due to multiple factors, e.g. costly access to third-party data. These restrictions give rise to a problem of developing predictors of human mobility in most setting, since the amount of data available to train these prediction models is insufficient. This paper explores the feasibility of using a public data source such as Twitter to predict the number of trips at the nationwide level. The proposed approach combines a large set of geotagged Twitter posts with an open data source published by the Spanish government on traveller mobility based on mobile phone location. Both datasets are used as input to Machine Learning models to validate the use of Twitter data for improving the prediction of these models. The results show that Twitter data have considerable value as a predictor of large-scale human mobility, especially for Long Short-Term Memory (LSTM) models. As a result, the relevance of this work resides in demonstrating that the use of Twitter could be considered as an alternative to substantially enhance the
prediction of mobility within a country when it is combined with other open data sources.

The management of road traffic incidents is a problem faced by governments in many countries. Normally, road operators have the infrastructure in place to monitor such incidents, albeit in a reactive manner. In Spain, there are traffic cameras on major roads to check for possible incidents, however, incident notification is slow and not automated. As an alternative, this paper proposes a system for automatic real-time traffic alerts. Thus, 1,500 camera images from the Dirección General de Tráfico (DGT) deployed on the main Spanish roads are analyzed in real time every 4 minutes. These images are not preprocessed, they have different qualities and are also affected by weather conditions such as fog, rain, sun reflections, etc. The system uses several Deep Learning classification models trained on a well-known dataset of traffic images including flowing traffic, dense traffic, accidents and fires. These models are used to classify the DGT images in real time, with satisfactory initial results, detecting both flowing traffic and dense traffic.

Tourism has become a very active ecosystem to deploy solutions based on Information and Communication Technologies. Indeed, it is now possible to analyse the mobility behaviour of tourists in great detail. However, current solutions aimed at anticipating tourist flows usually follow a limited approach based on the local (e.g., to predict the next landmark to visit) or regional (e.g., to predict the incoming number of tourists in a city) level. This paper states a novel approach to solve the problem of tourist inflow forecasting on a broader nationwide scale by defining it as an edge prediction task. To do so, we model the tourist mobility of a country as a graph which fuses heterogeneous tourism data obtained from multiple sources related to the country's mobility and infrastructure features. Then, as a major contribution, an ensemble of Graph Neural Networks are fed with the graph models to provide the final prediction. The proposed solution has been tested in Spain showing a F1 score higher than 0.7., 16 páginas

Traffic congestion is a significant problem in many cities, leading to delays, increased fuel consumption, and environmental pollution. In recent years, optimization algorithms have been used to improve traffic control systems and reduce congestion. This paper proposes an optimization algorithm based on genetic algorithms to optimize traffic signal controllers in Cádiz, Spain, using the Simulation of Urban MObility (SUMO) traffic simulator. The proposed optimization algorithm is a promising solution for the optimization of traffic control systems, which can lead to more efficient traffic flow, reduced congestion, and improved environmental conditions.

Time-series analysis plays a crucial role in extracting meaningful patterns from sequential data, serving to gain insights into temporal trends. Specifically, the burgeoning urbanization trend accentuates the urgency of traffic forecasting in modern cities due to its socio-economic and environmental impact. While Deep Learning techniques, notably Long Short-Term Memory (LSTM) networks, have shown promise in predicting traffic, they often overlook contextual factors like weather and holidays. To address this challenge, this paper proposes a hybrid model combining LSTM with categorical and continuous data to forecast traffic volume on the Interstate 94 American highway. Incorporating weather, temporal patterns, and holidays, this study explores the performance of a model that includes contextual factors against standalone LSTM. The results show superior predictive accuracy for the proposed hybrid model. SHapley Additive exPlanations (SHAP) analysis reveals the influence of diverse features, emphasizing the significance of contextual attributes in enhancing traffic prediction.

This paper presents a novel Multi-DL Fuzzy Approach aimed at performing image recognition in the development of a real-time traffic alert system, addressing the problem of traffic congestion and related incidents. Traditional monitoring by road operators predominantly relies on fixed location cameras, yielding limited and sometimes ambiguous information. This study proposes leveraging Twitter (now known as 'X') as a more comprehensive data source alongside employing fuzzy techniques with Deep Learning (DL) neural networks such as CNN, VGG16, and Xception to analyze and classify traffic images. The innovative integration of these technologies augments the precision in categorizing varying traffic conditions, namely fluid and dense traffic, accidents and fires. Thus, this proposal mitigates the ambiguities prevalent in traffic image interpretation, and reduces the dependency on static data sources. The proposed models showed improved results by combining information from the DL models, elevating accuracy from 84% in crisp classification to 90% utilizing fuzzy information.

