O futuro das avaliações por meio das redes sociais / The future of assessments through social media / El futuro de las evaluaciones mediante las redes sociales

O objetivo geral da presente pesquisa é discutir as principais inovações em avaliação psicológica possibilitadas pela existência das redes sociais. Mais especificamente, iremos caracterizar as práticas (e fragilidades) da avaliação psicológica convencionais, os métodos mais modernos de psicometria computacional e exemplos de aplicações de psicometria computacional a partir de dados provenientes de redes sociais. De forma geral, as práticas convencionais da avaliação psicológica da psicometria foram criadas no século XIX e muitas de suas práticas, desenvolvidas próximo à metade do século XX, continuam sendo utilizadas de forma pouco crítica. Como alternativa, a psicometria computacional, uma abordagem da psicometria que combina métodos da ciência da computação orientados a dados e teoria psicométrica, tem sido utilizada para gerar inovações na área de avaliação. Por fim, discutimos algumas aplicações da psicometria computacional e como essas inovações irão, provavelmente, gerar mudanças profundas no contexto de avaliação.(AU)

The overall aim of this study was to discuss the main innovations in psychological assessment made possible by the existence of social networks. More specifically, we characterize the practices (and weaknesses) of conventional psychological assessment, the most modern methods of computational psychometry and examples of applications of computational psychometry using data from social networks. In general, the conventional practices of psychological assessment of psychometrics were created in the 19th century and many of its practices, developed around the middle of the 20th century, continue to be used in a non-critical way. As an alternative, computational psychometrics, an approach to psychometrics that combines data-driven methods of computer science and psychometric theory, has been used to generate innovations in the area of assessment. Finally, we discuss some applications of computational psychometrics and how these innovations are likely to generate profound changes in the assessment context.(AU)

El objetivo general de esta investigación es discutir las principales innovaciones, en materia de evaluación psicológica, posibilitadas por la existencia de las redes sociales. Más específicamente, caracterizaremos las prácticas convencionales (y debilidades) de la evaluación psicológica, los métodos más modernos de psicometría computacional y ejemplos de aplicaciones de psicometría computacional a partir de los datos de redes sociales. En general, las prácticas convencionales de evaluación psicológica de la psicometría se crearon en el siglo XIX y muchas de sus prácticas, desarrolladas a mediados del siglo XX, continúan utilizándose de forma acrítica. Como alternativa, la psicometría computacional, un enfoque de la psicometría que combina métodos informáticos basados en datos y teoría psicométrica, se ha empleado para generar innovaciones en el área de la evaluación. Por último, discutimos algunas aplicaciones de la psicometría computacional y cómo es probable que estas innovaciones generen cambios profundos en el contexto de la evaluación.(AU)

A pesquisa científica na era do Big data: cinco maneiras que mostram como o Big data prejudica a ciência, e como podemos salvá-la / The scientific research in the age of Big data: five ways that show how the Big data harms the science, and how we can save it / La investigación científica en la era del Big data: cinco maneras que muestran como el Big data perjudica la ciencia, y como la salvar

O livro A pesquisa científica na era do Big data: cinco maneiras que mostram como o Big data prejudica a ciência, e como podemos salvá-la, de Sabina Leonelli, publicado pela Editora Fiocruz em 2022, explora em seus capítulos as definições do termo Big data e os seus impactos negativos na pesquisa científica. Em seguida, a autora revela uma nova abordagem epistemológica para o Big data e, por fim, apresenta um conjunto de propostas para a pesquisa científica. A revisão e atualização de definições, tanto quanto as importantes reflexões e os questionamentos por um uso consciente do Big data na pesquisa científica fazem com que a obra adicione importantes contribuições à biblioteca do pesquisador de informação e comunicação em saúde

The book titled A pesquisa científica na era do Big Data: cinco maneiras que mostram como o Big Data prejudica a ciência, e como podemos salvá-la [The scientific research in the age of Big Data: five ways that show how the Big Data harms the science, and how we can save it], by Sabina Leonelli, published in 2002, by Editora Fiocruz, explores in its chapters the definitions of Big Data and its negative impacts on scientific research. Then, the author reveals a new epistemological approach to Big data and finally she presents a set of proposals for developing a good scientific research. The literature review and updating of definitions as well as the important reflections and questions for a conscious use of Big data in scientific research make the work an important contribution to the researcher's library of the information and communication about health.

