Search

En este estudio analizamos el reconocimiento de emociones en música a través de la evaluación dinámica de la valencia de 285 canciones seleccionadas. Nuestro objetivo fue utilizar un método desarrollado para analizar el valor emocional de una canción a partir de sus letras en español, utilizando tecnología para inferir las emociones expresadas en frases. Se empleó el paquete Syuzhet en el entorno R para la estimación de la valencia, incorporando tres léxicos emocionales distintos. También se realizó un análisis de frecuencia de palabras. Los resultados resaltaron la predominancia de emociones positivas como la alegría y emociones negativas como la tristeza. Las letras de Juan Gabriel exploran predominantemente temas de amor y desamor. En general, la música norteña mexicana refleja el amor hacia una mujer, su traición y el camino hacia la recuperación emocional.

Copyright of International Journal of Professional Business Review (JPBReview) is the property of Open Access Publications LLC 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.)

With the large number of apps deployed in cloud application stores, usability has become a fundamental attribute of software quality to enable user-centered de-sign. One of the challenges in usability tests is the automation of the process of determining the level of usability, based on the attributes of effectiveness, efficiency and satisfaction according to ISO 9241-11. This paper proposes as a contribution the use of robotic process automation (RPA) in the automatic determination of the attributes of effectiveness, efficiency and satisfaction in end-user tests, in order to estimate the level of usability of the software evaluated in these tests. For the development of this research, an adaptation of the itera-tive research pattern proposed by Pratt was used, so that 4 phases were de-fined: characterization of the tests, definition of the process, implementation of the process through RPA and evaluation of the automated process. From the metrics associated with effectiveness (number of subtasks per task), efficiency (times per task) and satisfaction (post-test questionnaire ratings and opinions), an automated process was designed and implemented using the UiPath tool, which in an Excel spreadsheet determines the percentage of effectiveness, the percentage and the percentage of satisfaction, incorporating the sentiment analysis approach in the calculation of the last attribute. The proof of concept performed by using the automated process was correctly developed, allowing to demonstrate its usefulness and contribution both in the optimization of the analysis times of a test with users, as well as in the incorporation of the sentiment analysis approach in the conventional analysis of this type of tests. [ABSTRACT FROM AUTHOR]

This paper presents a neutrosophic study on attitudes towards virtual technology, with a special focus on the "Experience Machine". Employing a methodology that incorporates the theory of indecision and neutrality into response analysis, the perceptions of 50 university students were investigated. Opinions and feelings were transformed into neutrosophic numbers to calculate contradiction and conduct a detailed analysis. The results indicate a predisposition towards agreement with virtual technology, although notable indecision and a significant presence of neutral attitudes were detected. The correlations and clustering methods applied reveal a complex dynamic of attitudes, challenging binary interpretations and highlighting the need for more nuanced strategies. This neutrosophic approach offers new perspectives for the development and marketing of innovative technologies, recognizing the diversity of emotions and opinions in user responses to emerging technologies. [ABSTRACT FROM AUTHOR]

Copyright of Educación y Humanismo is the property of Universidad Simon Bolivar 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 Comunicaciones en Estadística is the property of Universidad Santo Tomas 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.)

Introduction: The objective of this study was to explore the perception of loneliness of patients over 65 years of age with chronic pathologies that allude to this feeling. Method: The sample consisted of 36 patients (M=81.75; 50% men; 50% women) from a basic area (ABS) in Barcelona. The feeling of loneliness was evaluated with the UCLA scale and the question was asked: Could you describe why you feel lonely? Results: The results revealed a feeling of slight loneliness in (17%); moderate in (30%) and severe in (53%). The analysis of the responses showed that feelings of loneliness are associated with loss, estrangement or filial rupture, and the feeling of abandonment, which they described as disturbing, negative, and painful. Conclusions: Everyone feels alone, even if they are not, it is necessary to identify this feeling of loneliness, since it influences the state of physical and mental health that deteriorates the quality of life of patients. [ABSTRACT FROM AUTHOR]

