{"id":8474,"date":"2023-12-21T14:35:55","date_gmt":"2023-12-21T12:35:55","guid":{"rendered":"https:\/\/www.lisdatasolutions.com\/?p=8474"},"modified":"2023-12-21T17:59:30","modified_gmt":"2023-12-21T15:59:30","slug":"lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros","status":"publish","type":"post","link":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/","title":{"rendered":"LIS Data Solutions crea una herramienta de topic modeling para analizar foros"},"content":{"rendered":"<p>Saber de qu\u00e9 temas se habla en una red social o entender qu\u00e9 direcci\u00f3n toman las conversaciones de los usuarios de un foro de internet sobre una cuesti\u00f3n determinada no es f\u00e1cil: la informaci\u00f3n aparece desperdigada, repartida entre miles de comentarios, y es muy dif\u00edcil llevar a cabo un an\u00e1lisis manual de la misma.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_55 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Tabla de contenidos<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\" role=\"button\"><label for=\"item-69e3505a27dce\" ><span class=\"\"><span style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input aria-label=\"Toggle\" aria-label=\"item-69e3505a27dce\"  type=\"checkbox\" id=\"item-69e3505a27dce\"><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#Una_solucion_basada_en_el_machine_learning\" title=\"Una soluci\u00f3n basada en el machine learning\">Una soluci\u00f3n basada en el machine learning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#Como_usar_el_topic_modeling_para_generar_informacion_entendible\" title=\"C\u00f3mo usar el topic modeling para generar informaci\u00f3n entendible\">C\u00f3mo usar el topic modeling para generar informaci\u00f3n entendible<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#Datos_economicos\" title=\"Datos econ\u00f3micos\">Datos econ\u00f3micos<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"Una_solucion_basada_en_el_machine_learning\"><\/span>Una soluci\u00f3n basada en el <em>machine learning<\/em><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Para afrontar el reto de analizar la informaci\u00f3n contenida en foros web, en LIS Data Solutions pusimos en pr\u00e1ctica nuestros conocimientos en <em>big data<\/em> y <em>machine learning<\/em>. El proyecto, para el que se estableci\u00f3 una duraci\u00f3n estimada de 12 meses, presentaba un enfoque pr\u00e1ctico de algunas de nuestras investigaciones previas sobre t\u00e9cnicas de Procesamiento de Lenguaje Natural (PLN).<\/p>\n<p>Se trataba de realizar un an\u00e1lisis autom\u00e1tico de un conjunto de textos en espa\u00f1ol (en este caso, comentarios en foros de opini\u00f3n) para saber de qu\u00e9 se habla y obtener un resumen de los temas m\u00e1s destacados. Tambi\u00e9n deb\u00eda ser posible buscar la presencia de temas concretos, as\u00ed como realizar an\u00e1lisis a diferentes niveles o sugerir extensiones de los temas propuestos por los usuarios.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Como_usar_el_topic_modeling_para_generar_informacion_entendible\"><\/span>C\u00f3mo usar el <em>topic modeling<\/em> para generar informaci\u00f3n entendible<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Nuestro equipo de I+D decidi\u00f3 recurrir a t\u00e9cnicas de <em>machine learning <\/em>como el \u201ctopic modeling\u201d, que consiste en la detecci\u00f3n de patrones en el uso de las palabras y en la consecuente agrupaci\u00f3n de piezas de texto en funci\u00f3n de esos patrones.<\/p>\n<p>Creamos un corpus con comentarios de Amazon con los que entrenar al modelo en la forma de escribir en foros (informalmente, con faltas de ortograf\u00eda, con frases cortas y poco complejas, etc.) y probamos diferentes t\u00e9cnicas de <em>topic modeling<\/em> y encaje l\u00e9xico o <em>embedding<\/em>. Al acabar el proyecto, hab\u00edamos alcanzado nuestro objetivo: cont\u00e1bamos con un sistema que realizaba un an\u00e1lisis satisfactorio de los principales temas de cada conversaci\u00f3n y presentaba los datos de forma ordenada y f\u00e1cilmente entendible en un panel de control.<\/p>\n<p>&nbsp;<\/p>\n<p><img class=\"wp-image-8508 aligncenter\" src=\"https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/SODERCAN-scaled-e1703172167201-1024x189.jpg\" alt=\"SODERCAN LOGO\" width=\"422\" height=\"78\" srcset=\"https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/SODERCAN-scaled-e1703172167201-1024x189.jpg 1024w, https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/SODERCAN-scaled-e1703172167201-300x55.jpg 300w, https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/SODERCAN-scaled-e1703172167201-768x142.jpg 768w, https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/SODERCAN-scaled-e1703172167201.jpg 1400w\" sizes=\"(max-width: 422px) 100vw, 422px\" \/><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Datos_economicos\"><\/span>Datos econ\u00f3micos<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<table width=\"497\">\n<tbody>\n<tr>\n<td width=\"203\">Plazo Ejecuci\u00f3n<\/td>\n<td width=\"294\">27\/06\/2022 \u2013 30\/06\/2023<\/td>\n<\/tr>\n<tr>\n<td>Concedente<\/td>\n<td>SODERCAN<\/td>\n<\/tr>\n<tr>\n<td>T\u00edtulo del proyecto<\/td>\n<td>TIC 2022 \u2013 ANDES<\/td>\n<\/tr>\n<tr>\n<td>Presupuesto<\/td>\n<td>81.039,00 \u20ac<\/td>\n<\/tr>\n<tr>\n<td>Importe concedido<\/td>\n<td>17.623,48 \u20ac<\/td>\n<\/tr>\n<tr>\n<td>Fecha de concesi\u00f3n<\/td>\n<td>25\/01\/2023<\/td>\n<\/tr>\n<tr>\n<td>%<\/td>\n<td>22%<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"<p>Saber de qu\u00e9 temas se habla en una red social o entender qu\u00e9 direcci\u00f3n toman las conversaciones de los usuarios de un foro de internet sobre una cuesti\u00f3n determinada no es f\u00e1cil: la informaci\u00f3n aparece desperdigada, repartida entre miles de comentarios, y es muy dif\u00edcil llevar a cabo un an\u00e1lisis manual de la misma. Una [&hellip;]<\/p>\n","protected":false},"author":21,"featured_media":8483,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0},"categories":[186,190,31,43,42],"tags":[193,208,209,207],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions<\/title>\n<meta name=\"description\" content=\"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions\" \/>\n<meta property=\"og:description\" content=\"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/\" \/>\n<meta property=\"og:site_name\" content=\"LIS Data Solutions\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-21T12:35:55+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-12-21T15:59:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/pexels-picjumbocom-196655-scaled-e1703168526255.