The perception of German occupations on YouTube : gender and skill biases in video recommendations

Abstract

"This study investigates the representation of gender and skill biases in YouTube’s video recommendation system for occupations in Germany. Using a dataset of 526,535 synonyms and variants of male, female, and neutral job titles, we analyse recommendations across three occupational domains: computer science, preschool teaching, and food manufacturing. The study’s findings reveal notable patterns, including a higher overlap in recommendations for male and female job titles in female-dominated occupations and a disproportionately negative sentiment in videos associated with neutral job titles for male-dominated fields. A detailed metadata analysis highlights linguistic and educational framing as key factors shaping recommendations, yet it falls short of explaining observed sentiment trends. The results underscore the need for multi-method approaches to address algorithmic bias and suggest practical implications for developers, policymakers, and media literacy advocates. This research contributes to the growing discourse on fairness and inclusivity in algorithmically curated digital environments." (Authors' abstract, BIBB-Doku)