The recognition that different aspects of the urban environment can affect individuals' mental health is growing, as they are responsible for facilitating or inhibiting behaviors and lifestyles that affect sentiment. The increasing availability of user-generated data on social media provides information about users and their surroundings, enabling sentiment analysis. This study investigates the global production of documents on sentiment analysis and the built environment, urban or city, published between 2009 and 2023. Bibliometric indicators on trends, most cited articles, authors, institutions, countries, funding agencies, and thematic research areas were analyzed. The bibliometrix library of R software was used for the performance analysis and the VOSviewer software for mapping scientific connections. A total of 728 eligible papers were identified from 2009 to June 2023. Most publications were computer science papers (n=487). This type of analysis provides researchers with guidance on the possible critical points that can be found in this field of research, as well as informs about the multiplicity of scientific research conducted globally so far by authors, countries, sources, allocated funding, and active institutions, allowing improving the production of documents on sentiment analysis concerning the urban environment. [ABSTRACT FROM AUTHOR]

Student Evaluation of Teaching (SET) serves as an ad hoc way of assessing teaching effectiveness within higher education institutions. This paper introduces an approach to analyzing sentiments expressed in SET comments using a Large Language Model (LLM). By employing natural language processing techniques, the polarity conveyed by students upon course completion is extracted and analyzed, aiming to furnish educators and stakeholders with valuable insights into teaching quality and areas for improvement in teaching practice. This study showcases the effectiveness of LLMs in sentiment analysis of comments, underscoring their potential to enhance the evaluation process. The development of a prototype tool, collaborative labeling of end-of-course evaluations, and a comparison with LLM-based labeling are experimentally explored. Subsequently, the implications for educational institutions are discussed, and future research directions in this domain are proposed. [ABSTRACT FROM AUTHOR]

Estimamos índices de sentimiento a nivel regional y nacional utilizando información en formato de texto del Programa Trimestral de Entrevistas a Directivos, empleada para la elaboración del Reporte sobre las Economías Regionales del Banco de México, referente a los factores que los entrevistados consideran que afectaron, afectan o pudieran afectar la actividad económica en su sector o entidad federativa. Estos índices, estimados con información de los programas de entrevistas trimestrales llevados a cabo entre enero de 2016 y enero de 2021, son posteriormente asociados con diferentes indicadores de actividad económica regional y nacional publicados por el INEGI, obteniéndose correlaciones positivas y estadísticamente significativas entre los índices de sentimiento y algunos indicadores de actividad económica. Dado que estos índices de sentimiento pueden obtenerse con mayor rapidez que la mayoría de los indicadores tradicionales de actividad económica aquí analizados, el trabajo destaca la relevancia de la información en formato de texto contenida en el Programa Trimestral de Entrevistas a Directivos para complementar la obtenida con indicadores tradicionales.

Introducción: la pandemia COVID-19 ha afectado la práctica odontológica por el alto riesgo de contagio durante su ejercicio. El objetivo del estudio fue determinar el nivel de ansiedad, sentimientos manifestados y medidas adoptadas en la atención clínica por el odontólogo durante la pandemia COVID-19 en Lima Metropolitana-Perú. Métodos: estudio descriptivo, prospectivo y transversal realizado en 386 odontólogos de Lima Metropolitana-Perú en los primeros meses del 2021. El nivel de ansiedad se midió a través del: Generalized Anxiety Disorder. Se confeccionó y validó un cuestionario para medir los sentimientos y medidas adoptadas, que fue enviado a través de distintas redes sociales. Resultados: los niveles de ansiedad leve y moderada se presentaron en el 42,5% y 21,2% respectivamente, presentándose mayores niveles de severidad en las mujeres (p

Mental health problems have been rising worldwide, possibly associated with urban population growth and related lifestyles. The recognition that the various aspects of the urban environment can affect the mental health of individuals has been increasing since they are responsible for facilitating or inhibiting behaviors and lifestyles that impact the feeling. In this context, it is essential to understand the potential impact of the urban environment of the city of Lisbon. To do so, we resorted to sentiment analysis, using a lexicon from the NRC Sentiment and Emotion, based on data from the social network X, enabling the identification of places where both positive and negative sentiment prevail. Next, an machine learning (ML) model associated with an agnostic model was used to increase the understanding of the factors of the urban environment that can explain the sentiment. Four ML models were tested, Random Forest (RF), Extreme Gradient Boosting (XGBoost), Neural Network (NN), K-Nearest Neighbour (KNN), and a linear model for comparison (Generalized Linear Model - GLM). The agnostic models applied, the Local Interpretable Model-Agnostic Explanations (LIME) and the Shapley Additive exPlanation (SHAP), played a crucial role in this study. Answering the starting question, the explanatory variables most related to sentiment are distance to fitness facilities, distance to green spaces, the popularity of locations (estimated through the social network Flickr), and distance to the cycling network. [ABSTRACT FROM AUTHOR]

