
handle: 11441/166015
El Procesamiento del Lenguaje Natural es la capacidad para comprender el lenguaje humano de las máquinas. Hace uso de algoritmos de aprendizaje automático para tomar información del mundo real, procesarla y analizarla con el objetivo de que pueda entenderlo como lo hace el ser humano. La rama que del Procesamiento del Lenguaje Natural en la que se centra el estudio es el Análisis de Sentimientos basado en el proceso de detección de sentimientos en texto. Estos modelos se centrar en analizar la polaridad (positiva o negativa). Para llevar a cabo el Análisis de Sentimientos se siguen los siguientes pasos: recopilación de datos, preprocesado del texto, análisis de los datos y comprensión de los resultados obtenidos. En el mundo real, empresas con la finalidad de conocer opiniones sobre algún tema o producto en concreto pueden hacer uso de ello y sacar conclusiones en base a los resultados. Este trabajo se centra en analizar un número de tweets sobre compañías españolas telefónicas realizando una comparación entre tres algoritmos de aprendizaje automático: “K-Nearest Neighbors”, “Multinomial Naïve Bayes” y “Support Vector Machine” (“Stochastic Gradient Descent”).
Natural Language Processing (NLP) is the ability of machines to understand human language. It applies machine learning algorithms to gather information from the real world, process and analyse it, with the aim of understanding language as humans do. Sentiment Analysis is a specific branch of NLP, which focuses on the detection of sentiment in text. Sentiment analysis models aim to analyse the polarity (positive or negative) of the text. To conduct a Sentiment Analysis, the following steps are generally followed: data collection, text pre processing, data analysis and understanding of the results obtained. This approach is often used in the real world by companies to gather feedback on specific topics or products and draw conclusions based on the results. This research is focused on the analysis of a collection of tweets concerning Spanish telecommunication companies, by comparing three machine learning algorithms: "K-Nearest Neighbors", "Multinomial Naïve Bayes" and “Support Vector Machine” ("Stochastic Gradient Descent").
Universidad de Sevilla. Grado en Ingeniería de las Tecnologías de Telecomunicación
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