Predicting human mobility is a key element in the development of intelligent transport
systems. Current digital technologies enable capturing a wealth of data on mobility flows between
geographic areas, which are then used to train machine learning models to predict these flows.
However, most works have only considered a single data source for building these models or
different sources but covering the same spatial area. In this paper we propose to augment a macro
open-data mobility study based on cellular phones with data from a road traffic sensor located
within a specific motorway of one of the mobility areas in the study. The results show that models
trained with the fusion of both types of data, especially long short-term memory (LSTM) and
Gated Recurrent Unit (GRU) neural networks, provide a more reliable prediction than models
based only on the open data source. These results show that it is possible to predict the traffic
entering a particular city in the next 30 minutes with an absolute error less than 10%. Thus, this
work is a further step towards improving the prediction of human mobility in interurban areas by
fusing open data with data from IoT systems.

Countries all around the world recognise the impact of air quality on public health, advocating for city centre decarbonisation and pollutant monitoring via Internet of Things technologies. Using data collected from these systems, it is possible to generate models that predict pollution based on regular patterns where mobility data can enhance the accuracy and robustness of these advanced machine learning models. This paper follows this approach, utilising vehicle traffic data from image recognition, on-site vehicle detectors, and synthetic data to maximise prediction accuracy in various urban environments. The results reveal that this proposal improves prediction for traffic-related pollutants, such as SO2 and PM2.5 , which are linked to severe respiratory diseases. These results also highlight the role of synthetic data in enhancing prediction performance under limited datasets.

Nowadays, music streaming services allow users to get instant access to an unprecedented amount of music of any type. This entails that songs, including potential new hits, can be discovered by listeners in any part of the globe and their propagation can be tracked through these streaming services. In this context, the present work focuses on recognizing the mobility patterns that songs follow in such a propagation among different countries of the world. To this end, this work defines a novel mechanism to uncover such mobility patterns of music from a directed-graph structure where nodes are countries and each edge reflects a frequent propagation of songs between pairs of countries. The resulting patterns reflect strong correlations with the migratory flows and the cultural and social similarities among regions. For instance, a propagation pattern was observed among North European countries with a good command of English. From such patterns, potential predictors for anticipating the mobility of a song are discussed. The results of this work can be beneficial for record companies and artists in their marketing campaigns for album releases and the organization of concerts and festivals.

Sentiment analysis has gained prominence in the digital era, particularly within social media contexts. This study explores the integration of metadata, such as reposts, favorites, or followers, alongside textual information for sentiment analysis. A dataset of posts in Spanish is created, filtering by a set of keywords (a total of 17) of interest to us. A total of 3,962 posts were collected along with their metadata. Then, they have been manually classified as positive, negative, and neutral, and processed. The research studies and compares different models like LightGBM, BERT, and a hybrid model combining BERT outputs with metadata. Evaluation metrics, such as F1-score and precision, were employed, revealing that the hybrid model achieved the highest F1-score of 69.4%, showcasing the effectiveness of merging text comprehension capabilities with contextual metadata. While the incorporation of metadata enhanced overall sentiment classification, precision varied across sentiment classes, with notable improvements in neutral and positive sentiments, over 16% and 8% respectively.

During the last years, the analysis of spatio-temporal data extracted from Online Social Networks (OSNs) has become a prominent course of action within the human-mobility mining discipline. Due to the noisy and sparse nature of these data, an important effort has been done on validating these platforms as suitable mobility proxies. However, such a validation has been usually based on the computation of certain features from the raw spatio-temporal trajectories extracted from OSN documents. Hence, there is a scarcity of validation studies that evaluate whether geo-tagged OSN data are able to measure the evolution of the mobility in a region at multiple spatial scales. For that reason, this work proposes a comprehensive comparison of a nation-scale Twitter (TWT) dataset and an official mobility survey from the Spanish National Institute of Statistics. The target time period covers a three-month interval during which Spain was heavily affected by the COVID-19 pandemic. Both feeds have been compared in this context by considering different mobility-related features and spatial scales. The results show that TWT could capture only a limited number features of the latent mobility behaviour of Spain during the study period.

The use of Generative Artificial Intelligence (GenAI) is revolutionising how companies create digital content on social networks. However, how users respond to this content remains less explored. The aim of this article is to compare GenAI-generated content with human-generated content on Instagram. First, through a survey of 273 students, we explored user engagement with the eSports team’s content on Instagram. Second, we measured followers’ engagement behaviors (i.e., “likes”, comments, shares and reach) with GenAI-generated content versus human-created content. Results indicate that both GenAI tools (ChatGPT and Gemini) achieved similar levels of engagement in terms of “likes”. ChatGPT stood out for its use of interactive features like opinion polls, particularly in “stories”, while Gemini excelled in total reach and visibility. In contrast, human-generated content attracted a higher proportion of non-followers, suggesting a stronger potential to expand the existing audience. These findings underscore the advantages of adopting a hybrid strategy that combines the scalability and speed of GenAI with the contextual relevance and authenticity of human-created content.