In this study, sentiment analysis was developed and applied to technological products in the Twitter/X social network, also, the opinions expressed by customers were determined and finally the most suitable predictive model derived from Machine Learning was identified. For this purpose, 7102 tweets related to Apple and Samsung products were collected, using the methodology proposed by Erl, Khattak and Buhler which facilitated the implementation of its critical phases. The results obtained from sentiment analysis were evaluated using standard metrics such as Accuracy, Precision, Recall and F1-Score, applied to four machine learning models: K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF) and CatBoost Classifier (CC). Of these, the CatBoost Classifier proved to be the most effective, achieving 89% in Accuracy, 90% in Precision, 89% in Recall and 88% in F1-Score. It was concluded that the CatBoost Classifier model was the optimal model for analyzing sentiment on Twitter/X, due to its ability to provide valuable insights into the perception of promoted technology products enabling effectiveness in digital marketing campaigns. [ABSTRACT FROM AUTHOR]

Copyright of Dixit. Comunicación, Profesión, Conocimiento is the property of Universidad Catolica del Uruguay Damaso Antonio Larranaga 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 Doxa Comunicación is the property of Fundacion Universitaria San Pablo - CEU 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 Doxa Comunicación is the property of Fundacion Universitaria San Pablo - CEU 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.)

This article discusses a study on sentiment analysis of hotel reviews, specifically focusing on environmental aspects. The study uses advanced techniques to analyze user sentiments and categorize them as positive or negative. The findings show that positive evaluations have better prediction results. The study suggests that improving staff service, maintaining a clean environment, and offering friendly and affordable services can greatly enhance customer satisfaction in the hotel industry. The article provides valuable insights for decision-making and positioning hotels for success. [Extracted from the article]

Copyright of Revista Facultad de Ingeniería - UPTC is the property of Universidad Pedagogica y Tecnologica de Colombia, Facultad de Ingenieria 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 role of nature documentaries in shaping public attitudes and behavior toward conservation and wildlife issues is unclear. We analyzed the emotional content of over 2 million tweets related to Our Planet, a major nature documentary released on Netflix, with dictionary and rule‐based automatic sentiment analysis. We also compared the sentiment associated with species mentioned in Our Planet and a set of control species with similar features but not mentioned in the documentary. Tweets were largely negative in sentiment at the time of release of the series. This effect was primarily linked to the highly skewed distributions of retweets and, in particular, to a single negatively valenced and massively retweeted tweet (>150,000 retweets). Species mentioned in Our Planet were associated with more negative sentiment than the control species, and this effect coincided with a short period following the airing of the series. Our results are consistent with a general negativity bias in cultural transmission and document the difficulty of evoking positive sentiment, on social media and elsewhere, in response to environmental problems. [ABSTRACT FROM AUTHOR]

El discurso de odio dirigido hacia personas migrantes y refugiadas plantea uno de los mayores desafíos en la comunicación en redes sociales. A través del análisis automatizado de 124.337 mensajes sobre migración recogidos en Twitter en España entre 2015 y 2020, se analiza la presencia de odio y el sentimiento subyacente en el discurso, así como su evolución y las posibles diferencias entre comunidades autónomas. Se ha observado que, aunque la atención prestada a la cuestión migratoria fue superior en 2015 y 2016, años centrales de la crisis de refugiados del Mediterráneo, el mayor volumen de odio se detectó en 2019 y 2020, tras el ascenso de Vox y su retórica anti-inmigración. En general, el sentimiento de estos mensajes fue negativo, si bien la diferencia entre aquellos que tienen odio y los que no es reducida. Por último, se han observado diferencias entre regiones autónomas, siendo Asturias la de mayor presencia de odio y Cantabria la que muestra un sentimiento más negativo; estas diferencias, no obstante, no son elevadas y no se han detectado patrones claros que las expliquen.

