Search

This paper demonstrates an automated workflow for extracting network data from policy documents. We use natural language processing tools, part‐of‐speech tagging, and syntactic dependency parsing, to represent relationships between real‐world entities based on how they are described in text. Using a corpus of regional groundwater management plans, we demonstrate unique graph motifs created through parsing syntactic relationships and how document‐level syntax can be aggregated to develop large‐scale graphs. This approach complements and extends existing methods in public management and governance research by (1) expanding the feasible geographic and temporal scope of data collection and (2) allowing for customized representations of governance systems to fit different research applications, particularly by creating graphs with many different node and edge types. We conclude by reflecting on the challenges, limitations, and future directions of automated, text‐based methods for governance research. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Content creators on platforms such as YouTube, Instagram and Twitch are a fundamental part of adolescent culture, as they act as influencers, leaders and referents in the consumption of multimedia products aimed at the adolescent public. Communication research must intervene in the analysis of the possibilities and risks of these virtual spaces, in which not only consumption practices but also forms of coexistence and values of democratic systems are organised. The aim of this paper is to study the communicative interactions generated on social networks such as YouTube and Instagram in the profiles of the influencers with the most followers among teenagers in Spain, based on the number of contents generated and the responses they receive from users. Using natural language processing (NLP) techniques and sentiment analysis, 10 influencers with the most followers were studied, extracted from 2,749 questionnaires carried out among young people aged between 12 and 18 in Spain. The results show that while the number of views is strongly correlated with the number of likes reflected in the 2.142 videos, there is no strong correlation with the number of comments. This points to the need to revise the concept of audience engagement. Furthermore, although the 'positivity bias' prevails in the expression of emotions between influencers and followers, the analysis of the polarity of the titles of the videos analysed shows a high percentage of neutral and negative polarity, as strategies for attracting attention. In relation to the analysis of the word-clouds, it is observed that the comments of influencers and followers tend to have a positive and neutral polarity, under a redundant communication model in its bidirectionality. The conclusions point to the social and marketing implications of the power of influencers. [ABSTRACT FROM AUTHOR]

Copyright of Revista de Ciencias Sociales (13159518) is the property of Revista de Ciencias Sociales de la Universidad del Zulia Venezuela and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of RIE: Revista de Investigacion Educativa is the property of RIE: Revista de Investigacion Educativa and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

El objetivo del estudio es analizar el impacto de las tecnologías de procesamiento del lenguaje natural y aprendizaje automático en las prácticas pedagógicas para la enseñanza de idiomas, desde enfoques pedagógicos como el constructivismo, aprendizaje autónomo y aprendizaje basado en problemas, considerando aspectos éticos en la tecnología educativa. Para ello, se revisaron 40 documentos académicos, utilizando un análisis exhaustivo de contenido, con técnicas de análisis temático y codificación para identificar tendencias y patrones emergentes en la literatura revisada. Los resultados muestran que las estrategias basadas en inteligencia artificial promueven la participación activa de los estudiantes en la construcción del conocimiento, destacando cómo tecnologías como los chatbots facilitan la resolución de problemas lingüísticos en el aprendizaje basado en problemas. Asimismo, se observa que el aprendizaje autónomo se beneficia de herramientas de inteligencia artificial, fomentando la autonomía estudiantil y la adaptabilidad en el aprendizaje. Sin embargo, se subraya la importancia de abordar aspectos éticos, como la privacidad de los datos y el sesgo algorítmico. En conclusión, se enfatiza la necesidad de una reflexión crítica y de prácticas responsables en el diseño e implementación de herramientas tecnológicas para garantizar un entorno de aprendizaje ético y equitativo en la enseñanza de idiomas.

Among the possible solutions for automatic lexical disambiguation in natural language processing tasks, we find methods based on machine learning algorithms, semantic relatedness, and semantic similarity measures. While machine learning methods use endogenous sources of knowledge, semantic relatedness and similarity measures resort to exogenous sources of knowledge, such as definitions from lexicographic resources or lexical meaning relations from ontologies or thesauri, which offer a conceptual hierarchy. In this work, we present and analyze the different types of methods for automatic lexical disambiguation divided into four groups: based on machine learning algorithms, based on semantic relatedness measures, based on semantic similarity measures, and based on hybrid measures. We postulate that the advantage of methods based on relationship and similarity measures lies in the fact that their results are derived from statistical efficiency and linguistic knowledge found in the parameters that make up each of the measures used. [ABSTRACT FROM AUTHOR]

