{"id":35978,"date":"2024-10-10T14:08:35","date_gmt":"2024-10-10T12:08:35","guid":{"rendered":"https:\/\/www.l3s.de\/?p=35978"},"modified":"2024-10-10T14:12:17","modified_gmt":"2024-10-10T12:12:17","slug":"defusing-toxic-online-debates-with-ai","status":"publish","type":"post","link":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/","title":{"rendered":"KI im Einsatz gegen toxische Online-Debatten"},"content":{"rendered":"<p class=\"wp-block-paragraph\"><strong>L3S Best Publication of the Quarter (Q3\/2024)<br>Category: Natural Language Processing, Large Language Models<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\" style=\"font-size:23px\"><strong>LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback<\/strong>&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Authors: Timon Ziegenbein, Gabriella Skitalinskaya, Alireza Bayat Makou, Henning Wachsmuth&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>Erschienen in <a href=\"https:\/\/aclanthology.org\/2024.acl-long.244.pdf\" target=\"_blank\" rel=\"noopener\" title=\"\">Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics <\/a>(A* conference)&nbsp;<\/em><\/p>\n\n\n\n<div style=\"height:28px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Das Papier in K\u00fcrze<\/strong>:\u202f&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Eine gro\u00dfe Herausforderung f\u00fcr Social-Media-Plattformen ist es, daf\u00fcr zu sorgen, dass Online-Diskussionen zivil und produktiv verlaufen. Solche Plattformen verlassen sich in der Regel sowohl auf Nutzer als auch auf automatische Erkennungsinstrumente, um unangemessene Argumente anderer Nutzer zu markieren, die dann von Moderatoren \u00fcberpr\u00fcft werden. Diese Art der Post-Hoc-Moderation ist jedoch teuer und zeitaufw\u00e4ndig, und die Moderatoren sind mit der Menge und Schwere der markierten Inhalte oft \u00fcberfordert. Eine vielversprechende Alternative besteht darin, negatives Verhalten bereits bei der Erstellung von Inhalten zu verhindern. In diesem Beitrag wird untersucht, wie unangemessene Sprache in Argumenten rechnerisch entsch\u00e4rft werden kann. Wir schlagen einen rechnerischen Ansatz vor, der auf der Grundlage eines gro\u00dfen Sprachmodells (LLM) ein Gleichgewicht zwischen dem Erhalt des Inhalts und der Angemessenheit herstellt. Wir evaluieren verschiedene Grade der Inhaltserhaltung und Angemessenheit in menschlichen Bewertungsstudien. Systematische Experimente zeigen, dass unser Ansatz die Unangemessenheit von Argumenten abschw\u00e4chen kann, w\u00e4hrend ihr Inhalt weitgehend erhalten bleibt. Er \u00fcbertrifft signifikant konkurrierende Berechnungsgrundlagen und Menschen.\u00a0<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Welche potenziellen Auswirkungen haben Ihre Ergebnisse?<\/strong>\u202f&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Die Ergebnisse dieser Forschung k\u00f6nnen f\u00fcr die Entwicklung eines computergest\u00fctzten Tools genutzt werden, das Nutzern helfen kann, in Online-Diskussionen angemessenere Argumente zu verfassen. Dieses Tool kann in Social-Media-Plattformen integriert werden, um negatives Verhalten bei der Erstellung von Inhalten zu verhindern. Dies kann dazu beitragen, die Qualit\u00e4t von Online-Diskussionen zu verbessern und Social-Media-Plattformen zivilisierter und produktiver zu machen.\u00a0<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Was ist das Neue an Ihrer Forschung?<\/strong>\u202f&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Diese Forschungsarbeit ist die erste, die einen rechnerischen Ansatz vorschl\u00e4gt, der die Erhaltung des Inhalts und die Angemessenheit beim Umschreiben unangemessener Argumente in Einklang bringt. Der Ansatz basiert auf einem gro\u00dfen Sprachmodell (Large Language Model, LLM) und nutzt Verst\u00e4rkungslernen, um zu lernen, wie man Argumente umschreibt, ohne dass parallele Daten ben\u00f6tigt werden.\u00a0<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Link zum Paper:<\/strong><strong>\u202f<\/strong>\u202f<a href=\"https:\/\/aclanthology.org\/2024.acl-long.244.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/aclanthology.org\/2024.acl-long.244.pdf<\/a>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>In der Kategorie \"Natural Language Processing, Large Language Models\" bietet die beste L3S-Ver\u00f6ffentlichung des Quartals eine L\u00f6sung an, wie KI den Diskurs in den sozialen Medien versachlichen kann.<\/p>","protected":false},"author":11,"featured_media":35979,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[161],"tags":[],"class_list":["post-35978","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-best-publications"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 4.9.8 - aioseo.com -->\n\t<meta name=\"description\" content=\"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"borovynska\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 4.9.8\" \/>\n\t\t<meta property=\"og:locale\" content=\"de_DE\" \/>\n\t\t<meta property=\"og:site_name\" content=\"L3S Research Center - Trustworthy AI &amp; Digital Transformation\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"Defusing toxic online debates with AI - L3S Research Center\" \/>\n\t\t<meta property=\"og:description\" content=\"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2024-10-10T12:08:35+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2024-10-10T12:12:17+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n\t\t<meta name=\"twitter:site\" content=\"@l3s_luh\" \/>\n\t\t<meta name=\"twitter:title\" content=\"Defusing toxic online debates with AI - L3S Research Center\" \/>\n\t\t<meta name=\"twitter:description\" content=\"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.