Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

The natural, artificial, and social domains of intelligence: a triune approach

  • Navarro, Jorge
  • Marijuán, Pedro C.
A “triune approach” to the three main domains of intelligence is advocated. It would be the most cogent way to understand the uses and impact of artificial intelligence in its intrinsic relation with human nature and social structures. The enormous technological success of artificial intelligence and the widespread social applications, impinging both in individual lives and in multiple economic and social structures, are making necessary a reflection on the wider dynamics of intelligence, interconnecting the artificial information pathways with the natural information flows and the social structural substrates. As a telling instance, the traditional poor understanding and management of “social emotions” is dangerously amplified in today’s social networks, contributing to unrest, polarization, and widespread desocialization processes. In contemporary societies, the essential link between intelligence and life has to be plainly revealed as a counterpoint to the link between artificial intelligence and computation.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Evolution of social mood in Spain throughout the COVID-19 vaccination process: a machine learning approach to tweets analysis

  • Turón, A.
  • Altuzarra, A.
  • Moreno-Jiménez, J. M.
  • Navarro, J.
Objectives: This paper presents a new approach based on the combination of machine learning techniques, in particular, sentiment analysis using lexicons, and multivariate statistical methods to assess the evolution of social mood through the COVID-19 vaccination process in Spain. Methods: Analysing 41,669 Spanish tweets posted between 27 February 2020 and 31 December 2021, different sentiments were assessed using a list of Spanish words and their associations with eight basic emotions (anger, fear, anticipation, trust, surprise, sadness, joy and disgust) and three valences (neutral, negative and positive). How the different subjective emotions were distributed across the tweets was determined using several descriptive statistics; a trajectory plot representing the emotional valence vs narrative time was also included. Results: The results achieved are highly illustrative of the social mood of citizens, registering the different emerging opinion clusters, gauging public states of mind via the collective valence, and detecting the prevalence of different emotions in the successive phases of the vaccination process. Conclusions: The present combination in formal models of objective and subjective information would therefore provide a more accurate vision of social reality, in this case regarding the COVID-19 vaccination process in Spain, which will enable a more effective resolution of problems.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Reducing incompatibility in a local AHP-group decision making context

  • Aguarón, Juan
  • Escobar, María Teresa
  • Moreno-Jiménez, José María
In the context of local analytic hierarchy process-group decision making (AHP-GDM), this paper presents a theoretical framework and a semi-automatic procedure for reducing incompatibility between the actors involved in the decision making process and the collective position. The row geometric mean is employed as the prioritisation procedure and the geometric compatibility index (GCOMPI ) as the incompatibility measure; individual pairwise comparison matrices are considered as the input of the reduction process, whilst the collective vector is the output. The reduction is attained by slightly modifying, in relative terms, the judgements of the collective pairwise comparison matrix, irrespective of the method used to obtain it, that further improve the GCOMPI . The resulting judgements of the collective matrix and the associated collective priorities are close to the initial collective values. The procedure does not modify the judgements of the initial individual matrices and this simplifies the process of reaching consensus. A simulation analysis is utilised to study the performance of the algorithm along with an illustrative numerical example. The analysis proves that the proposed algorithm is easy to implement and efficient, it provides mathematically closed results and significantly reduces the GCOMPI associated with the precise consistency consensus matrix which is one of the AHP-GDM tools. The framework allows the procedure to be adapted to specific interests.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Multicriteria evaluation of technological competitiveness in diversification processes. An application to the automotive components industry

  • Muerza, Victoria
  • Larrodé, Emilio
  • Moreno-Jiménez, José María
  • Royo, Beatriz
Considering technological competitiveness in diversification processes as the existence of key technologiesthat guarantee the current and future effective running of firms in terms of their technological and oper-ational potential, this paper presents a multicriteria approach for its evaluation and provides an index formeasuring the technological competitiveness of diversification processes. The application of this multicriteriaapproach, based on the analytic hierarchy process, in three real technological diversification processes allows(i) the validation of the hierarchical model (five levels and 25 attributes) and the index (73 indicators) pro-posed for evaluating the technological competitiveness; (ii) the use of this hierarchical model and index toconfirm the suitability of the diversification process and to extract knowledge related to the technological andoperational potential of the firm; and (iii) the exploitation of this knowledge in order to guarantee the long-term survival of automotive components industry’s firms. The methodology finds the most relevant attributesin the automotive component sector (innovative capacity and activity, good functioning of the managementand finance departments). Its practical application determines the firm’s suitability for a diversification pro-cess, identifies the attributes that require some improvement, and the decision opportunities. After 5 years,the three companies that have been studied showed a behaviour aligned with the values and recommenda-tions of the index developed to assess technological competitiveness. The main limitation lies in the difficultyof studying companies if they change or disappear in the future.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Social mood during the Covid-19 vaccination process in Spain. A sentiment analysis of tweets and social network leaders