El libro denominado A pesquisa científica na era do Big data: cinco maneiras que mostram como o Big data prejudica a ciência, e como podemos salvá-la [La investigación científica en la era del Big data: cinco maneras que muestran como el Big data perjudica la ciencia, y como la salvar], de Sabina Leonelli, publicado en 2002, por la Editora Fiocruz, explora em sus capítulos las definiciones de Big data y sus impactos negativos en la investigación científica. A continuación, la autora revela un nuevo enfoque epistemológico del Big data y, al fin y al cabo, presenta un conjunto de propuestas para desarrollar una investigación científica de cualidad. La revisión de literatura y la actualización de las definiciones, así como las importantes reflexiones y discusiones para un uso consciente del Big data en la investigación científica, hacen de la obra un aporte importante a la biblioteca del investigador de la información y la comunicación acerca de la salud

Practical foundations of machine learning for addiction research. Part II. Workflow and use cases.

In a continuum with applied statistics, machine learning offers a wide variety of tools to explore, analyze, and understand addiction data. These tools include algorithms that can leverage useful information from data to build models; these models can solve particular tasks to answer addiction scientific questions. In this second part of a two-part review on machine learning, we explain how to apply machine learning methods to addiction research. Like other analytical tools, machine learning methods require a careful implementation to carry out a reproducible and transparent research process with reliable results. This review describes a workflow to guide the application of machine learning in addiction research, detailing study design, data collection, data pre-processing, modeling, and results communication. How to train, validate, and test a model, detect and characterize overfitting, and determine an adequate sample size are some of the key issues when applying machine learning. We also illustrate the process and particular nuances with examples of how researchers in addiction have applied machine learning techniques with different goals, study designs, or data sources as well as explain the main limitations of machine learning approaches and how to best address them. A good use of machine learning enriches the addiction research toolkit.

Practical foundations of machine learning for addiction research. Part I. Methods and techniques.

Machine learning assembles a broad set of methods and techniques to solve a wide range of problems, such as identifying individuals with substance use disorders (SUD), finding patterns in neuroimages, understanding SUD prognostic factors and their association, or determining addiction genetic underpinnings. However, the addiction research field underuses machine learning. This two-part narrative review focuses on machine learning tools and concepts, providing an introductory insight into their capabilities to facilitate their understanding and acquisition by addiction researchers. This first part presents supervised and unsupervised methods such as linear models, naive Bayes, support vector machines, artificial neural networks, and k-means. We illustrate each technique with examples of its use in current addiction research. We also present some open-source programming tools and methodological good practices that facilitate using these techniques. Throughout this work, we emphasize a continuum between applied statistics and machine learning, we show their commonalities, and provide sources for further reading to deepen the understanding of these methods. This two-part review is a primer for the next generation of addiction researchers incorporating machine learning in their projects. Researchers will find a bridge between applied statistics and machine learning, ways to expand their analytical toolkit, recommendations to incorporate well-established good practices in addiction data analysis (e.g., stating the rationale for using newer analytical tools, calculating sample size, improving reproducibility), and the vocabulary to enhance collaboration between researchers who do not conduct data analyses and those who do.

E se o scanCOVID-19 tivesse nascido em 2022? / And if the scanCOVID-19 had been born in 2002? / Y si el scanCOVID-19 hubiese nacido en 2022?

Acompanhar a velocidade das mudanças, qualitativas e quantitativas, na produção de conhecimento em tempos de pandemia de covid-19 impulsionou o desenvolvimento de inúmeras iniciativas de monitoramento da informação científica. O scanCOVID-19 foi uma delas. Essa nota de conjuntura procura situar a importância do investimento em projetos dessa natureza, que possam ter reflexos nas relações entre ciência, Estado e sociedade.