\" \/>\n\t\t<meta name=\"twitter:creator\" content=\"@l3s_luh\" \/>\n\t\t<meta name=\"twitter:image\" content=\"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#blogposting\",\"name\":\"Defusing toxic online debates with AI - L3S Research Center\",\"headline\":\"Defusing toxic online debates with AI\",\"author\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/author\\\/borovynska\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/wp-content\\\/uploads\\\/2024\\\/10\\\/Natural-Language-Processing-Large-Language-Models.png\",\"width\":1200,\"height\":627},\"datePublished\":\"2024-10-10T14:08:35+02:00\",\"dateModified\":\"2024-10-10T14:12:17+02:00\",\"inLanguage\":\"de-DE\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#webpage\"},\"articleSection\":\"Best Publications\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.l3s.de\\\/de\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/category\\\/best-publications\\\/#listItem\",\"name\":\"Best Publications\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/category\\\/best-publications\\\/#listItem\",\"position\":2,\"name\":\"Best Publications\",\"item\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/category\\\/best-publications\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#listItem\",\"name\":\"Defusing toxic online debates with AI\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#listItem\",\"position\":3,\"name\":\"Defusing toxic online debates with AI\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/category\\\/best-publications\\\/#listItem\",\"name\":\"Best Publications\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/#organization\",\"name\":\"L3S Research Center\",\"description\":\"Trustworthy AI & Digital Transformation\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/LS3-Logo-2024.png\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#organizationLogo\",\"width\":4188,\"height\":2549},\"image\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#organizationLogo\"},\"sameAs\":[\"https:\\\/\\\/www.twitter.com\\\/l3s_luh\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCJzIw4-5qZJhmzOUsruHlhA\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/l3s-research-center\",\"https:\\\/\\\/de.wikipedia.org\\\/wiki\\\/L3S\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/author\\\/borovynska\\\/#author\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/author\\\/borovynska\\\/\",\"name\":\"borovynska\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#webpage\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/\",\"name\":\"Defusing toxic online debates with AI - L3S Research Center\",\"description\":\"In the category \\u2018Natural Language Processing, Large Language Models\\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.\",\"inLanguage\":\"de-DE\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/author\\\/borovynska\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/author\\\/borovynska\\\/#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/wp-content\\\/uploads\\\/2024\\\/10\\\/Natural-Language-Processing-Large-Language-Models.png\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#mainImage\",\"width\":1200,\"height\":627},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/defusing-toxic-online-debates-with-ai\\\/#mainImage\"},\"datePublished\":\"2024-10-10T14:08:35+02:00\",\"dateModified\":\"2024-10-10T14:12:17+02:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/#website\",\"url\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/\",\"name\":\"L3S Research Center\",\"alternateName\":\"L3S\",\"description\":\"Trustworthy AI & Digital Transformation\",\"inLanguage\":\"de-DE\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.l3s.de\\\/de\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"Defusing toxic online debates with AI - L3S Research Center","description":"In der Kategorie \"Natural Language Processing, Large Language Models\" bietet die beste L3S-Ver\u00f6ffentlichung des Quartals eine L\u00f6sung an, wie KI den Diskurs in den sozialen Medien versachlichen kann.","canonical_url":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BlogPosting","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#blogposting","name":"Defusing toxic online debates with AI - L3S Research Center","headline":"Defusing toxic online debates with AI","author":{"@id":"https:\/\/www.l3s.de\/de\/author\/borovynska\/#author"},"publisher":{"@id":"https:\/\/www.l3s.de\/de\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/10\/Natural-Language-Processing-Large-Language-Models.png","width":1200,"height":627},"datePublished":"2024-10-10T14:08:35+02:00","dateModified":"2024-10-10T14:12:17+02:00","inLanguage":"de-DE","mainEntityOfPage":{"@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#webpage"},"isPartOf":{"@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#webpage"},"articleSection":"Best Publications"},{"@type":"BreadcrumbList","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de#listItem","position":1,"name":"Home","item":"https:\/\/www.l3s.de\/de","nextItem":{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de\/category\/best-publications\/#listItem","name":"Best Publications"}},{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de\/category\/best-publications\/#listItem","position":2,"name":"Best