Resumen: En este artículo se presentan dos métodos para obtener medidas de calificación profesional y distancias ocupacionales de comparabilidad internacional, basados en técnicas de aprendizaje automático y de procesamiento del lenguaje natural. Con estas medidas se generan hechos descriptivos sobre las transiciones laborales y la distribución salarial en el Brasil, tras analizar todos los contratos de trabajo formales registrados en el periodo 2003‐2018. Los trabajadores que utilizan intensivamente competencias cognitivas no rutinarias obtienen mejores resultados en cuanto al empleo, los salarios y el cambio de ocupación. Tras la crisis económica brasileña de 2014, se observan indicios de cambio tecnológico con sesgo de rutina y de polarización del empleo. [ABSTRACT FROM AUTHOR]

Copyright of Revista Tecnología, Ciencia & Educación is the property of Centro de Estudios Financieros SL and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Brazilian Business Law Journal / Administração de Empresas em Revista is the property of Administracao de Empresas em Revista and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

El objetivo de este trabajo es esbozar un marco de referencia para conocer cuáles son los tipos y los elementos que comprenden un programa basado en inteligencia artificial (IA), esto permitirá formular propuestas de aplicación en el campo de la Bibliotecología y los estudios de la información, pues, aunque desde hace tiempo se reflexiona y analiza el uso de la IA, no hay casos de aplicaciones concretas. El empleo de la IA es habitual en muchas de las aplicaciones y tareas diarias, aunque ello no sea percibido de manera directa. Entonces, el propósito es analizar la IA desde un proceso de aplicación y continuidad a fin de aprovecharla como herramienta sin que su implementación conlleve la pérdida de algunas actividades profesionales o su reemplazo por programas que las automaticen. La propuesta es enfocarse en las posibilidades brindadas por la IA al ámbito bibliotecario y a los estudios de la información, que conducen a una búsqueda continua de aplicaciones en apoyo de la profesión del bibliotecario y la investigación en este campo. Asimismo, se advierten las habilidades que adquieren los profesionales de la información ante los contextos y las posibilidades de aplicación.

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The catastrophic earthquake that struck Morocco on September 8, 2023, garnered significant media coverage, leading to the swift dissemination of information across various social media and online plat- forms. However, the heightened visibility also gave rise to a surge in fake news, presenting formidable challenges to the efficient distribution of accurate information crucial for effective crisis management. This paper introduces an innovative approach to detection by integrating Natural language processing, bidirectional long-term memory (Bi-LSTM), convolutional neural network (CNN), and hierarchical attention network (HAN) models within the context of this seismic event. Leveraging advanced machine learning,deep learning, and data analysis techniques, we have devised a sophisticated fake news detection model capable of precisely identifying and categorizing misleading information. The amal gamation of these models enhances the accuracy and efficiency of our system, addressing the pressing need for reliable information amidst the chaos of a crisis. [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) is an interdisciplinary field that investigates the fascinating world of human language with the goal of creating computational models and algorithms that can comprehend, produce, and analyze natural language in a way that is similar to humans. LLMs still encounter issues with loud and unpolished input material despite their outstanding performance in natural language processing tasks. TextRefine offers a thorough pretreatment pipeline that refines and cleans the text data before using it in LLMs to overcome this problem . The pipeline includes a number of actions, such as removing social tags, normalizing whitespace, changing all lowercase letters to uppercase, removing stopwords, fixing Unicode issues, contraction unpacking, removing punctuation and accents, and text cleanup. These procedures work together to strengthen the integrity and quality of the input data, which will ultimately improve the efficiency and precision of LLMs. Extensive testing and comparisons with standard techniques show TextRefine’s effectiveness with 99 % of the accuracy. [ABSTRACT FROM AUTHOR]