Keeping up with the speed of qualitative and quantitative changes in the production of knowledge in times of the covid-19 pandemic was a stimulus to the development of numerous initiatives to track scientific information. The scanCOVID-19 was one of them. This note seeks to situate the importance of investing in projects of the same nature, which may have effects on the relations between science, state, and society.

Acompañar la velocidad de los cambios, cualitativos y cuantitativos, en la producción de conocimiento en tiempos de la pandemia de covid-19 ha impulsado el desarrollo de numerosas iniciativas de seguimiento de la información científica. El scanCOVID-19 fue uno de ellos. Esta nota de coyuntura busca situar la importancia de invertir en proyectos de esta naturaleza, que puedan tener efectos sobre las relaciones entre ciencia, Estado y sociedad.

Plataforma de analítica de datos para la caracterización poblacional y la evaluación del riesgo cardiovascular en pacientes del centro-occidente de Colombia / Data analytics platform for population characterization and cardiovascular risk assessment in patients from the west-center of Colombia

Resumen Introducción: Las enfermedades cardiovasculares son la primera causa de muerte en el mundo. Por tanto, muchas investigaciones han sido dirigidas hacia la predicción del riesgo cardiovascular, con el fin de poder evitarlo. Asimismo, se ha buscado la implementación de sistemas que involucren el análisis de datos automatizados que permita que la información se ponga a disposición, no solo del personal administrativo y directivo, sino también del personal clínico, para mejorar el control de las patologías. Objetivo: Construir una herramienta para la caracterización poblacional y la evaluación del riesgo cardiovascular en pacientes del centro-occidente de Colombia. Materiales y métodos: Se propone la construcción de una plataforma de análisis de datos sociodemográficos y clínicos. El modelo general de diseño de la plataforma es el desarrollo evolutivo, que entrelaza actividades de especificación, desarrollo y validación. La plataforma presenta un modelo vista-controlador que permite la creación de plantillas dinámicas distribuidas en módulos de acceso controlados por perfiles de usuario. Resultados: Se implementó el cálculo automatizado del riesgo de enfermedad cardiovascular y la emisión de alertas tempranas, lo cual mejoró la gestión de los procesos clínicos, así como el apoyo a la toma de decisiones administrativas, a través de la conformación de dos módulos interactivos en la plataforma. Conclusiones: La unión de saberes clínicos, administrativos y de ingeniería permitió la consolidación de una herramienta que contribuye en el monitoreo y trazabilidad de los pacientes, orientando la priorización de posibles intervenciones que impacten en la salud de estos.

Abstract Introduction: Cardiovascular diseases are the leading cause of death in the world. Countless research has been directed towards the prediction of cardiovascular risk, in order to avoid the threat. Furthermore, the implementation automated data analysis tools have been sought to allow for information to be made readily available, not only to administrative and managerial staff, but also to clinical staff to improve the control of pathologies. Objective: To build a tool for the characterization of the population and the evaluation of cardiovascular risk in patients from central-western Colombia. Materials and methods: The construction of a platform for the analysis of sociodemographic and clinical data is proposed. The overall platform design model is evolutionary development, which intertwines specification, development, and validation activities. The platform presents a Vista-Controller model, which allows the creation of dynamic templates distributed in access modules controlled by user profiles. Results: The automated calculation of cardiovascular disease risk and the issuance of early warnings were implemented, which improved the management of clinical processes, as well as support for administrative decision-making, through the creation of two interactive modules on the platform. Conclusions: The union of clinical, administrative and engineering knowledge allowed the consolidation of a tool that contributes to the monitoring and traceability of patients, which guides the prioritization of possible interventions that impact the health of patients.