  • Navarro, Jorge
  • Aguarón, Juan
  • Moreno-Jiménez, José María
  • Turón, Alberto
In accordance with the cognitive orientation contemplated in the resolution of complex problems posed in public decision-making using decision support systems and social networks, this work studies the possibility of identifying the state of mind of society through the state of mind of network leaders. Using sentiment and emotion analysis as research techniques and Twitter as a representative social network, the study corpus considers tweets and retweets in Spanish about COVID-19 in the period from February 27, 2020 to December 31, 2021. As cognitive orientation claims, the proposed techniques will allow us to extract the arguments that support the different positions and decisions from the analysis of the tweets issued exclusively by social leaders. In the case study considered, the COVID-19 vaccination process in Spain, the reduction in the number of tweets′ authors (more than 8,000) to the network leaders (just 8) was greater than 99 %; and the subsequent reduction in the number of associated tweets was greater than 88 % from the 18,193 tweets in society to the 2,145 tweets of the eight social leaders. The impressive degree of information compression achieved may be useful to establish new directions of social mood analysis applied to healthcare and business management.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Natural intelligence and the ‘economy’ of social emotions: A connection with AI sentiment analysis

  • Navarro, Jorge
  • Marijuán, Pedro C.
By approaching the concept of Natural Intelligence a new path may be open in a variety of theoretical and applied problems on social emotions. There is no doubt that intelligence emerges as a biological/informational phenomenon, although paradoxically a consistent elaboration of that concept has been missing. Regarding emotions, they have been keeping an unclear status, being often restricted to the anthropological or to ethological approaches closer to the behaviorist paradigm. Herein we propose a different track, centered in the life cycle advancement. The life cycle in its integrity becomes the nucleus of natural intelligence's informational processes, including the consistent expression of emotions along the maximization of fitness occasions. In human societies, the overall ‘economy’ of social emotions is manifest, showing up in the conspicuous interplay between bonding processes and different classes of social emotions. The essential link between natural intelligence, emotions, and the life cycle of individuals may harmonize with current progresses – and blind spots – of artificial intelligence fields such as ‘sentiment analysis.’
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Economic change and cultural evolution: the ultimate influence of human cognitive limitations

  • Bordonaba-Bosque, Daniel
  • González-Álvarez, María A.
  • Marijuán, Pedro C.
  • Navarro, Jorge
How cognitive limitations of individuals may affect the dynamics of cultural evolution under the effects of economic and technological forces is explored here. In particular, the extraordinary economic growth during the industrial and scientific revolutions of the last two centuries has been accompanied by an extraordinary acceleration of cultural changes. We will propose that these changes are due to competition, decay and replacement processes among the different kinds of cultural contents, ultimately resulting from our cognitive limitations. Different laws have been proposed recently for the decay of individualized cultural items and for the underlying competition processes, which will be discussed herein. With respect to the informational/cognitive limitations of individuals, the cognitive psychology views will be complemented—and somehow quantified—from the angle of the “social brain” or “sociotype” hypothesis. The generational phenomenon also emerges, by which differentiated generations develop a remarkable divergence in ways of life, aspirations, ideals, values, and often in the use of communication technologies. It is in this interactive individual–generational context of competitive processes that the acceleration of cultural change during the few last decades might be investigated by considering the vastly increased economic output and the widespread use of new communication technologies.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Mood and emotion assessment for risk reduction of pandemic spread through passenger air transport: a DSS applied to the COVID-19 in the case of Spain

  • Aguarón, J.
  • Altuzarra, A.
  • Aznar, R.
  • Escobar, M.T.
  • Jiménez-Martín, A.
  • Mateos, A.
  • Moreno-Díaz, A.
  • Moreno-Jiménez, J.M.
  • Moreno-Loscertales, C.
  • Muerza, V.
  • Navarro, J.
  • Sarango, A.
  • Turón, A.
  • Vargas, L.G.
This paper presents a decision support system (DSS) for sentiment analysis of Spanish texts based on lexicons. The information provided by this DSS, named Spanish Sentiment Analysis‐DSS (SSA‐DSS), is employed to assess the social impacts considered in an external software module (RRPS‐PAT) centered on risk reduction of pandemic spread through passenger air transport. RRPS‐PAT is a complex multiobjective optimization module simultaneously addressing different conflicting objectives, including epidemiological, economic, and social aspects. This allows more effective and realistic decisions to be made. The specificity and novelty of the problem suggest the use of lexicon‐based approaches because there is no prior information about the problem to train machine learning–based approaches. The SSA‐DSS covers the entire process from the incorporation of texts, particularly tweets, to be analyzed, the application of preprocessing and cleaning tools, the selection of lexicons (general, context, and emoji lexicons) to be used and their possible modification, to the visualization of results and their exportation to other software tools. This paper contemplates, apart from the RRPS‐PAT module, the connection with a social network analysis tool (Gephi) that complements the information provided by SSA‐DSS with the identification of social leaders. The usefulness and functionalities of SSA‐DSS are illustrated by means of an example related to the evolution of societal mood in Spain during the COVID‐19 pandemic.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Human cognitive limitations and emotions: The emergence of social complexity