To identify influential nodes in real networks, it is essential to note the importance of considering the local and global information in a network. In addition, it is also key to consider the dynamic information. Accordingly, the main aim of this paper is to present a new centrality measure based on return random walk and the effective distance gravity model (CRRWG). This new metric increases the relevance of nodes with a dual role: i) at the local level, they are important in their community or cluster, and ii) at the global level, they give cohesion to the network. It has advantages over other traditional models of centrality since it considers the global and local information, as well as the information of the dynamic interaction between the nodes, as recent studies on community-aware centrality measures demonstrate. Thus, the combination of dynamic and static information makes it easier to detect influential nodes in complex networks. To validate the effectiveness of the proposed centrality measure, it is compared with classic measures, such as Degree, Closeness, Betweenness, PageRank, and other measures based on the gravity model, effective distance and community-aware approaches. The experimental results show the effectiveness of CRRWG through a set of experiments on different types of networks.

Pollution in urban areas is turning into a primary focus for local governments in developed nations around the globe. Lots of data are currently collected for this from smart developments provided with atmospheric and climatic sensors. A hot research line is now exploiting such data to extract patterns and predict pollution levels in such a way that countermeasures can be taken beforehand and exposure to harmful concentrations is avoided. However, a key issue is the lack of significant data, due to incomplete smart infrastructures or calibration problems in sensors. Dealing with this, in this paper we propose the exploitation of synthetic data generation to enhance pollution prediction based on limited data sources, concretely extending real measurements of two weeks to up to ten extra years. We present a data generation approach based on Generative Adversarial Networks (GANs), with a particular model focused on generating artificial pollution data, which is later exploited using different Machine Learning (ML) algorithms. Results indicate that the usage of synthetic data further improves prediction when used as the basis dataset to be later finetuned using real records. For 62% of pollutants this way to proceed in data mixing (among five different approaches) provides the best results in evaluations. Such effect is due to extra model robustness due to data regularization, and better generalization capabilities by avoiding sensor limitations in real deployments.

The World Health Organization highlights that the number of annual road traffic deaths has reached 1.35 million (Global Status Report on Road Safety 2018). In addition, million of people suffer more or less important injuries as a consequence of this type of accidents. In this scenario, the prediction of the severity of traffic accidents is an essential point when it comes to improving the prevention and reaction of the entities responsible. On the other hand, the development of reliable methodologies to predict and classify the level of severity of traffic accidents, based on various variables, is a key component in the field of research in road safety. This work aims to propose a new approach, based on convolutional neural networks, for the detection of the severity of traffic accidents. Behind this objective is the preprocessing, analysis and visualization of data as well as the design, implementation and comparison of machine learning models considering accuracy as a performance indicator. For this purpose, a scalable and easily reusable methodology has been implemented. This methodology has been compared with other deep learning models verifying that the results of the designed neural network offer better performance in terms of quality measures.

Motivated by the large number of wearables offering geolocation, human mobility mining has emerged as an novel research field within AI. The study of mobility creates increasingly predictable models in which it is easy to find patterns of behaviour. However, this data is not publicly available and access to it is restricted to large telecommunications operators. In this context, this paper aims to solve one of the main problems of human mobility databases, i.e. the scarcity of data for the generation of human mobility models. For this purpose, Generative adversarial network (GANs) have been proposed to generate synthetic time-series mobility data. Moreover, several neural network models are proposed to assess the impact of synthetic data generation on the prediction of human mobility. Our results show that the use of synthetic data improves predictions of human mobility compared to models based on available measured data. Specifically, the reinforcement learning with synthetic data benchmark, when compared to using only ground truth data, achieved a 1.22% improvement in R2, a 0.70% reduction in RMSE, a 2.97% decrease in MAE, a 27.07% reduction in MAPE, and an 18.18% improvement in CVRMSE, demonstrating its effectiveness in enhancing predictive accuracy.Motivated by the large number of wearables offering geolocation, human mobility mining has emerged as an novel research field within AI. The study of mobility creates increasingly predictable models in which it is easy to find patterns of behaviour. However, this data is not publicly available and access to it is restricted to large telecommunications operators. In this context, this paper aims to solve one of the main problems of human mobility databases, i.e. the scarcity of data for the generation of human mobility models. For this purpose, Generative adversarial network (GANs) have been proposed to generate synthetic time-series mobility data. Moreover, several neural network models are proposed to assess the impact of synthetic data generation on the prediction of human mobility. Our results show that the use of synthetic data improves predictions of human mobility compared to models based on available measured data. Specifically, the reinforcement learning with synthetic data benchmark, when compared to using only ground truth data, achieved a 1.22% improvement in R2, a 0.70% reduction in RMSE, a 2.97% decrease in MAE, a 27.07% reduction in MAPE, and an 18.18% improvement in CVRMSE, demonstrating its effectiveness in enhancing predictive accuracy.

