Abstract:
The information from social media is emerging as a valuable source in decision-making, unfortunately the tools to turn these data into useful information still need some work. Using Support Vector Machines for polarity detection in short texts are popular among researchers for their good results, but parameter optimization to train classification models is a complex and costly process. This article compares two algorithms for automated parameter optimization in the process of creating classification models for polarity detection: the recently created Grey Wolf Optimizer and the Grid Search, using accuracy and f-score metrics.
Spanish Abstract:
Los datos provenientes de las redes sociales están emergiendo como una fuente valiosa de información para los procesos de toma de decisiones, desafortunadamente las herramientas para convertir estos datos en información útil todavía tienen mucho camino por recorrer. Utilizar máquinas de soporte vectorial para la detección de polaridad en textos cortos goza de popularidad entre los investigadores debido a sus buenos resultados. Sin embargo, la optimización de los parámetros necesarios para entrenar modelos es un proceso complejo y costoso. Este artículo compara dos algoritmos para la optimización automatizada de parámetros en el proceso de crear modelos de clasificación para la detección de polaridad: Optimizador de lobo gris y las búsqueda en malla, utilizando las métricas de precisión y valor-f.
In 2012 the Instituto Tecnológico de Costa Rica opened the Computer Engineering program at the recently created Centro Académico de Alajuela. At that time there were neither research space nor resources available for undergraduate students to practice problem solving by applying theoretical concepts to real life problems. The Laboratorio Experimental was proposed in mid 2013 as a research initiative where students and faculty could engage together in projects powered by low cost open hardware and free software. This article shares the experiences learned by the proponents of the lab and a detailed explanation of the projects, also describes the results of students academic experience.
In the risk engineering and management teaching, technical guides need to be complemented with standards, regulations, guides and professional criteria of Spanish and international prestigious institutions. This situation allows the extension of teaching opportunities, addressed to design teaching activities focused on the analysis and knowledge of considered industrial safety technologies. For this, from the Manufacturing Engineering area of the National Distance Education University, a methodology based on the simulation of the actual Health & Safety professional practice has been developed. In this work, an analysis of the student’s opinions on the teaching methodology of several National Distance Education University subjects related to industrial risk engineering and management is performed. The study covers a period of five academic years, collecting a total of 232 surveys. The analysis methodology has allowed to obtain a general view related to the student satisfaction. Among, the conclusions, it can be highlighted the satisfaction with evaluation model, the flexibility, the quality of contents and the teaching methodology. Finally, in the future, this methodology will be used to perform another teaching performance based on other approaches based, for example, specifically in the training -obtained in these subjects- for professional issues.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.