Asdrúbal López‐Chau

Affective polarization is a phenomenon that has invaded the political arena empowered by social networks. In this chapter, the authors analyze the Capitol riot posts on Twitter. To achieve this, the authors use affective computing introducing the multi-emotional charge combined with statistical analysis based on the t-student test and Welch's t-test. The research questions guiding this study are: How do social media platforms' messages impact on inciting? Do social media platforms' messages with negative emotional charge affect legitimizing of the Capitol protest? Findings identify the significant influence of Donald Trump on Twitter during the Capitol riot. Moreover, data analysis identifies positive and negative emotions towards Donald Trump as well as similarities in the showed emotions of Trump and the audience.

This chapter presented an analysis of the application of lexicon-based political sentiment analysis in social media. The aim is to identify the most frequently used lexicons in political sentiment analysis, their results, similarities, and differences. For this, the authors conducted a systematic literature review based on PRISMA methodology. Afinn, NRC, and SenticNet lexicons are tested and combined for data analysis from the 2020 U.S. presidential campaign. Findings show that political sentiment analysis is a new field studied for only 10 years. Political sentiment analysis could generate benefits in understanding problems such as political polarization, discourse analysis, politician influence, candidate profiling, and improving government-citizen interaction, among other problems in the public sphere, enhanced by the combination of lexicons and multimodal analysis. The authors conclude that polarity was one of the critical dimensions identified for finding variations in the behavior and polarity of sentiments. Limitations and future work also are presented.

One of the pillars of connected government is citizen centricity: an approach in which citizen participation is essential. In Mexico, social networks are currently one of the most important means by which citizens express their needs and provide opinions to the government. The goal of this chapter is to contribute to citizen centricity by adapting the methodology of sentiment analysis of social media posts to an expanded version for crisis situations. The main difference in this approach from the normally accepted one is that instead of using pre-defined classes (positive and negative) for sentiments, the authors first determined the different data categories and then applied them to the classic process of sentiment analysis. This approach was tested using posts on Mexico's earthquake in 2017. They found that needs, demands, and claims made in the posts reflect sentiments in a better way, and this can help to improve the government-citizen connection.

The financial profile of natural and legal persons allows financial institutions and financial services companies to identify the level of default of credit applicants. In this way, maintaining a healthy financial profile is derived from a positive history and status, the result of good financial decisions. In Latin America, the vast majority of people pay little attention to strengthening this type of profile, and it is a subject that is rarely addressed on the most popular social media platforms. In this chapter, a search for opinions of Latin Americans regarding the financial profile on the Twitter social network was made, finding that there is a very small number of responses to publications on this topic. Therefore, a web platform is proposed to provide advice on this important issue. The general design of a module for text analysis using sentiment analysis and machine learning techniques is also proposed.

The COVID-19 pandemic has become a critical and disruptive event that has substantially changed the way people live and work. Although several studies have examined the effects of remote work on organizational outcomes and behaviors, only a few have inquired into how its opportune implementation impacts aggregate emotions over time. This chapter aims to conduct a sentiment analysis with public reactions on Twitter about telework during the pandemic period. The results showed fluctuations in emotional polarity, starting with a higher positive charge in the early pandemic scenarios that became weaker, and the negative polarity of emotions increased. Fear, sadness, and anger were the emotions that increased the most during the pandemic. Knowledge about people's sentiments about telework is important to complement organizational research and to complement the framework for the development of efficient telework implementation strategies.

Aplicación de inteligencia artificial y tecnologías para la transformación digital: Pymes, desarrollo sostenible e inclusión social es un libro que presenta resultados de investigación de diferentes áreas del conocimiento. Profesores-investigadores de varias universidades de reconocimiento y prestigio en el país muestran en la era de la inteligencia artificial (IA) como a través del uso de herramientas digitales se pueden buscar alternativas de solución a problemáticas sociales, económicas, académicas y ambientales en sectores productivos, escolares, médicos, turísticos y comerciales con el propósito de favorecer a personas vulnerables en regiones marginadas de México. La presente obra refleja el esfuerzo por obtener resultados de investigación desde un enfoque multidisciplinario, considerando varias perspectivas y marcos de referencia que permitan tener un mayor alcance que si se realizaran desde una única disciplina, y cuyo objetivo principal es que la tecnología constituya un pilar en la inclusión social a pesar de las brechas que pudiesen existir.

ANÁLISIS CIENTÍFICO DESDE DISTINTAS PERSPECTIVAS COLECCIÓN CIENTÍFICA EDUCACIÓN, EMPRESA Y SOCIEDAD Primera Edición 2022 Vol. 17 Editorial EIDEC Sello Editorial EIDEC (978-958-53018) NIT 900583173-1 ISBN: 978-628-95419-0-8 Formato: Digital PDF (Portable Document Format) DOI: https://doi.org/10.34893/h0578-1489-6417-x Publicación: Colombia Fecha Publicación: 30/11/2022 Coordinación Editorial Escuela Internacional de Negocios y Desarrollo Empresarial de Colombia – EIDEC Centro de Investigación Científica, Empresarial y Tecnológica de Colombia – CEINCET Red de Investigación en Educación, Empresa y Sociedad – REDIEES Revisión y pares evaluadores Centro de Investigación Científica, Empresarial y Tecnológica de Colombia – CEINCET Red de Investigación en Educación, Empresa y Sociedad – REDIEES

Automatic face recognition has evolved significantly with the use of deep learning techniques, enabling more robust systems that can withstand variations in lighting, pose, and expression. This paper presents the implementation of a face recognition system for video recordings using the MTCNN face detection algorithm, which is used for its accuracy in identifying and locating faces in uncontrolled environments with varying lighting conditions. After face detection, the VGG-16 model was used as a deep feature extractor, leveraging its architecture to employ transfer learning techniques to learn hierarchical and discriminative representations of the face. The system processes the video frames using the OpenCV library, then uses the MTCNN network for facial identification, and finally assigns identities through a classifier trained, as previously mentioned, with the VGG-16 model. In recent studies, authors report that convolutional neural networks consistently outperform traditional methods due to their ability to automate the extraction of relevant features and handle complex environmental conditions. Preliminary results indicate that the MTCNN–VGG-16 integration forms an effective strategy for facial recognition in real-world scenarios, demonstrating high accuracy and stability under diverse visual conditions. This work provides an accessible and reproducible architecture for potential applications in video analytics, surveillance, and intelligent automation

La clasificación en conjuntos de datos no balanceados es un problema actual e \nimportante (Khan2012). Ejemplos de aplicaciones del mundo real en las que se \ngeneran este tipo de datos son, por ejemplo, diagnósticos médicos de \nenfermedades tales como cáncer o diabetes mellitus, detección de errores en \ncódigo fuente, ataques informáticos en servidores e identificación de transacciones \nbancarias fraudulentas. En este tipo de escenarios, es sumamente importante \ndetectar casos que generalmente ocurren con poca frecuencia con respecto a la \ncantidad de datos obtenidos, ya que representan un riesgo que hay que observar \noportunamente. Para los ejemplos de aplicaciones mencionadas anteriormente, \nestos casos poco frecuentes serían los pacientes enfermos de cáncer o diabetes, \nlos fragmentos de código fuente con errores, los accesos inválidos a servidores y \nlas transacciones ilícitas. Sin embargo, como se mencionó anteriormente, los \nalgoritmos de clasificación, presentan problemas con conjuntos de datos no \nbalanceados (He2009).