{"id":117701,"date":"2018-03-11T10:47:18","date_gmt":"2018-03-11T10:47:18","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/mineria-de-opiniones-basada-en-caractera%c2%adsticas-guiada-por-ontologa%c2%adas\/"},"modified":"2018-03-11T10:47:18","modified_gmt":"2018-03-11T10:47:18","slug":"mineria-de-opiniones-basada-en-caractera%c2%adsticas-guiada-por-ontologa%c2%adas","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/ciencias-tecnologicas\/mineria-de-opiniones-basada-en-caractera%c2%adsticas-guiada-por-ontologa%c2%adas\/","title":{"rendered":"Miner\u00eda de opiniones basada en caracter\u00edsticas guiada por ontolog\u00edas"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Isidro Pe\u00f1alver Martinez <\/strong><\/h2>\n<p>Objetivos el trabajo realizado en esta tesis doctoral persigue los siguientes objetivos: (i) definici\u00f3n y formalizaci\u00f3n de una metodolog\u00eda de miner\u00eda de opiniones basada en caracter\u00edsticas para clasificar los sentimientos de las opiniones. Esta metodolog\u00eda incluir\u00e1 procesamiento del lenguaje natural, identificaci\u00f3n de caracter\u00edsticas, c\u00e1lculo de la polaridad de las caracter\u00edsticas y an\u00e1lisis de sentimientos; (ii) dise\u00f1o e implementaci\u00f3n de una aplicaci\u00f3n software para llevar a cabo el proceso de an\u00e1lisis de sentimientos de las opiniones de los usuarios. Este sistema se dise\u00f1ar\u00e1 para cumplir con los requisitos que implica el entorno de miner\u00eda de opiniones descrito. Se emplear\u00e1n para ello las tecnolog\u00edas m\u00e1s novedosas y los recursos mejor valorados disponibles actualmente; (iii) validaci\u00f3n de la aplicaci\u00f3n de software en varios dominios. La metodolog\u00eda propuesta y el software desarrollado ser\u00e1n validados en dos dominios totalmente diferentes: opiniones sobre pel\u00edculas y finanzas. metodolog\u00eda la metodolog\u00eda que se ha creado responde a un innovador sistema de an\u00e1lisis de sentimientos basado en caracter\u00edsticas que utiliza como base de conocimiento una ontolog\u00eda del dominio. Esta metodolog\u00eda propuesta es independiente del dominio y del idioma empleados. A partir de ella se identifican las caracter\u00edsticas relevantes dentro de cada opini\u00f3n. Durante el proceso de identificaci\u00f3n se tiene en cuenta la estructura sem\u00e1ntica de la ontolog\u00eda. Cada una de las frases que contengan expresiones ling\u00ed\u00bc\u00edsticas que est\u00e9n directamente relacionadas con t\u00e9rminos de la ontolog\u00eda se tienen en cuenta para calcular la polaridad global de la opini\u00f3n del usuario. La aplicaci\u00f3n de esta metodolog\u00eda ha propiciado el desarrollo de un nuevo software para la clasificaci\u00f3n de sentimientos de opiniones basado en c\u00e1lculos vectoriales en el espacio r3.  conclusiones el tipo de lenguaje informal que emplean los usuarios en sus opiniones dificulta mucho el empleo de t\u00e9cnicas de pln efectivas. Las herramientas que tenemos en la actualidad no contemplan irregularidades ling\u00ed\u00bc\u00edsticas en la mayor\u00eda de los casos. La investigaci\u00f3n llevada a cabo en este trabajo ha estado motivada principalmente por la carencia de recursos, m\u00e9todos y herramientas para un efectivo procesamiento de la informaci\u00f3n subjetiva. Adem\u00e1s, el uso de ontolog\u00edas en el proceso de miner\u00eda de opiniones basada en caracter\u00edsticas resulta muy beneficioso. El sistema de software implementado alcanza resultados \u00f3ptimos cuando hay muchas palabras con alto contenido emocional cerca de la expresi\u00f3n ling\u00ed\u00bc\u00edstica que identifica a una caracter\u00edstica dentro de la opini\u00f3n de un usuario. Ya que el sistema tiene mucha informaci\u00f3n para poder calcular correctamente la polaridad de la caracter\u00edstica. Dependiendo del dominio en el que se trabaje se tendr\u00e1 un grado de subjetividad m\u00e1s o menos alto a la hora de clasificar las caracter\u00edsticas identificadas en las opiniones. En dominios donde la ambig\u00ed\u00bcedad y el margen de interpretaci\u00f3n en funci\u00f3n del contexto son bajos, c\u00f3mo por ejemplo el dominio de las pel\u00edculas, los resultados para la clasificaci\u00f3n de sentimientos de caracter\u00edsticas ser\u00e1n buenos. En otros donde las opiniones tengan mucho margen de interpretaci\u00f3n, exista un componente de ambig\u00ed\u00bcedad alto y las opiniones tengan un significado muy ligado al momento temporal en el que se emiten, los resultados para la clasificaci\u00f3n de sentimientos de caracter\u00edsticas ser\u00e1n peores. Este es el caso del dominio financiero.  