With the growth in the number of applications deployed in the cloud, one of the aspects that contributes to improving user productivity and enterprise competitiveness is usability. According to ISO 9241-11, usability is defined in terms of the attributes of effectiveness, efficiency, and satisfaction, where satisfaction is the subjective attribute. In a user test developed in a usability laboratory, the satisfaction attribute is obtained using perception surveys, so one of the challenges is to contribute to the objective determination of this attribute, given the subjectivity of the surveys. This paper proposes a new approach for the determination of the satisfaction attribute is user tests based on the use of sentiment analysis techniques. The proposed approach was developed using the four methodological phases of the iterative research pattern: observe the application, identify the problem, develop the solution, and test the solution. As a result, the proposed approach was implemented through a tool developed in Java and Python, which combines the conventional approach with the opinion mining approach for the determination of the level of satisfaction per user and across the entire test. This approach is intended to serve as a reference at the academic and business level in the objective determination of the satisfaction attribute based on affective computing techniques. [ABSTRACT FROM AUTHOR]

The aim of this study is to analyze the sentiments and emotions of a corpus of 7 543 English reviews collected from the TripAdvisor platform, pertaining to 38 food and beverage establishments located in Bahias de Huatulco, during the period 2013-2023. The Robustly Optimized BERT Approach model is implemented for this purpose, complemented by an analysis of word frequencies and themes present in the review corpus. The findings suggest that most words used by diners have a favorable connotation towards the establishments. Furthermore, the percentage of positive reviews remains consistently high at around 90% over time, while negative reviews and those associated with feelings of sadness and anger represent a low percentage and show minimal variations over time. Performance metrics indicate a high overall accuracy in the classification of reviews (91%), albeit with a limited ability to accurately classify neutral reviews. The results of this study are consistent with existing literature, emphasizing the importance of the gastronomic experience in a tourist destination, and providing relevant insights for enhancing service quality in food and beverage establishments in Bahias de Huatulco. [ABSTRACT FROM AUTHOR]

It was proposed to answer if the machines can really analyze the sentiments of the tweets, then the messages in Spanish on Twitter that spoke of KFC were analyzed. The tweets were captured every day in the time period of the first quarter of the year 2022 from the Latin American region, later they were analyzed by month and for each company mentioned in the tweets, these came to add 39,269 messages for KFC. We focused on discovering what were the feelings related to each message left, for this reason the polarity of the feeling between positive and negative was sought, the first being related to wellbeing, happiness, and love, while the second polarity, negative was related to discomfort, sadness, and hatred. After obtaining the polarity, it remained to discover what its degree was, the high, medium and low indicators were used, thus having the degrees: high positives, medium positives, low positives, high negatives, medium negatives, and low negatives. The term neutral or neutral was used for unpolarized messages, not meaning a feeling, that is, neutral feelings do not exist, it is only the result of the absence of sufficient data to classify it in some polarity. Everything mentioned was done through artificial intelligence, but considering that it was sought to answer if the feelings of the text messages can really be analyzed, that is why two different heuristics were used, Machine Learning and Deep Learning, with them it was possible identify the polarity and degree of sentiment of Twitter messages regarding the KFC company in the first quarter in Latin America 2022. [ABSTRACT FROM AUTHOR]

Copyright of Revista Facultad de Odontología Universidad de Antioquia is the property of Universidad de Antioquia 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.)

Introducción: Los comentarios que realizan los clientes de las empresas en las redes sociales y portales de comercio electrónico sobre productos y servicios ofrecidos por estas, no solo permiten a las empresas determinar la percepción de los clientes para la toma de decisiones a nivel de marketing, sino que también sirven como referencia para otros clientes a tomar decisiones antes de comprar un producto. Una de las técnicas derivadas del procesamiento del lenguaje natural y la computación afectiva que permite determinar el de una opinión es el análisis de sentimiento. Objetivo: Determinar un indicador cuantitativo del nivel de percepción mediante una ecuación matemática que involucra el valor de polaridad (positiva, negativa, neutra) de una opinión. Metodología: Este trabajo se enfocó en la automatización del proceso de minería de opinión y la determinación del nivel de percepción mediante la identificación de las librerías más utilizadas e idóneas para el desarrollo de este trabajo; la identificación de ecuaciones matemáticas para determinar el nivel de percepción, la implementación de una herramienta para automatizar el proceso y la verificación de su utilidad mediante un caso de estudio. Resultados: Por medio de una ecuación matemática que involucra las tres polaridades de una opinión obteniendo una herramienta automatizada en lenguaje Python, que hace uso de la librería Paralleldots. Conclusiones: La herramienta desarrollada permite realizar estudios de minería de opinión en los que el valor agregado es la estimación de un nivel de percepción por opinión y general. El enfoque propuesto pretende servir como referencia para ser replicado y extrapolado en diferentes contextos de aplicación además del marketing.