Research Objective: the main objective in this article is to identify new variables that can improve a Proposed Integrative Model (PIM) for ChatGPT adoption. PIM, in turn, is based on three consolidated theories: TAM (Technology Acceptance Model), DIT (Diffusion of Innovation Theory) and TCMD (Theory of Cognitive Moral Development). Methodology/Approach: the approach in this study is qualitative, with interviews from experts who use ChatGPT in their areas, including three journalists, two technology professionals and three teachers. The interview guide involved the three theories. Textual data is analyzed with AtlasTi. software. Originality/Relevance: the research address doubts and fears about ChatGPT, an emerging technology highlighted in several fields, including Education. The results describe and interpret several influences (for example: psychological, social and technological) on the use of ChatGPT, in a nation (Brazil) with one of the largest populations in the world. Main Results: we identified 16 new variables potentially influential in the use of ChatGPT: accessibility, access to connectivity, trust in technology, creativity, entertainment, expectations, previous experience, feedback and continuous improvement, perceived innovation, integration with existing systems, time saving, customization, reduction workload, perceived risk, satisfaction and safety. Three aspects emerged around morality: intrinsic relationship between morality and ChatGPT: (i) attributing responsibility to the company OpenAI; (ii) intimate nature, intrinsic and individual characteristic of morality as an independent element of any technology; (iii) practice of reproducing content, historically considered illegal, which does not represent anything new from a legal point of view, regardless the technological era. [ABSTRACT FROM AUTHOR]

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Pixel-Bit, Revista de Medios y Educacion is the property of Pixel-Bit, Revista de Medios y Educacion and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Revista Gestão & Tecnologia is the property of Revista Gestao & Tecnologia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

El estudio de la construcción y el análisis de índices de sentimiento en redes sociales es una técnica reciente que ha captado interés por su capacidad para identificar tendencias en los precios de las acciones. Además, la aplicación de inteligencia artificial para analizar rápidamente grandes volúmenes de datos de diversas fuentes de información ha creado una nueva forma de evaluar información masiva de redes sociales. El procesamiento del lenguaje natural (NLP, por sus siglas en inglés) es el método preferido que se sigue en la investigación. Originado en los años cincuenta, el NLP surgió de la intersección entre la inteligencia artificial y la lingüística. En un comienzo se empleó para recuperar información textual, con métodos basados en estadísticas para indexar y buscar de manera eficaz en grandes secciones de texto.

Los sistemas de inteligencia artificial como ChatGPT, el chatbot de OpenAI, basado en la familia de modelos de lenguaje GPT (generative pre-trained transformers), así como aquellas otras soluciones basadas en esta tecnología y ajustadas para tareas específicas, han despertado un gran interés en diversos ámbitos, entre los que se incluyen el sector legal y, particularmente, el sector de la abogacía. Sin embargo, tales modelos presentan todavía importantes limitaciones y riesgos asociados a su empleo y funcionamiento, que deben ser considerados a fin de hacer un uso adecuado y jurídicamente responsable de esta tecnología. El presente trabajo tiene por objeto aproximar a los lectores (hombres y mujeres) a la configuración, a la arquitectura y al funcionamiento de estos sistemas, así como a sus funcionalidades dentro del sector jurídico, incluyendo una revisión a sus limitaciones y riesgos jurídicos asociados, con importantes implicaciones prácticas en su aplicación.

The morphological features of an inflectional language like Old English (OE), which also presents generalized spelling inconsistencies, limit the use of lemmatizing and tagging tools that can be applied to natural languages. Consequently, the development of Natural Language Processing (NLP) models, which crucially depend on lemmatized corpora, is slowed down. Against this background, this article develops a lemmatizer within the framework of Morphological Generation that allows for the type-based automatic lemmatization of OE class IV strong verbs (L--Y). The lemmatizer incorporates a set of algorithms to account for features of inflectional, derivational, morphophonological and diatopic variation. The generated forms are automatically compared with Taylor et al. (2003) and Healey et al. (2004) to confirm their attestation and are assigned a lemma. Overall, the research proves successful in setting up form-lemma associations, while highlighting areas of ambiguity and mismatches. The main conclusion of the article is that taking the route of automatic lemmatization with this methodological framework will contribute to the field of OE lexicography by both lemmatizing attested inflectional forms and by identifying areas for manual revision. [ABSTRACT FROM AUTHOR]

Copyright of Revista Española de Quimioterapia is the property of Sociedad Espanola de Quimioterapia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

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.