objectives the work done in this thesis has the following objectives: (i) definition and formalization of a feature-based opinion mining methodology to classify the feelings of opinions. This methodology will include natural language processing, feature identification, features polarity calculation and sentiment analysis; (ii) design and implementation of a software application to perform the sentiment analysis  in user reviews. This system will be designed to meet the requirements involving the methodology. The latest technologies and the most valued resources currently available will be used; (iii) validation of the software application in several domains. The proposed methodology and the software application will be validated in two entirely different domains: movies and finance reviews. methodology the methodology proposed in this work has been used to develop a software system to perform featured-based opinion mining in user reviews. It uses a domain ontology as knowledge base. This methodology is independent of the domain and language used. The relevant features are identified within each review. During the features identification process the system uses the semantic structure of the ontology. Each phrase that contain linguistic expressions that are directly related to ontology concepts are taken into account when calculating the overall polarity of the user opinions. The system for the classification of feelings in user opinions is based on vector calculations in the r3 space. conclusions the informal language used by users in their opinions hinders the use of effective nlp techniques much. In most cases the existing tools do not include irregularities linguistic. The research conducted in this work has been motivated primarily by a lack of resources, methods and tools for effective processing of subjective information. Furthermore, the use of ontologies in the feature based opinion mining process produces large profits. The software system deployed achieves optimal results when there are many words with high emotional content near linguistic expression identifying a feature within a user&apos;s opinion. Since the system has a lot of information to calculate the feature polarity properly. Each domain will have a degree of subjectivity rather high when classifying identified features in the opinions. In domains where ambiguity and interpretation depending on the context are low, such as the domain of movies, the results for features sentiment analysis are promising. In other where opinions have much interpretation of context and there is a high component ambiguity results for feature based opinion mining process will be worse. This is the case in the financial domain.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Miner\u00eda de opiniones basada en caracter\u00edsticas guiada por ontolog\u00edas<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Miner\u00eda de opiniones basada en caracter\u00edsticas guiada por ontolog\u00edas <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Isidro Pe\u00f1alver Martinez <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Murcia<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 24\/06\/2015<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Rafael Valencia Garc\u00eda<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: rodrigo Mart\u00ednez b\u00e9jar <\/li>\n<li>dagoberto Castellanos nieves (vocal)<\/li>\n<li>alejandro Rodriguez gonzalez (vocal)<\/li>\n<li>Juan  Miguel Gomez berbis (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Isidro Pe\u00f1alver Martinez Objetivos el trabajo realizado en esta tesis doctoral persigue los siguientes objetivos: (i) definici\u00f3n [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[332,13880,8235,886,15624],"tags":[193254,137360,231798,206773,159842,69329],"class_list":["post-117701","post","type-post","status-publish","format-standard","hentry","category-ciencias-tecnologicas","category-informatica","category-murcia","category-semantica","category-software","tag-alejandro-rodriguez-gonzalez","tag-dagoberto-castellanos-nieves","tag-isidro-penalver-Martinez","tag-juan-miguel-gomez-berbis","tag-rafael-valencia-garcia","tag-rodrigo-Martinez-bejar"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/117701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=117701"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/117701\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=117701"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=117701"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=117701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}