This article analyzes the sentiment of messages posted on the social network Twitter during the electoral debates in for the regional elections held in Galicia and the Basque Country in 2020. The aim is to test whether a dominant negative sentiment exists in the messages and whether this varies when the candidate for re-election intervenes --election competition--, whether it differs when parties from the ideological extremes intervene --echo chambers--, and whether the same reaction occurs when the issue at stake affects both electorates equally. It is shown that in the Basque Country it is more important who intervenes --more electoral competition--, while in Galicia the issues are the ones that motivate Twitter conversations. [ABSTRACT FROM AUTHOR]

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.)

Objective: to know the feelings experienced by elderly people in the face of social distancing in the Covid-19 pandemic. Method: qualitative study that adopted as reference the Theory of Social Representations by the method of Collective Subject Discourse. 29 elderly people participated in the study and the selection was intentional or theoretical, using the snowball technique. Data were collected between October and December 2020, through a questionnaire of sociodemographic, family and health characterization and an open question guiding the study. The statements were recorded, transcribed and analyzed. Results: the elderly reported experiencing feelings of worry, fear, naturalness, comfort, with a greater predominance of feelings of discomfort, sadness, loneliness and security. Final considerations: positive and negative feelings were experienced by the elderly during the period of social distancing due to the Covid-19 pandemic. [ABSTRACT FROM AUTHOR]

Hononymy can be problematic in the conceptualisation of cultural heritage, however, in this paper we work in a mixed way to ensure that on the theoretical as well as on the empirical level. In this paper we combine an extensive literature review on cultural heritage in the context of tourism with the treatment firstly resulting from natural language engineering and then from semantic content analysis, in order to check the existence of differences in communication on the one hand, and the complementarity of automatic coding methods and manual analysis on the other. The results, although neither conclusive nor generalisable, are a gateway to an in-depth study of the concept through the visitors' testimonies. [ABSTRACT FROM AUTHOR]

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.)

La hononimia puede resultar problemática en la conceptualización del patrimonio cultural, sin embargo, en este artículo se trabaja de forma mixta para asegurar que en el plano teórico, tanto como, en el empírico. En este trabajo combinamos una extensa revisión literaria sobre el patriminio cultural en contexto turístico con el tratamiento primero resultado de la ingeniería del lenguaje natural y después, del análisis semántico del contenido, con el objeto de comprobar de un lado la existencia de diferencias en la comunicación y por otro la complementariedad de los métodos de codificación automáticos y el análisis manual. Los resultados, aún no siendo concluyentes ni generalizables, son una puerta a el estudio en profundidad del concepto a través de los testimonios de los visitantes.

Copyright of Human Review is the property of Eagora Science 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.)

Para reducir la tasa de contagio por COVID-19, el Gobierno colombiano ha adoptado, entre otras medidas, el aislamiento obligatorio. Esta medida ha generado opiniones divididas, pues a pesar de que ayuda a disminuir la propagación del virus, genera problemas mentales y económicos difíciles de sortear. El objetivo de este documento es analizar los sentimientos subyacentes de los comentarios de Twitter relacionados con el aislamiento, identificando los temas y palabras más frecuentemente utilizados en este contexto. Se construyó un algoritmo de machine learning para identificar los sentimientos de 72 564 publicaciones, y se aplicó un análisis de redes sociales para identificar los temas más frecuentes en los conjuntos de datos. Los resultados sugieren que el algoritmo presenta gran precisión para clasificar sentimientos. Asimismo, a medida que se extiende el aislamiento, los comentarios relacionados con la cuarentena crecen de manera proporcional. Se identificó al miedo como el sentimiento predominante durante todo el periodo de confinamiento en Colombia. To reduce the rate of contagion by Covid-19, the Colombian government has adopted, among other measures, for mandatory isolation, with divided opinions, because despite helping to reduce the spread of the virus, it generates mental and economic problems that are difficult to overcome. The objective of this document was to analyze the underlying sentiments in the Twitter comments related to isolation, identifying the topics and words most frequently used in this context. A machine learning algorithm was built to identify sentiments in 72,564 posts and a social network analysis was applied establishing the most frequent topics in the data sets. The results suggest that the algorithm is highly accurate in classifying feelings. Also, as the isolation extends, comments related to the quarantine grow proportionally. Fear was identified as the predominant feeling throughout the period of confinement in Colombia.