La atribución de significado a los segmentos de información propia del análisis de textos abiertos en investigación cualitativa implica una considerable inversión de tiempo. Las herramientas de Procesamiento de Lenguaje Natural pueden convertirse en un recurso para el investigador cualitativo, en cuanto que sus algoritmos permiten interpretar los textos y codificar cualitativamente de forma mucho más rápida. Esta tarea, sin embargo, requiere probar previamente el nivel de comprensión verbal de estas herramientas. La aparición del modelo GPT-3 de OpenAI ha supuesto un salto cualitativo respecto a modelos de Procesamiento de Lenguaje Natural anteriores. El objetivo fue analizar la capacidad de comprensión verbal de esta herramienta. Se aplicaron las pruebas del índice de comprensión verbal de la batería para la medición del cociente intelectual WAIS-IV. Los resultados de las pruebas de fiabilidad fueron satisfactorios. Respecto al nivel de comprensión verbal, las respuestas situaron a GPT-3 en un percentil superior al 99, comparado con los estándares humanos. Estos resultados demuestran que es posible utilizar este modelo como herramienta para el análisis de textos abiertos, abriendo enormes posibilidades para la investigación cualitativa, aunque su uso debe basarse en una utilización precisa y diseñada ad hoc para cada proceso de análisis.

Introducción: El artículo muestra los resultados del estudio «Análisis lexical de España, poema en cuatro angustias y una esperanza de Nicolás Guillén» que constituyó el trabajo de diploma del primero de sus autores y es parte del proyecto Léxico poético de Nicolás Guillén que dirige el segundo, desarrollado en el Centro de Lingüística Aplicada de Santiago de Cuba. Métodos: Haciendo uso del Etiquetador y Procesador de Corpus Textuales (ETIPROCT) se asignaron etiquetas a las unidades léxicas del poema, según su correspondiente categoría gramatical, además de extraer de esta importante información linguo-estadística. Resultados: Los principales resultados apuntan al predominio de los sustantivos comunes entre todas las clases de palabras, al notable uso de las perífrasis verbales, a la relevancia de las formas que pertenecen a las conjunciones y preposiciones por su alta frecuencia, así como del nombre Federico, y al empleo de algunas formas ingeniosas. Conclusiones: El estudio reveló aspectos notables sobre las características del léxico poético guilleneano en el texto analizado en el uso, por ejemplo, de los sustantivos propios y comunes y las perífrasis verbales.

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Lingüística y Literatura is the property of Universidad de Antioquia, Facultad de Comunicaciones and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Forma y Funcion is the property of Universidad Nacional de Colombia, Facultad de Ciencias Humanas, Departamento de Linguistica and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: A huge amount of clinical data is generated daily and it is usually filed in clinical reports as natural language. Data extraction and further analysis requires reading and manual review of each report, which is a time consuming process. With the aim to test folksonomy to quickly obtain and analyze the information contained in media reports we set up this study. Methods and objectives: We have used folksonomy to quickly obtain and analyze data from 1631 discharge clinical reports from the Nephrology Department of Hospital del Mar, without the need to create a structured database. Results: After posing some questions related to daily clinical practice (hypoglycaemic drugs used in diabetic patients, antihypertensive drugs and the use of renin angiotensin blockers during hospitalization in the nephrology department and data related to emotional environment of patients with chronic kidney disease) this tool has allowed the conversion of unstructured information in natural language into a structured pool of data for its further analysis. Conclusions: Folksonomy allows the conversion of the information contained in clinical reports as natural language into a pool of structured data which can be further easily analyzed without the need for the classical manual review of the reports. Resumen: Antecedentes y objetivo: Gran parte de la información médica que se deriva de la práctica clínica habitual queda recogida en forma de lenguaje natural en los informes médicos. Clásicamente, la extracción de información clínica para su posterior análisis a partir de los informes médicos requiere de la lectura y revisión manual de cada uno de ellos con la consiguiente inversión de tiempo. El objetivo de este proyecto piloto ha sido evaluar la utilidad de la folksonomía para la extracción y análisis rápido de los datos que contienen los informes médicos. Material y métodos: En este proyecto piloto hemos utilizado la folksonomía para el análisis y la rápida extracción de datos de 1.631 informes médicos de alta de hospitalización del Servicio de Nefrología del Hospital del Mar sin necesidad de crear una base de datos estructurada previamente. Resultados: A partir de determinadas preguntas sobre la práctica médica habitual (tratamiento hipoglicemiante de los pacientes diabéticos, tratamiento antihipertensivo y manejo de los inhibidores del sistema renina angiotensina durante el ingreso en nefrología y análisis de datos relacionados con la esfera emocional de los pacientes renales) la herramienta ha permitido estructurar y analizar la información contenida en texto libre en los informes de alta. Conclusiones: La aplicación de folksonomía a los informes médicos nos permite transformar la información contenida en lenguaje natural en una serie de datos estructurados y analizables de manera automática sin necesidad de proceder a la revisión manual de los mismos.