Centrality metrics are one of the most meaningful features in a large number of real-world network systems. In that sense, the Betweenness centrality is a widely used measurement that quantifies the importance of a node in the information flow in a network. Moreover, there is a centrality measure, based on random-paths betweenness centrality, that provides a classification of the nodes of undirected networks, that are able to reinforce dense communities according to their role. In this paper, a new centrality model, based on random-paths betweenness centrality and applied on directed networks, is presented. This model, based on four indices, describes the behaviour of the nodes within the network in terms of its role, such as a transition node, in the same cluster or between clusters. Finally, we evaluate the model with several use cases based on real networks, two of them are proposed and created in this paper, giving insight into some interesting findings about the networks’ features.

Key nodes have a significant impact, both structural and functional, on complex networks. Evaluating the importance of a node, from an information flow perspective, has applications in many areas but, to a great extent, they are focused on the shortest path perspective. Then, there exist measures based on the representation of the frequency in which each node plays the role of a transition node by random trajectories between two other nodes. Development of a specific kind of material, metallic glasses, has been mainly based on trial and error methods and, this approach is inefficient in terms of time and cost. Therefore, the development of new approaches for metallic glasses design remains an open topic for researchers in this field. The understanding of the role of each element could be useful for the generation of new metallic glasses and the improvement of existing ones. This work aims to study the formation capacity of metallic glass from the point of view of complex networks, using random walk betweenness centrality approaches, as well as the proposal of a new hypothesis that can serve as a roadmap for future research in this field of generation of new metallic glass. The results and discussions indicate that the proposed approach may be of great interest, for the development of metallic glasses, given the great correlation between the results of this study and the actual obtaining of metallic glasses in recent research.

This paper is republished with permission of the International Institute of Acoustics and Vibration. It was originally published in the Proceedings of the 29th International Congress on Sound and Vibration, Prague, July 9-13, 2023, To manage noise pollution, cities use monitoring systems over wireless acoustic sensor networks. These networks are mainly composed of fixed-location sound pressure level sensors deployed in outdoor sites of the city for long-term monitoring. However, due to high economic and human resource costs, it is not feasible to deploy fixed metering stations on every street in a city. Therefore, these continuous measurements are usually complemented with short-term measurements at different selected locations, which are carried out by acoustic sensors mounted on vehicles or at street level. In this research, the sensitivity of artificial neural networks for estimation of the long-term environmental acoustic pattern of a location based on the information collected during a short time period is analyzed. An evaluation has been carried out through a comparison of eight artificial neural network architectures using real data from the acoustic sensor network of Barcelona, Spain, showing that precision and recall performance appears to be more strongly associated with environmental patterns rather than the considered architecture.

Many cities around the world are deploying wireless sensor networks to capture information on different environmental parameters. Noise, as one of the main pollutants with negative effects on health and economy, is monitored through sound pressure level. In this work, the application of unsupervised clustering to sound pressure level data from a wireless acoustic sensors network (WASN) is proposed. Data from a sensor network deployed in the city of Madrid are used to show the
usefulness of performing a clustering process with the aim of detecting different patterns of behavior of noise levels. The preliminary results obtained have allowed us to divide the city into several acoustic zones, which help city managers to propose improvement plans.

[EN] Ontological model that categorises dimensions, domains, and types of problems that can affect citizens' quality of life and well-being., Esta ontología es parte del proyecto de I+D+i PID2020-112827GB-I00 financiado por MICIU/AEI/10.13039/501100011033.

[EN] Citizens¿ experiences are posted on social-media platforms (e.g. Twitter, Facebook, etc.)
to share their opinions, report significant occurrences, or show situations of interest. In
this way, citizens can act as social sensors, providing useful information for public institutions, companies or other citizens in decision making. In this context, DIAPASON (unifieD
hybrId ApProach to microtext Analysis in Social-media crOwdseNsing) is a system that
explores text-based user-generated content to detect problems in a given community. This
chapter aims to present the knowledge acquisition, specification and conceptualisation
stages in the development of the ontological model of DIAPASON. To illustrate, we describe the case of Beach Quality problems., This publication is part of the R&D&i project PID2020-112827GB-I00,
funded by MICIU/AEI/10.13039/501100011033.

