Análisis de sentimientos en twitter sobre aprendizaje móvil
Análisis de sentimientos en twitter sobre aprendizaje móvil
Portada
Código QR
Director
Autor corporativo
Recolector de datos
Otros/Desconocido
Director audiovisual
Editor/Compilador
Editores
Universidad Tecnológica de Pereira
Tipo de Material
Fecha
2022
Cita bibliográfica
Título de serie/ reporte/ volumen/ colección
Trabajos de investigación
Es Parte de
Resumen
El aprendizaje móvil (m-learning) genera reacciones encontradas entre expertos en educación y organismos orientadores y reguladores de esta. Espacios como Twitter son escenario de discusiones y propuestas sobre m-learning, lo que requiere identificar las tendencias de los temas de interés, la polaridad y los usuarios potencialmente más influyentes en estas publicaciones. A partir de la revisión sistemática de literatura realizada en Scopus y Web of Science se identificaron 21 documentos sobre análisis de sentimiento en Twitter, de los cuales solo el 10% trataba sobre m-learning. Un proceso de monitorización pudo permitir la identificación de tendencias en los temas de interés, la polaridad y los usuarios potencialmente más influyentes en las publicaciones sobre m-learning en Twitter. Usando la API Rest de Twitter se importaron 27.668 tuits entre el 28/09/2019 y el 28/12/2019. Se procesaron mediante análisis de redes sociales, minería de texto y análisis de sentimientos, usando NodeXL y el Lenguaje R. La red de comunicación creada mostró 20.530 nodos, 36.240 conexiones y 4.974 grupos. El 49% de los tuits expresaba sentimiento positivo, el 10% negativo, y el 41% neutro. Las tendencias en los temas de interés se asociaron a hashtags como #edtech, #education, #AI. Usuarios como @eraser, @favfuckboi y @kurteichenwald se destacaron entre los potencialmente más influyentes dentro del conjunto de quienes publicaron tuits identificados como positivos y @zaiddibis, @sian_ruffell, @zimperium dentro del grupo de los negativos. La investigación busca avanzar en la comprensión de las opiniones sobre el desarrollo de propuestas educativas apoyadas en dispositivos móviles. Los avances metodológicos y los procesos de análisis desarrollados podrán ser usados en campos como la salud, la política y los desastres naturales.
Mobile learning (m-learning) generates mixed reactions between education experts and education guiding and regulatory bodies. Spaces such as Twitter are the scenario of discussions and proposals on m-learning, which requires identifying the trends of the topics of interest, polarity and potentially most influential users in these publications. From the systematic review of literature carried out in Scopus and Web of Science, we identified 21 documents on sentiment analysis on Twitter, out of which only 10% dealt with m-learning. Through a monitoring process we identified trends in topics of interest, polarity and potentially most influential users in m-learning posts on Twitter. Using Twitter's Rest API, we imported 27,668 tweets over the period between 09/28/2019 and 12/28/2019. We processed them using social network analysis, text mining and sentiment analysis, using NodeXL and the R Language. The communication network created showed 20,530 nodes, 36,240 connections and 4,974 groups. 49% of tweets expressed positive sentiment, 10% negative, and 41% neutral. Trends in topics of interest were associated with hashtags such as #edtech, #education, #AI. Users such as @eraser, @favfuckboi and @kurteichenwald were among the potentially most influential within the set of those who published tweets identified as positive, and within the group of negatives, @zaiddibis, @sian_ruffell, @zimperium stood out. The research seeks to advance the understanding of opinions on the development of educational proposals supported by mobile devices. The methodological progress achieved, and the analysis processes developed can also be used in fields such as health, politics and natural disasters.
Mobile learning (m-learning) generates mixed reactions between education experts and education guiding and regulatory bodies. Spaces such as Twitter are the scenario of discussions and proposals on m-learning, which requires identifying the trends of the topics of interest, polarity and potentially most influential users in these publications. From the systematic review of literature carried out in Scopus and Web of Science, we identified 21 documents on sentiment analysis on Twitter, out of which only 10% dealt with m-learning. Through a monitoring process we identified trends in topics of interest, polarity and potentially most influential users in m-learning posts on Twitter. Using Twitter's Rest API, we imported 27,668 tweets over the period between 09/28/2019 and 12/28/2019. We processed them using social network analysis, text mining and sentiment analysis, using NodeXL and the R Language. The communication network created showed 20,530 nodes, 36,240 connections and 4,974 groups. 49% of tweets expressed positive sentiment, 10% negative, and 41% neutral. Trends in topics of interest were associated with hashtags such as #edtech, #education, #AI. Users such as @eraser, @favfuckboi and @kurteichenwald were among the potentially most influential within the set of those who published tweets identified as positive, and within the group of negatives, @zaiddibis, @sian_ruffell, @zimperium stood out. The research seeks to advance the understanding of opinions on the development of educational proposals supported by mobile devices. The methodological progress achieved, and the analysis processes developed can also be used in fields such as health, politics and natural disasters.
Descripción general
Notas
URL del Recurso
Identificador ISBN
978-958-722-781-9