{"id":49,"date":"2024-04-17T11:54:02","date_gmt":"2024-04-17T11:54:02","guid":{"rendered":"https:\/\/www.danielgoralczyk.com\/?page_id=49"},"modified":"2024-11-20T12:42:30","modified_gmt":"2024-11-20T12:42:30","slug":"thesis","status":"publish","type":"page","link":"https:\/\/www.danielgoralczyk.com\/de\/thesis\/","title":{"rendered":"Masterarbeit"},"content":{"rendered":"<p class=\"wp-block-paragraph\">Titel: <strong>Navigating Ideological Impact: Exploring Negativity Bias on YouTube<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><br>Mein Abschlussprojekt an der Universit\u00e4t Konstanz gipfelte in der Erstellung einer Masterarbeit \u00fcber die YouTube-Inhalte, die von US-Senatoren ver\u00f6ffentlicht werden. Diese Arbeit, die mit der Note 1,3 bewertet wurde, erm\u00f6glichte es mir, meine Expertise in Web Scraping, Natural Language Processing (NLP) und \u00fcberwachten maschinellen Lernverfahren zu vertiefen. Mithilfe von R und Python sammelte, analysierte und visualisierte ich die Korrelation zwischen Sentiment und Zuschauerzahlen von YouTube-Videos. Die Thesis ist auf Anfrage verf\u00fcgbar, und der Code f\u00fcr das Projekt ist in einem GitHub-Repository zu finden. <a data-type=\"link\" data-id=\"https:\/\/github.com\/Daniel-Goralczyk\/MA-thesis\" href=\"https:\/\/github.com\/Daniel-Goralczyk\/MA-thesis\">Hier<\/a>.<\/p>\n\n\n\n<div style=\"height:25px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"has-text-align-left wp-block-paragraph\"><strong>Zusammenfassung (Auf Englisch):<\/strong><br>In modern politics, social media has become an indispensable tool for politicians to share their opinions and engage with their constituents. Across disciplines, there is a well-documented negativity bias in the human psyche, meaning that negative information is prioritized in our cognitive processes. In response to the negativity bias, this study delves into the underexplored terrain of YouTube to investigate how U.S. senators employ negativity to broaden their audience. With YouTube\u2019s reputation as a space for diverse opinions, this research also scrutinizes the impact of ideological factors on video views. Employing an innovative approach, a comprehensive dataset of 44,100 video captions from current U.S. senators is collected and subjected to sentiment analysis using the RoBERTa neural language model. Through a linear mixed-effects model, the results suggest that senator videos containing more negative discourse increase viewership, a trend that persists even after controlling for individual characteristics. However, conclusive evidence regarding the definitive impact of ideological factors on baseline viewership remains elusive.<\/p>\n\n\n\n<div style=\"height:25px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity custom-separator\"\/>\n\n\n\n<div style=\"height:25px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Obwohl der Code im GitHub-Repository zu finden ist, war der Weg von komplexen Herausforderungen und wertvollen Lernerfahrungen gepr\u00e4gt. Eine bemerkenswerte Leistung war die Entwicklung von R Markdown-Dateien, die verschiedene Schritte des Projekts detailliert beschreiben. Die erste Seite skizziert den Prozess der Sammlung von YouTube-Untertiteln f\u00fcr eine gegebene Liste von Videos. Ich entwickelte ein Skript, um einen Browser zu automatisieren, der systematisch eine Liste von URLs durchlief und verf\u00fcgbare Untertitel herunterlud. Dieses Vorgehen f\u00fchrte zur Ansammlung von 44.100 Textdateien, die jeweils einem Video entsprechen. Das \u00dcberwinden von Hindernissen, wie dem Umgang mit Pop-ups und Werbung w\u00e4hrend des Web Scraping, stellte eine erhebliche Herausforderung dar. Eine besonders lohnende Errungenschaft war die erfolgreiche Implementierung einer Ad-Blocker-Funktionalit\u00e4t in meinen automatisierten Browser.<\/p>\n\n\n\n<div style=\"height:15px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Scraping Data with RSelenium<\/strong> (R): <a href=\"https:\/\/www.danielgoralczyk.com\/de\/thesis\/data-collection-rselenium\/\" data-type=\"link\" data-id=\"https:\/\/www.danielgoralczyk.com\/thesis\/data-collection-rselenium\/\">Link<\/a>.<\/li>\n\n\n\n<li><strong>Replication of Figures<\/strong> (R): <a href=\"https:\/\/www.danielgoralczyk.com\/de\/thesis\/thesis-replication-of-figures\/\" data-type=\"page\" data-id=\"726\">Link<\/a>.<\/li>\n\n\n\n<li><strong>Replication of Tables <\/strong>(R): <a href=\"https:\/\/www.danielgoralczyk.com\/de\/thesis\/thesis-replication-of-tables\/\" data-type=\"page\" data-id=\"729\">Link<\/a>.<\/li>\n<\/ol>","protected":false},"excerpt":{"rendered":"<p>Title: Navigating Ideological Impact: Exploring Negativity Bias on YouTube My final project at the University of Konstanz culminated in the crafting of a master&#8217;s thesis regarding the YouTube content posted by U.S. Senators. This work, which received a high grade (1.3), allowed me to develop expertise in web scraping, Natural Language Processing (NLP) techniques, and [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-49","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/pages\/49","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/comments?post=49"}],"version-history":[{"count":9,"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/pages\/49\/revisions"}],"predecessor-version":[{"id":1326,"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/pages\/49\/revisions\/1326"}],"wp:attachment":[{"href":"https:\/\/www.danielgoralczyk.com\/de\/wp-json\/wp\/v2\/media?parent=49"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}