Publications","item":"https:\/\/www.l3s.de\/de\/category\/best-publications\/","nextItem":{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#listItem","name":"Defusing toxic online debates with AI"},"previousItem":{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#listItem","position":3,"name":"Defusing toxic online debates with AI","previousItem":{"@type":"ListItem","@id":"https:\/\/www.l3s.de\/de\/category\/best-publications\/#listItem","name":"Best Publications"}}]},{"@type":"Organization","@id":"https:\/\/www.l3s.de\/de\/#organization","name":"L3S Research Center","description":"Trustworthy AI & Digital Transformation","url":"https:\/\/www.l3s.de\/de\/","logo":{"@type":"ImageObject","url":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024.png","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#organizationLogo","width":4188,"height":2549},"image":{"@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#organizationLogo"},"sameAs":["https:\/\/www.twitter.com\/l3s_luh","https:\/\/www.youtube.com\/channel\/UCJzIw4-5qZJhmzOUsruHlhA","https:\/\/www.linkedin.com\/company\/l3s-research-center","https:\/\/de.wikipedia.org\/wiki\/L3S"]},{"@type":"Person","@id":"https:\/\/www.l3s.de\/de\/author\/borovynska\/#author","url":"https:\/\/www.l3s.de\/de\/author\/borovynska\/","name":"borovynska"},{"@type":"WebPage","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#webpage","url":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/","name":"Defusing toxic online debates with AI - L3S Research Center","description":"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.","inLanguage":"de-DE","isPartOf":{"@id":"https:\/\/www.l3s.de\/de\/#website"},"breadcrumb":{"@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#breadcrumblist"},"author":{"@id":"https:\/\/www.l3s.de\/de\/author\/borovynska\/#author"},"creator":{"@id":"https:\/\/www.l3s.de\/de\/author\/borovynska\/#author"},"image":{"@type":"ImageObject","url":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/10\/Natural-Language-Processing-Large-Language-Models.png","@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#mainImage","width":1200,"height":627},"primaryImageOfPage":{"@id":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/#mainImage"},"datePublished":"2024-10-10T14:08:35+02:00","dateModified":"2024-10-10T14:12:17+02:00"},{"@type":"WebSite","@id":"https:\/\/www.l3s.de\/de\/#website","url":"https:\/\/www.l3s.de\/de\/","name":"L3S Research Center","alternateName":"L3S","description":"Trustworthy AI & Digital Transformation","inLanguage":"de-DE","publisher":{"@id":"https:\/\/www.l3s.de\/de\/#organization"}}]},"og:locale":"de_DE","og:site_name":"L3S Research Center - Trustworthy AI &amp; Digital Transformation","og:type":"article","og:title":"Defusing toxic online debates with AI - L3S Research Center","og:description":"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.","og:url":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/","og:image":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png","og:image:secure_url":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png","article:published_time":"2024-10-10T12:08:35+00:00","article:modified_time":"2024-10-10T12:12:17+00:00","twitter:card":"summary_large_image","twitter:site":"@l3s_luh","twitter:title":"Defusing toxic online debates with AI - L3S Research Center","twitter:description":"In the category \u2018Natural Language Processing, Large Language Models\u2019, the best L3S publication of the quarter offers a solution for how AI can civilise the discourse in social media.","twitter:creator":"@l3s_luh","twitter:image":"https:\/\/www.l3s.de\/wp-content\/uploads\/2024\/11\/LS3-Logo-2024-WHITE.png"},"aioseo_meta_data":{"post_id":"35978","title":null,"description":null,"keywords":null,"keyphrases":{"focus":{"keyphrase":"","score":0,"analysis":{"keyphraseInTitle":{"score":0,"maxScore":9,"error":1}}},"additional":[]},"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":"","og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"BlogPosting","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":"-1","robots_max_videopreview":"-1","robots_max_imagepreview":"large","priority":null,"frequency":"default","local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2024-10-10 12:08:36","updated":"2025-06-16 11:12:21","seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/www.l3s.de\/de\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/www.l3s.de\/de\/category\/best-publications\/\" title=\"Best Publications\">Best Publications<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tDefusing toxic online debates with AI\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/www.l3s.de\/de"},{"label":"Best Publications","link":"https:\/\/www.l3s.de\/de\/category\/best-publications\/"},{"label":"Defusing toxic online debates with AI","link":"https:\/\/www.l3s.de\/de\/defusing-toxic-online-debates-with-ai\/"}],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/posts\/35978","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/comments?post=35978"}],"version-history":[{"count":3,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/posts\/35978\/revisions"}],"predecessor-version":[{"id":39367,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/posts\/35978\/revisions\/39367"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/media\/35979"}],"wp:attachment":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/media?parent=35978"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/categories?post=35978"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/tags?post=35978"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}