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1385\" \/>\n\t<meta property=\"og:image:height\" content=\"924\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Natalia Andueza\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Natalia Andueza\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/\",\"url\":\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/\",\"name\":\"LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions\",\"isPartOf\":{\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/#website\"},\"datePublished\":\"2023-12-21T12:35:55+00:00\",\"dateModified\":\"2023-12-21T15:59:30+00:00\",\"author\":{\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/b2748ac1971664b77f38389a77eb1fc7\"},\"description\":\"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Portada\",\"item\":\"https:\/\/www.lisdatasolutions.com\/es\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LIS Data Solutions crea una herramienta de topic modeling para analizar foros\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/#website\",\"url\":\"https:\/\/www.lisdatasolutions.com\/es\/\",\"name\":\"LIS Data Solutions\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.lisdatasolutions.com\/es\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"es\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/b2748ac1971664b77f38389a77eb1fc7\",\"name\":\"Natalia Andueza\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/67d34db2d9aca971aeec85ef05923c86?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/67d34db2d9aca971aeec85ef05923c86?s=96&d=mm&r=g\",\"caption\":\"Natalia Andueza\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions","description":"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/","og_locale":"es_ES","og_type":"article","og_title":"LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions","og_description":"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.","og_url":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/","og_site_name":"LIS Data Solutions","article_published_time":"2023-12-21T12:35:55+00:00","article_modified_time":"2023-12-21T15:59:30+00:00","og_image":[{"width":1385,"height":924,"url":"https:\/\/www.lisdatasolutions.com\/wp-content\/uploads\/2023\/12\/pexels-picjumbocom-196655-scaled-e1703168526255.jpg","type":"image\/jpeg"}],"author":"Natalia Andueza","twitter_card":"summary_large_image","twitter_misc":{"Escrito por":"Natalia Andueza","Tiempo de lectura":"2 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/","url":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/","name":"LIS Data Solutions crea una herramienta de topic modeling para analizar foros | LIS Data Solutions","isPartOf":{"@id":"https:\/\/www.lisdatasolutions.com\/es\/#website"},"datePublished":"2023-12-21T12:35:55+00:00","dateModified":"2023-12-21T15:59:30+00:00","author":{"@id":"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/b2748ac1971664b77f38389a77eb1fc7"},"description":"LIS Data Solutions ha creado un modelo de machine learning que emplea topic modeling para analizar la informaci\u00f3n recogida en foros web.","breadcrumb":{"@id":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.lisdatasolutions.com\/es\/blog\/lis-data-solutions-crea-una-herramienta-de-topic-modeling-para-analizar-foros\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/www.lisdatasolutions.com\/es\/"},{"@type":"ListItem","position":2,"name":"LIS Data Solutions crea una herramienta de topic modeling para analizar foros"}]},{"@type":"WebSite","@id":"https:\/\/www.lisdatasolutions.com\/es\/#website","url":"https:\/\/www.lisdatasolutions.com\/es\/","name":"LIS Data Solutions","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.lisdatasolutions.com\/es\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"es"},{"@type":"Person","@id":"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/b2748ac1971664b77f38389a77eb1fc7","name":"Natalia Andueza","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/www.lisdatasolutions.com\/es\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/67d34db2d9aca971aeec85ef05923c86?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/67d34db2d9aca971aeec85ef05923c86?s=96&d=mm&r=g","caption":"Natalia Andueza"}}]}},"_links":{"self":[{"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/posts\/8474"}],"collection":[{"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/users\/21"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/comments?post=8474"}],"version-history":[{"count":8,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/posts\/8474\/revisions"}],"predecessor-version":[{"id":8538,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/posts\/8474\/revisions\/8538"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/media\/8483"}],"wp:attachment":[{"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/media?parent=8474"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/categories?post=8474"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lisdatasolutions.com\/es\/wp-json\/wp\/v2\/tags?post=8474"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}