The constructional element of irony has been noted by Veale (2012) and Veale & Hao
(2010), who claim that ironic interpretation can be triggered by conventionalized constructions
that bear a high ironic potential, as is the case of about as X as Y (About as fun
as watching paint dry). In inferential pragmatics, Attardo (2000) identifies indices of irony
(e.g. agreement markers such as yeah , right , sure ), which, in our view, can be regarded
as contributing factors or constraints on the characterization of potentially ironic constructions.
The present paper addresses the constructional dimension of irony, with special
emphasis on the axiological element of potentially ironic constructions, and it explains
implicational constructions and attitudinal and denotational figures of speech in relation
to irony. Axiology relates to the positive or negative evaluation of the various elements of
an utterance and is based on its explicit content and its additional meaning implications.
For instance, in the example mentioned above, the axiological load of the construction
depends largely on the meaning implications of the monotonous and uneventful activity
of observing paint dry. The heavy attitudinal element of irony makes this figure of speech
a particularly fertile ground for the study of axiological neutrality and non-neutrality. The
present paper provides a preliminary approach to the strategies that serve the purpose of
triggering the ironic interpretation of utterances., This publication is part of the R&D&i project PID2020-112827GB-I00,
funded by MICIU/AEI/10.13039/501100011033.

Datasets of English and Spanish tweets used in the project "ALLEGRO: Smart multi-modal crowdsensing-based system as a service oriented to the prediction of social problems". Tweets in each dataset were manually tagged according to a specific social problem: Black Economy, Institutional Elder Abuse, Student Dropout, and Violence Against Women., Este database es parte del proyecto de I+D+i PID2020-112827GB-I00 financiado por MICIU/AEI/10.13039/501100011033.

[EN] We are witnessing the digitalization era, where artificial intelligence (AI)/machine learning (ML) models are mandatory to
transform this data deluge into actionable information. However, these models require large, high-quality datasets to predict
high reliability/accuracy. Even with the maturity of Internet of Things (IoT) systems, there are still numerous scenarios where
there is not enough quantity and quality of data to successfully develop AI/ML-based applications that can meet market
expectations. One such scenario is precision agriculture, where operational data generation is costly and unreliable due to
the extreme and remote conditions of numerous crops. In this paper, we investigated the generation of synthetic data as a
method to improve predictions of AI/ML models in precision agriculture. We used generative adversarial networks (GANs)
to generate synthetic temperature data for a greenhouse located in Murcia (Spain). The results reveal that the use of synthetic
data significantly improves the accuracy of the AI/ML models targeted compared to using only ground truth data., This work is derived from R&D projects RTC2019-007159-5, as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, FSE invest in your future and ERDF A way of making Europe and the grant PID2020-112827GBI00 funded by MCIN/AEI/10.13039/501100011033.

[EN] Motivated by the large number of wearables offering geolocation, human mobility mining has emerged as an novel research field within AI. The study of mobility creates increasingly predictable models in which it is easy to find patterns of behaviour. However, this data is not publicly available and access to it is restricted to large telecommunications operators. In this context, this paper aims to solve one of the main problems of human mobility databases, i.e. the scarcity of data for the generation of human mobility models. For this purpose, Generative adversarial network (GANs) have been proposed to generate synthetic time-series mobility data. Moreover, several neural network models are proposed to assess the impact of synthetic data generation on the prediction of human mobility. Our results show that the use of synthetic data improves predictions of human mobility compared to models based on available measured data. Specifically, the reinforcement learning with synthetic data benchmark, when compared to using only ground truth data, achieved a 1.22% improvement in R2, a 0.70% reduction in RMSE, a 2.97% decrease in MAE, a 27.07% reduction in MAPE, and an 18.18% improvement in CVRMSE, demonstrating its effectiveness in enhancing predictive accuracy., This work is derived from R&D projects RTC2019-007159-5, as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, "FSE invest in your future" and "ERDF A way of making Europe" and the grant PID2020-112827GB-I00 funded by MCIN/AEI/10.13039/501100011033.

[EN] The management of the COVID-19 pandemic has been shown to be critical for reducing its dramatic effects. Social sensing can analyse user-contributed data posted daily in social-media services, where participants are seen as Social Sensors. Individually, social sensors may provide noisy information. However, collectively, such opinion holders constitute a large critical mass dispersed everywhere and with an immediate capacity for information transfer. The main goal of this article is to present a novel methodological tool based on social sensing, called COVIDSensing. In particular, this application serves to provide actionable information in real time for the management of the socio-economic and health crisis caused by COVID-19. This tool dynamically identifies socio-economic problems of general interest through the analysis of people¿s opinions on social networks. Moreover, it tracks and predicts the evolution of the COVID-19 pandemic based on epidemiological figures together with the social perceptions towards the disease. This article presents the case study of Spain to illustrate the tool., This work is derived from R&D project RTI2018-096384-B-I00, as well as the Ramon y
Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033 and ERDF A way
of making Europe, by the Spanish Agencia Estatal de Investigación (grant number PID2020-
112827GB-I00/ AEI/10.13039/501100011033), and by the Conselleria de Innovación, Universidades,
Ciencia y Sociedad Digital, Proyectos AICO/2020, Spain, under Grant AICO/2020/302.