En la Minería de Datos, un área que ha ganado interés es la determinación del perfil del autor, que identifica patrones compartidos por un grupo de personas y aborda problemas de clasificación de los usuarios de la Web de acuerdo a edad, género, orientación política, etc. En este informe, se tomará como caso de estudio la tarea de identificación de la alineación política, la cual tiene como objetivo determinar a partir de los escritos de las personas el sesgo político. En este tipo de campo, un aspecto clave es disponer un conjunto de datos adecuados para que los procesos de minería de datos y aprendizaje automático puedan obtener resultados confiables. Para ello, se realiza la experimentación sobre un corpus para el estudio de la alineación política en documentos de periodistas argentinos. El estudio incluye varios tipos de análisis de documentos de periodistas opositores y progubernamentales, como ser la relevancia de los términos en cada clase de documentos, el análisis de sentimientos, el modelado de tópicos y el análisis de indicadores psicolingüísticos obtenidos del sistema LIWC. En los resultados experimentales, se pueden observar patrones interesantes, como por ejemplo los tópicos sobre los que escriben ambos tipos de periodistas, cómo se distribuyen las polaridades de los sentimientos y cómo los escritos de los periodistas progubernamentales y periodistas opositores difieren en las distintas categorías de LIWC.

La imagen pública de una persona corresponde a la opinión y consideración de los demás, en base a como se proyecta y como es percibida. Se puede observar la imagen pública de una persona a través de las redes sociales, debido a que usuarios expresan opiniones que despiertan interés social acerca de ellas. Nuestro objetivo es determinar la aceptación del presidente de la república del Ecuador Lenin Moreno en base a las opiniones de los usuarios de Twitter. Para ello se han recolectado datos en dos periodos de tiempo para observar cambios en la percepción de su imagen, y se les ha aplicado el análisis de sentimientos para determinar si las opiniones son positivas, negativas o neutras. El resultado del análisis de sentimientos se lo representa como series temporales, y se añade una línea de tendencia con el fin de observar la variación que han tenido las opiniones. Se concluye que las opiniones de las personas, en su gran mayoría, tienen polaridad negativa, y de acuerdo a la pendiente de la línea de tendencia. La imagen del presidente no presentara cambios relevantes.

El propósito de este documento consiste en analizar los sentimientos subyacentes en publicaciones de Twitter sobre la vacunación contra la covid-19. Para cumplir el objetivo, se extraen, mediante minería de datos, 38.034 publicaciones de esta red social y se aplican técnicas de Machine Learning, en concreto, análisis de sentimientos y análisis de redes, para identificar los sentimientos que expresan los usuarios de esta red social hacia la vacunación por covid-19. También se identifican las cuentas más importantes de Twitter en temas de vacunación. Los resultados sugieren que, en su mayoría, los sentimientos hacia las vacunas son negativos. El miedo y la ira, respectivamente, son las emociones más recurrentes en las opiniones de Twitter. Por otra parte, se identifica que las cuentas más relevantes pertenecen a medios de comunicación, políticos e influenciadores, los cuales se clasifican de acuerdo con los principales sentimientos respecto de la vacuna. Destaca la oposición al gobierno, con sentimientos de ira, y a medios de comunicación reconocidos, con emociones asociadas a la alegría.

Introduction: This study evaluates the emotionality associated with vaccination against COVID-19 using the sentiment analysis technique of tweets in Spanish-speaking Ibero-American countries. Method: In January 2021 a mixed cross-sectional observational study of 41023 tweets from nine Spanish-speaking Ibero-American countries (Chile, El Salvador, Venezuela, Ecuador, Argentina, Mexico, Panama, Peru and Spain) was carried out with a quantitative phase and analysis techniques of feelings based on artificial intelligence algorithms and a qualitative phase where an analysis of the discourse of the tweets whose emotionality was extremely positive and negative was carried out. Results: From the sentiment analysis of the tweets, it was observed that the countries present a negative emotionality associated with the vaccination against COVID-19, which could be attributed to mistrust towards the authorities and the efficacy or safety of the vaccines, according to the analysis of the discourse in the extremely negative emotionality tweets. Conclusions: Sentiment analysis techniques in combination with extreme emotionality discourse analysis made it possible to monitor negative opinions and their possible associated factors in vaccination against COVID-19 in the Ibero-American countries studied. [ABSTRACT FROM AUTHOR]