La informetría y el análisis del discurso aplicados a la producción científica en la Ciencia de Datos y Ciencia de la información / Informetrics and discourse analysis applied to scientific production in Data Science and Information Science

Resumen Objetivo. Investigar la producción científica en la intersección temática de la Ciencia de Datos (CD) y la Ciencia de la Información (CI). Método. Estudio informétrico, descriptivo, y de primera incursión, en el análisis del discurso escrito de los textos académicos incluidos en la Web of Science (WoS), periodo 1900 al 6 de noviembre de 2020, y cuya cobertura de búsqueda fue en las bases de datos: SCI.Expanded, SSCI, A&HCI, ESCI, CPCI-S, CPCI.SSH, BKCI-. y BKCI.SSH. Resultados. Se recuperaron y analizaron 49 documentos representados en 38 artículos, 7 textos de memorias de congresos, 2 capítulos de libro y 2 materiales editoriales. El conjunto de las investigaciones que tratan el tema de la CD y la CI sumaron 128 citas, 2.6 citas por documento e índice H: 7. Discusión.Conceptualmente, se encontró que para la CD y la CI su origen son los datos y que ambas disciplinas son predominantemente de carácter práctico. En aquellas investigaciones con mayor visibilidad hay participación multiautoral. La CD y la CI son áreas del conocimiento recientes en las cuales las tecnologías de la información son indispensables para el análisis de grandes cantidades de datos e información. Conclusiones. La CD y CI tienen un carácter intra y multi y transdisciplinar y se caracterizan por utilizar las tecnologías de la información para el análisis de grandes cantidades de datos e información.

Abstract Objective. To research scientific production at the thematic intersection of Data Science (DS) and Information Science (IS). Method. Informetric, descriptive study, and of first incursion, in the analysis of the written discourse of the academic texts included in the Web of Science (WoS), period 1900 to November 6, 2020, and coverage in the databases: SCI-Expanded, SSCI, A & HCI, ESCI, CPCI-S, CPCI-SSH, BKCI-S and BKCI-SSH. Results. 49 documents represented in 38 articles, 7 conference memoires, 2 book chapters and 2 editorial materials were retrieved and analyzed. The set of investigations that deal with the subject of DS and IS added 128 citations, 2.6 citations per document and H index: 7. Discussion. Conceptually, it was found that for DS and IS their origin is the data and that both disciplines are predominantly practical. In those investigations with greater visibility there are more than an author. DS and IS are recent areas of knowledge in which information technologies are indispensable for the analysis of large amounts of data and information. Conclusions. DS and IS have an intra- and multi and transdisciplinary character and they are characterized by the use of information technologies for the analysis of large amounts of data and information.

Manipulación, análisis y visualización de datos de la encuesta demográfica y de salud familiar con el programa R / Manipulation, analysis, and visualization of data from the demographic and family health survey with the R program

RESUMEN La Encuesta Demográfica de Salud Familiar (ENDES) es una encuesta nacional de base poblacional con representatividad a nivel departamental y área de residencia, constituyéndose en una fuente de información del estado de salud de la población peruana. Con el objetivo de estandarizar su procesamiento y posterior reutilización por parte de la comunidad académica y otros actores interesados; documentamos el código para la manipulación, análisis y visualización de datos del cuestionario de salud de la ENDES 2017, mediante un ejemplo sobre prevalencia de hipertensión arterial y obesidad, utilizando el entorno y lenguaje de programación estadístico R. Se presenta y detalla secuencialmente el código en R, así como, el sustento teórico de la estructura de la encuesta para la manipulación de las bases de datos, considerando que la compleja estructura de la ENDES podría ser una potencial barrera que enfrentan los investigadores. Finalmente, este ejemplo puede servir de base para que se generen mayores estudios basados en la ENDES que sean relevantes para la toma de decisiones en salud pública.

ABSTRACT The Demographic and Family Health Survey (ENDES, in Spanish) is a national population-based survey with representation at the departmental level and area of residence, constituting a source of information on the health status of the Peruvian population. In order to standardize its processing and subsequent reuse by the academic community and other stakeholders, we documented the code for the manipulation, analysis, and visualization of data from the ENDES 2017 health questionnaire, through an example on the prevalence of hypertension and obesity, using the R statistical programming environment and language. The R code is presented and detailed sequentially, as well as the theoretical support of the survey structure for the manipulation of databases, considering that the complex structure of the ENDES could be a potential barrier faced by researchers. Finally, this example can serve as a basis for generating further studies based on the ENDES that are relevant to public health decision-making.

Keywords: Data Science; Epidemiological Surveys; Statistics as a matter; Hypertension; Obesity; Peru