[EN] Greenhouses constitute intricate systems where numerous variables play a pivotal role in enhancing crop yields within the framework of intensive agriculture. Consequently, real-time monitoring and visualization of these variables are imperative to strike a balance between resource efficiency and production maximization. Furthermore, the ability to make predictive assessments regarding these variables is essential to avert potential greenhouse disasters. In this article, we introduce an intelligent alert system designed to efficiently oversee agricultural operations within a functioning greenhouse, ultimately bolstering productivity through the optimization of crop growth and energy consumption. This system comprises a web application, GreenhouseGuard, which improves the graphical and statistical representation of data collected by a network of sensors strategically positioned throughout the greenhouse, as well as the forecasts generated from this data. These sensors are strategically located to provide ization options and forecasts of greenhouse variables to enable in-depth analysis of the acquired information. Consequently, this alert system empowers greenhouse managers to proactively address abnormal situations that may jeopardize their crop yields., Funding This work is derived from R&D projects RTC2019-007159-5, as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, "FSE invest in your future" and "ERDF A way of mak-ing Europe". Financial support for this research has been also provided under grant PID2020-112827GB-I00 funded by MCIN/AEI/10.13039/501100011033. It is also partially granted by the "EMERGIA" programme, funded by the Junta de Andalucia through the grant EMC21_004171.

[EN] Polarity shifting can be considered one of the most challenging problems in the context of sentiment analysis. Polarity shifters are treated as linguistic contextual items that can incre-ment, reduce or neutralise the polarity of a word called `focus¿ included in an opinion. The automatic detection of such items enhances performance and accuracy of computational systems for opinion mining. From a symbolic approach, we aim to advance in the automatic processing of the polarity shifters that affect the opinions expressed on tweets in English. To this end, we describe a novel knowledge-based model to deal with quantification in English, which increments or reduces the polarity of opinions. In particular, we explain the linguistic rules of each category of quantification shifter, including information about the scope and direction with respect to the focus. Furthermore, we present the mathematical formulae that calculate the strength of the effect on the prior polarity. Finally, we describe the matrices associated to the linguistic rules, which serve to model the knowledge in text-mining systems, [ES] El cambio de polaridad se considera uno de los problemas más desafiantes dentro del ámbito de la minería de opiniones. Los operadores de cambio de polaridad son elementos lingüísticos contextuales que pueden aumentar, reducir o neutralizar la polaridad de una palabra denominada ¿foco¿ que se incluye en la expresión de una opinión. La detección au-tomática de tales elementos mejora el rendimiento y la precisión de los sistemas computa-cionales para la minería de opiniones. Desde un enfoque simbólico, este artículo presenta un avance en el procesamiento automático de los operadores contextuales que afectan la polaridad de las opiniones expresadas en tuits escritos en inglés. Con este fin, proponemos un nuevo modelo basado en el conocimiento relativo a la cuantificación en inglés, la cual puede incrementar o reducir la polaridad de las opiniones. En concreto, describimos las reglas lingüísticas de cada categoría de operador asociado a la cuantificación, incluyendo información sobre el alcance y la dirección del operador con respecto al foco. Además, indicamos las fórmulas matemáticas que calculan la fuerza del efecto sobre la polaridad previa. Finalmente, presentamos las matrices asociadas a las reglas lingüísticas, las cuales facilitan la modelización del conocimiento en un sistema de minería textual., Esta publicación es parte del proyecto de I+D+i PID2020-112827GB-I00, financiado por MICIU/AEI/10.13039/501100011033, y del proyecto SMARTLAGOON [101017861], financiado por Horizonte 2020 - Programa Marco de Investigación e Innovación de la Unión Europea.

[EN] TexMiLAB is a workbench that allows researchers to do text-mining experiments in two modes: graphical user interface and C# scripting interface., Este software es parte del proyecto de I+D+i PID2020-112827GB-I00 financiado por MICIU/AEI/10.13039/501100011033.