This article investigates how three media outlets (the digital written editions of CNN, Fox News, and the BBC), perceived as politically partisan, framed the news on Edward Snowden, who disclosed sensitive cybersecurity issues. As the media is an influential actor in domestic and international politics, how the news coverage on Internet security flaws framed the facts under narrative dispute matters. Sentiment analyses were conducted on hundreds of articles published on the free-access written news websites between 2013-2018. The results show positive or negative sentiments expressed in most headlines, while more neutral texts are found in the news cores. [ABSTRACT FROM AUTHOR]

Awareness-raising campaigns on disability have been launched to make society aware of the difficulties faced daily by people with conditions other than those of normotypical development. The objective of this study is to analyze the impact on Twitter of ten Spanish disability campaigns, held between 2013 and 2020. Trendinalia has been used to determine the amount, position and duration of the trending topic (TT) generated; and a sentiment analysis tool was used on Twitter to determine the positive, neutral or negative valence of tweets. The results show the quantitative success of campaigns on Twitter, although their impact is not uniform for all campaigns. On a qualitative level, although the tweets of all campaigns generally have more positive than negative connotations, in some conversations the greatest number of messages present a neutral tone. An analysis of the results shows that disability is an interesting topic for Twitter users and that it is important to carry out initiatives such as these campaigns to provide a voice for people with disabilities. The results obtained can be useful to guide the implementation of successful strategies for future campaigns. [ABSTRACT FROM AUTHOR]

Copyright of Palabra Clave is the property of Universidad de la Sabana 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.)

A lo largo de la pandemia ocasionada por la Covid-19 se han llevado a cabo distintos estudios sobre la respuesta emocional a nivel social, frecuentemente empleando como base del análisis los mensajes en redes sociales. En este trabajo, y empleando técnicas computacionales de text mining, se compara el patrón detectado en la investigación de Dubey (2020) con el que aparece en una de las obras icónicas en literatura de ciencia ficción: The Puppet Masters (1951), de Robert A. Heinlein. Esta novela describe la historia de una invasión por parte de parásitos alienígenas, y el hilo narrativo se articula en torno al miedo al contagio y la paranoia imperante por quienes estarán o no infectados, pudiendo infectar a otros. Es decir, describe un escenario que, en lo esencial, es muy similar a la actual situación. Los resultados demuestran que existe una enorme similitud entre ambos patrones emocionales. El hecho de que una novela de hace casi 70 años exhiba un patrón emocional extraordinariamente similar al que hemos observado en la sociedad durante la pandemia, pone de manifiesto no solo la capacidad de Heinlein para dotar de verosimilitud a sus obras, sino que, una vez más, la vida parece imitar al arte.

The aim of this work is to study the news coverage by the main Spanish generalist newspapers on Twitter during the campaign for the Community of Madrid elections in 2021 (n = 2,709). Natural language processing techniques and machine learning algorithms are applied to identify the predominant topic related to the elections and the mentions of candidates and political parties by each media, and to calibrate the emotional value of the messages published by El país, El mundo, Eldiario.es, and El confidencial. Among other findings, the results reveal how the media coverage focused mainly on campaign events and electoral debates. Despite the detection of minor differences between the newspapers, a general pattern emerges through this content, with a notable dominance of Isabel Díaz Ayuso but little influence of Rocío Monasterio as the lead candidates for their party. The sentiment analysis reveals the political alignment of each newspaper, using mainly negative messages with the aim of reducing the importance of a candidate or political party. While El país and Eldiario.es focused their criticism on Vox and the Partido Popular, El mundo and El confidencial criticized the actions of the national government, the PSOE's proposal to join forces with Unidas Podemos, and Vox's position, as well as emphasizing the disaster faced by Ciudadanos. It can be deduced that the media contributed to Ayuso's success and to the consolidation of her image as an individual distinct from her own party. [ABSTRACT FROM AUTHOR]