Copyright of Cuadernos.info is the property of Pontificia Universidad Catolica de Chile, Facultad de Comunicaciones and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ciência da Informação is the property of Instituto Brasileiro de Informacao em Ciencia e Tecnologia (IBICT) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

El uso masivo de las redes sociales y el anonimato que este brinda ha posibilitado no solamente la comunicación inmediata entre los usuarios, sino también que acrezca la difusión del discurso de odio contra ciertos grupos de nuestra sociedad en forma de mensajes ofensivos para ellos, esto ha desembocado en un grave problema social; el cual sigue siendo tema de investigación actual junto con NLP. El propósito del presente trabajo es hacer una comparación de nuestro modelo de reconocimiento de "HateCheck" contra los resultados del autor, utilizando la misma base de datos que ellos. Para ello haremos uso de las principales métricas como son: precisión, recall y F1.

En este artículo se presenta UnderRL Tagger, un programa informático de acceso libre diseñado para el etiquetado morfosintáctico (POS tagging) en lenguas que no cuentan con etiquetadores automáticos. El programa busca facilitar el trabajo con corpus en estas lenguas infrasoportadas tecnológicamente y en las lenguas minoritarias, aportando así a los procesos de revitalización desde la investigación descriptiva y las herramientas computacionales. UnderRL Tagger permite que el proceso manual de etiquetado se convierta poco a poco en automático gracias a un sistema que permite recordar y reutilizar las etiquetas, manejar grandes cantidades de textos y generar archivos de salida en formato XML con etiquetas basadas en el sistema estandarizado EAGLES. Este artículo muestra el proceso de modelado y elaboración del sistema, sus diferentes funcionalidades y las perspectivas de trabajos posteriores.

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Nowadays, most software companies have adopted agile development methodologies, which suggest the capture of requirements through user stories. Issues Management Systems allow development teams to manage user stories and other issues, such as errors, change requests, and others. Although these systems provide features for categorizing or labeling issue types, the user often needs to include or specify this information correctly. A poor issue categorization causes many user stories to end up buried in a large volume of data, making it difficult to identify them. This article presents and compares three neural network models to classify issues as User Stories. As the ultimate goal of this research is to improve the quality of the software development project documentation, the comparison is practical to select a model to be embedded in an IMS tool for automatically categorizing issues. The compared models are a BRNN-LSTM model, an Elmo-based model, and a BERT-based model. It applied the CRISP-MD methodology to train, validate, and test the three proposed neural network models. Then, a comparison was performed regarding their accuracy and performance. As a result, the article shows that the BERTbased model is the one that best fits the problem posed, managing to classify the issues as user stories with an accuracy of approximately 97%. This model can analyze the text syntactically and semantically with the best accuracy and performance. [ABSTRACT FROM AUTHOR]

This paper investigates how government communications on Twitter®, in the context of the Covid-19 crisis, has produced different feelings among citizens. This type of interaction has effects on the perception of rulers and compliance with restrictions. Using R's tidytext package, a total of 28,344 Covid-related tweets were analyzed between January 2020 and March 2021 from ten user profiles on Twitter® (the mayors and Town Halls of Barranquilla, Bogotá, Cali, and Medellín, the President, and the presidency). The study seeks to contribute to the field of government communications during the Covid-19 crisis and the feelings they arouse toward citizen and government interactions during the study period. [ABSTRACT FROM AUTHOR]

Build a chatbot for the promotion of Primary Health Care for Community Health Agents (ACS) of the Family Health Strategy (ESF) in a municipality in Ceará. Methodological study of the technological production of a chatbot. For the construction of the technology, the Planning stages were followed, with an exploratory research being carried out with 143 ACS workers of the ESF in the municipality. Afterwards, the objectives, risk assessment and technology development were defined using the Dialogflow tool with integration to the Telegram communication channel. There were 79 responses to support the content to be promoted by the chatbot. The contents provided by the chatbot were organized into subthemes, the main theme being Primary Health Care in the context of the municipality of Acaraú. The use of chatbots provide new perspectives in the form of health promotion in the use of technological and innovative resources. [ABSTRACT FROM AUTHOR]