[EN] Clustering algorithms are one of the most widely used kernels to generate knowledge from large datasets. These algorithms group a set of data elements (i.e., images, points, patterns, etc.) into clusters to identify patterns or common features of a sample. However, these algorithms are very computationally expensive as they often involve the computation of expensive fitness functions that must be evaluated for all points in the dataset. This computational cost is even higher for fuzzy methods, where each data point may belong to more than one cluster. In this paper, we evaluate different parallelisation strategies on different heterogeneous platforms for fuzzy clustering algorithms typically used in the state-of-the-art such as the Fuzzy C-means (FCM), the Gustafson-Kessel FCM (GK-FCM) and the Fuzzy Minimals (FM). The experimental evaluation includes performance and energy trade-offs. Our results show that depending on the computational pattern of each algorithm, their mathematical foundation and the amount of data to be processed, each algorithm performs better on a different platform., This work has been partially supported by the Spanish Ministry of Science and Innovation, under the Ramon y Cajal Program (Grant No. RYC2018-025580-I) and by the Spanish "Agencia Estatal de Investigacion" under grant PID2020-112827GB-I00 /AEI/ 10.13039/501100011033, and under grants RTI2018-096384-B-I00, RTC-2017-6389-5 and RTC2019-007159-5, by the Fundacion Seneca del Centro de Coordinacion de la Investigacion de la Region de Murcia under Project 20813/PI/18, and by the "Conselleria de Educacion, Investigacion, Cultura y Deporte, Direccio General de Ciencia i Investigacio, Proyectos AICO/2020", Spain, under Grant AICO/2020/302.

[ES] Los cognados son palabras ortográficamente similares en distintas lenguas que
comparten la misma etimología. La investigación de los cognados es valiosa en ámbitos
como la lingüística histórica, la adquisición de lenguas, la recuperación de información y
la traducción automática, entre otros. En este contexto, la identificación de false friends
supone un reto para los métodos automáticos de detección de cognados, ya que la
similitud ortográfica no es suficiente para detectar estos pares de palabras. Con este fin,
evaluamos siete modelos vectoriales-espaciales no supervisados diferentes basados en
redes neuronales para detectar cognados y distinguir los cognados verdaderos de los false friends a partir de una lista de pares de palabras en inglés y español. Esta variedad de
modelos permitió determinar el impacto de varios factores en la calidad de los
resultados y la eficacia de los modelos: los recursos lingüísticos empleados en la
construcción del modelo (por ejemplo, corpus de textos, redes asociativas léxicas o
ambos), la alineación interlingüística de los espacios semánticos y la fusión de
significados en palabras polisémicas., [EN] Cognates are orthographically similar words in different languages that share the same etymology. Investigating cognates is valuable in fields such as historical linguistics, language acquisition, information retrieval, and machine translation, among many other. In this context, identifying false friends poses a challenge for automatic methods of cognate detection, as orthographic similarity is not sufficient to distinguish such word pairs. To this end, we evaluated seven different unsupervised vector-space models based on neural networks to detect cognates in general and to distinguish true cognates from false friends in a list of word pairs in English and Spanish. This variety of models allowed us to determine the impact of several factors on the quality of the results and the effectiveness of the models: language resources employed in model construction (e.g., text corpora, lexical associative networks, or both), cross-lingual alignment of semantic spaces, and meaning conflation in polysemous words., This publication is part of the R&D&I project PID2020-112827GB-I00, funded
by MICIU/AEI/10.13039/501100011033.

[EN] The development of a model to quantify semantic similarity and relatedness between words has been the major focus of many studies in various fields, e.g. psychology, linguistics, and natural language processing. Unlike the measures proposed by most previous research, this article is aimed at estimating automatically the strength of associative words that can be semantically related or not. We demonstrate that the performance of the model depends not only on the combination of independently constructed word embeddings (namely, corpus- and network-based embeddings) but also on the way these word vectors interact. The research concludes that the weighted average of the cosine-similarity coefficients derived from independent word embeddings in a double vector space tends to yield high correlations with human judgements. Moreover, we demonstrate that evaluating word associations through a measure that relies on not only the rank ordering of word pairs but also the strength of associations can reveal some findings that go unnoticed by traditional measures such as Spearman's and Pearson's correlation coefficients., s Financial support for this research has been provided by the Spanish Ministry of
Science, Innovation and Universities [grant number RTC 2017-6389-5], the Spanish ¿Agencia Estatal
de Investigación¿ [grant number PID2020-112827GB-I00 / AEI / 10.13039/501100011033], and the
European Union¿s Horizon 2020 research and innovation program [grant number 101017861: project
SMARTLAGOON].
Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.

[EN] This article describes a methodological framework for developing synthetic corpora with
a small language model from a prompt engineering perspective. Instead of the typical
approach in text mining, which prioritises corpus size in model training, this study applies
a corpus linguistics methodology that accounts for corpus domain and distribution considerations to generate diverse and realistic texts. These synthetic corpora were evaluated
through their integration into a text classification system to detect social problems. Therefore, the objective is to demonstrate whether using a theoretically sound methodology
based on corpus linguistics can improve the performance of systems trained with such
synthetic corpora. The study concludes that factors such as stratification and proportionality in the sampling method have even more impact than corpus size., This publication is part of the R&D&I projects PID2020-112827GB-I00 and PID2023-147137NB-I00, funded by MICIU/AEI/10.13039/501100011033 and by ERDF, EU, and partially supported by the research project CIPROM/2023/29, funded by Direcció General de Ciència i Investigació Generalitat Valenciana (Spain).

