{"id":2844,"date":"2026-06-09T11:50:45","date_gmt":"2026-06-09T11:50:45","guid":{"rendered":"https:\/\/interactivehpc.dk\/?p=2844"},"modified":"2026-06-10T07:43:15","modified_gmt":"2026-06-10T07:43:15","slug":"video-tutorial-llm-text-classification","status":"publish","type":"post","link":"https:\/\/interactivehpc.dk\/?p=2844","title":{"rendered":"Video Tutorial: LLM Text Classification"},"content":{"rendered":"\n<figure class=\"wp-block-video\"><video height=\"1080\" style=\"aspect-ratio: 1920 \/ 1080;\" width=\"1920\" controls poster=\"https:\/\/interactivehpc.dk\/wp-content\/uploads\/2026\/04\/LLM-Recording.jpg\" src=\"https:\/\/interactivehpc.dk\/wp-content\/uploads\/2026\/04\/LLM-Text-Classification.mp4\"><track src=\"https:\/\/interactivehpc.dk\/wp-content\/uploads\/2026\/04\/LLM-Text-Classification_EN.vtt\" label=\"LLM Text Classification_EN\" srclang=\"en\" kind=\"subtitles\" default\/><\/video><\/figure>\n\n\n\n<p class=\"gp-gutenbergpro-fa6ad wp-block-paragraph\">The purpose of this webinar is to demonstrate how to perform automated text classification using pre-trained, open-source large language models (LLMs). The efficiency that This webinar demonstrates how to perform automated text classification using pre-trained, open-source large language models (LLMs). The use case is classification of text according to sentiment, but the general workflow is applicable to many other text classification tasks.<\/p>\n\n\n\n<p class=\"gp-gutenbergpro-89cae wp-block-paragraph\"><strong>In the webinar, it is demonstrated how to:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list gp-gutenbergpro-7bed0\">\n<li>Retrieve text data from online sources<\/li>\n\n\n\n<li>Store and prepare the data for analysis<\/li>\n\n\n\n<li>Set up an LLM text classifier<\/li>\n\n\n\n<li>Perform the text classification<\/li>\n\n\n\n<li>Use a web app for human validation of the classification result<\/li>\n<\/ul>\n\n\n\n<p class=\"gp-gutenbergpro-1b626 wp-block-paragraph\"><strong>Time stamps:<\/strong><\/p>\n\n\n\n<p class=\"gp-gutenbergpro-ddb1c wp-block-paragraph\">00:00: Introduction and agenda<br>02:04: Terminology and UCloud workflow outline<br>08:30: Best practices in web scraping<br>11:30: Setting up the UCloud workflow<br>18:30: Scraping and storing the data<br>27:06: Setting up the the classification pipeline<br>42:15: Classifying the data and analyzing the results<br>57:27: Creating a web app for result validation by humans<\/p>\n\n\n\n<p class=\"gp-gutenbergpro-4a8ed wp-block-paragraph\">All scripts used in the webinar can be found here: <a href=\"https:\/\/github.com\/JHavstein\/ucloud-workshop-text-classification-using-LLMs\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/JHavstein\/ucloud-workshop-text-classification-using-LLMs<\/a><\/p>\n\n\n\n<p class=\"gp-gutenbergpro-1ed98 wp-block-paragraph\"><\/p>\n\n\n\n<p class=\"gp-gutenbergpro-bdb49 wp-block-paragraph\"><a href=\"https:\/\/interactivehpc.dk\/?page_id=2540\" data-type=\"page\" data-id=\"2540\">Sign up for our newsletter and stay updated on future webinars.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The purpose of this webinar is to demonstrate how to perform automated text classification using pre-trained, open-source large language models (LLMs). The efficiency that This webinar demonstrates how to perform automated text classification using pre-trained, open-source large language models (LLMs). The use case is classification of text according to sentiment, but the general workflow is [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2914,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"gtp_columnspro_styling":"{}","gtp_paragraph_styling":"{\"bdb49822-953e-484e-88b0-bb08a6b46367\":\" .gp-gutenbergpro-bdb49 { background-position-x: 50%;\\nbackground-position-y: 50%;\\nbackground-size: cover;\\nheight: px; }\",\"4a8edd36-7a08-407d-a374-3d6e24c78239\":\" .gp-gutenbergpro-4a8ed { background-position-x: 50%;\\nbackground-position-y: 50%;\\nbackground-size: cover;\\nheight: px; }\"}","gtp_heading_styling":"{}","gtp_spacer_styling":"{}","gtp_video_styling":"{}","gtp_group_styling":"{}","gtp_cover_styling":"{}","footnotes":""},"categories":[40,38,10],"tags":[264,320,268,266],"class_list":["post-2844","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-interactive-hpc","category-supercomputing","category-tutorial","tag-ai___en","tag-ai-application___en","tag-large-language-models___en","tag-llm___en"],"lang":"en","translations":{"en":2844,"da":2916},"pll_sync_post":[],"_links":{"self":[{"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/posts\/2844","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2844"}],"version-history":[{"count":8,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/posts\/2844\/revisions"}],"predecessor-version":[{"id":2929,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/posts\/2844\/revisions\/2929"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=\/wp\/v2\/media\/2914"}],"wp:attachment":[{"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2844"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2844"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/interactivehpc.dk\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2844"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}