  • Marijuán, Pedro C.
  • Navarro, Jorge
An evolutionary approach to human cognition and social complexity, acknowledging the essential role of social emotions, is attempted. From the start, every kind of cognition, either artificial or natural, is limited. In living beings, it is the life cycle, life course, or life history what determines the extension, intensity, and limitations of the cognitive tools evolved to adapt to the own niche: from bacteria to multicellulars, animals, mammals, anthropoids, etc. Herein we will briefly survey some of those instances. In the human case, the essential niche becomes an extended social group with a rich diversity of cognitive links or ‘bonds’ in continuous interaction. Evolutionarily, the adaptation process to this social niche has involved a series of brain size increases, allowing, above all, the cognitive wonders inherent in language. But it has also involved a restructuring of the cognitive ‘shortcuts’ — essentially, emotions — that help individuals to navigate their own life in the natural environment and, especially, within the highly complex social milieu. Ultimately, this social adaptation process made possible the emergence of human ‘ultrasociality’ –the crux of Anthropogenesis-- and the most conspicuous behavioral traits still observable in contemporary societies, the effects of which also reverberate in the practice of science itself.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Entropy-Based Analysis of Emotional Dynamics in Doctor–Patient Co-Decision in Primary Care

  • Sarango, Ayrton
  • Aguarón, Juan
  • Aznar, Rodrigo
  • Bordonaba, Daniel
  • Moreno-Loscertales, Cristina
  • Moreno-Jiménez, José María
  • Navarro, Jorge
Decision-making in healthcare involves both clinical evidence and emotional and cognitive processes that are often difficult to formalize. While sentiment analysis has been widely used to capture emotional information in clinical interactions, it does not fully account for how emotional categories are distributed across interactions. This study proposes an entropy-based approach to complement sentiment analysis by quantifying the diversity and distribution of emotional states expressed during doctor–patient consultations. A dataset of 30 primary care consultations involving patients with hypertension (HTA) and dyslipidemia (DLM) was analyzed using natural language processing techniques. Emotional information was extracted using the NRC Emotion Lexicon, and normalized Shannon entropy was computed at the intervention level. Intervention-based, role-based, and phase-based analyses were conducted. The results show that emotional entropy varies throughout the consultation and across consultation phases. Consultation-level analyses showed higher overall entropy in HTA than in DLM consultations, while no significant overall effect of the speaker role was found. Entropy also varied significantly in consultation phases, although the disease-by-phase interaction was not significant. Robustness analyses supported the stability of these patterns, and the negligible association with sentiment valence indicates complementary information. These findings highlight entropy as a complementary measure for analyzing emotional dynamics in clinical interactions.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

A healthcare cognitive decision support system for doctor–patient co-decisions in primary care using sentiment analysis

  • Moreno-Jiménez, J.M.
  • Aznar, R.
  • Moreno-Loscertales, C.
  • Sancho, M.
  • Sarango, A.
  • Turón, A.
  • Navarro, J.
Decision support systems (DSS) in the artificial intelligence era require the integration of cognitive and affective information to support human-centred decision-making. This study proposes a healthcare cognitive decision support system (HC-DSS) based on lexicon sentiment analysis for doctor–patient co-decisions in primary care. Thirty audio transcriptions from actual consultations involving patients with hypertension (HTA) or dyslipidaemia (DLM) are analysed using the Spanish sentiment analysis-decision support system (SSA-DSS) updated with automatic speaker identification. Results show that HTA consultations exhibit greater affective intensity and variability across both positive and negative emotional dimensions, while DLM consultations present comparatively more stable and less reactive affective patterns. Phase-based analyses further reveal that emotional valence and trust follow structured, condition-specific trajectories, with peak sensitivity during treatment and decision-making stages. Based on these exploratory findings, a four-phase consultation model is proposed as a sentiment-aware DSS framework to support more emotionally informed and personalised doctor–patient co-decisions in primary care, as well as the education and empowerment of individuals and society in healthy lifestyle habits.