[ES] La elaboración manual de extensos recursos lingüísticos para su uso en sistemas de inteligencia artificial es una tarea que requiere un gran esfuerzo económico y humano en un período largo de tiempo, razón por la cual se recomienda un uso sostenible de los recursos existentes. En este contexto, el objeto de investigación de este artículo es WordNet, una base de datos léxica diseñada originariamente para el estudio de las redes semánticas. En concreto, analizamos la sostenibilidad de este recurso lexicográfico en campos de la inteligencia artificial como el procesamiento del lenguaje natural y la ingeniería del conocimiento desde la perspectiva de tres atributos esenciales: extensibilidad, interoperabilidad y reusabilidad., [EN] The manual compilation of comprehensive language resources for artificial intelligence systems is a labour-intensive, time-consuming and economically costly task, which is why a sustainable use of existing resources is recommended. In this context, the research goal of this article is WordNet, a lexical database originally designed for the study of semantic networks. In particular, we analyse the sustainability of this lexicographical resource in the artificial intelligence fields of natural language processing and knowledge engineering from the perspective of three core attributes: extensibility, interoperability and reusability., Esta publicación es parte del proyecto de I+D+i PID2020-112827GB-I00 financiado por MCIN/AEI/10.13039/501100011033 y del proyecto SMARTLAGOON [referencia 101017861] financiado por el Programa Horizonte 2020 de
la Unión Europea.

[EN] The creation of smart greenhouses is playing a crucial role in paving the way toward precision agriculture characterized by enhanced efficiency. Integral to these greenhouses are decision-support systems that leverage sophisticated forecasting algorithms to predict a range of parameters. However, these predictors often employ a single model approach for forecasting all variables of interest, leading to imbalanced predictions where some variables are accurately predicted while others do not. Such inconsistencies can undermine the overall reliability of the decision-support systems. Addressing this challenge, this paper proposes an approach that harnesses the potential of multiple deep-learning models operating concurrently to predict a broad array of environmental parameters within a smart and operational greenhouse. Each model is specifically tailored to concentrate on a distinct subset of target variables, thus ensuring that the overall accuracy of the prediction is optimized. The effectiveness of this approach has been evaluated in a real-world greenhouse setting. The results indicate a substantial improvement, exhibiting more than an 8% enhancement in the Mean Absolute Percentage Error (MAPE) compared to a single-model alternative, particularly in predicting specific environmental variables, confirming the potential for more reliable and precise agricultural decision-support systems., This work is derived from R&D projects RTC2019-007159-5, PID 2020-112827GB-I00, as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, "FSE invest in your future".

[EN] Polarity shifting can be considered one of the most challenging problems in the context of Sentiment Analysis. Polarity shifters, also known as contextual valence shifters (Polanyi and Zaenen 2004), are treated as linguistic contextual items that can increase, reduce or neutralise the prior polarity of a word called focus included in an opinion. The automatic detection of such items enhances the performance and accuracy of computational systems for opinion mining, but this challenge remains open, mainly for languages other than English. From a symbolic approach, we aim to advance in the automatic processing of the polarity shifters that affect the opinions expressed on tweets, both in English and Spanish. To this end, we describe a novel knowledge-based model to deal with three dimensions of contextual shifters: negation, quantification, and modality (or irrealis)., This work is part of the project grant PID2020-112827GB-I00, funded by MCIN/AEI/10.13039/501100011033, and the SMARTLAGOON project [101017861], funded by Horizon 2020 - European Union Framework Programme for Research and Innovation.

[EN] Social-media platforms have become a global phenomenon of communication, where users publish content in text, images, video, audio or a combination of them to convey opinions, report facts that are happening or show current situations of interest. Smart-city applications can benefit from social media and digital participatory platforms when citizens become active social sensors of the problems that occur in their communities. Indeed, systems that analyse and interpret user-generated content can extract actionable information from the digital world to improve citizens' quality of life. This article aims to model the knowledge required for automatic problem detection to reproduce citizens' awareness of problems from the analysis of text-based user-generated content items. Therefore, this research focuses on two primary goals. On the one hand, we present the underpinnings of the ontological model that categorises the types of problems affecting citizens' quality of life in society. In this regard, this study contributes significantly to developing an ontology based on the social-sensing paradigm to support the advance of smart societies. On the other hand, we describe the architecture of the text-processing module that relies on such an ontology to perform problem detection, which involves the tasks of topic categorisation and keyword recognition., This article was supported under grant PID2020-112827GB-I00 funded by MCIN/AEI/10.13039/501100011033, and under grant number 101017861 [project SMARTLAGOON] by the European Union's Horizon 2020 research and innovation program.