Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.04534 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915373459177472 |
|---|---|
| author | Dagtas, Selimhan Cakmak, Mert Can Agarwal, Nitin |
| author_facet | Dagtas, Selimhan Cakmak, Mert Can Agarwal, Nitin |
| contents | Short-form video platforms such as YouTube Shorts increasingly shape how information is consumed, yet the effects of engagement-driven algorithms on content exposure remain poorly understood. This study investigates how different viewing behaviors, including fast scrolling or skipping, influence the relevance and topical continuity of recommended videos. Using a dataset of over 404,000 videos, we simulate viewer interactions across both broader geopolitical themes and more narrowly focused conflicts, including topics related to Russia, China, the Russia-Ukraine War, and the South China Sea dispute. We assess how relevance shifts across recommendation chains under varying watch-time conditions, using GPT-4o to evaluate semantic alignment between videos. Our analysis reveals patterns of amplification, drift, and topic generalization, with significant implications for content diversity and platform accountability. By bridging perspectives from computer science, media studies, and political communication, this work contributes a multidisciplinary understanding of how engagement cues influence algorithmic pathways in short-form content ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04534 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating User Watch-Time to Investigate Bias in YouTube Shorts Recommendations Dagtas, Selimhan Cakmak, Mert Can Agarwal, Nitin Social and Information Networks Short-form video platforms such as YouTube Shorts increasingly shape how information is consumed, yet the effects of engagement-driven algorithms on content exposure remain poorly understood. This study investigates how different viewing behaviors, including fast scrolling or skipping, influence the relevance and topical continuity of recommended videos. Using a dataset of over 404,000 videos, we simulate viewer interactions across both broader geopolitical themes and more narrowly focused conflicts, including topics related to Russia, China, the Russia-Ukraine War, and the South China Sea dispute. We assess how relevance shifts across recommendation chains under varying watch-time conditions, using GPT-4o to evaluate semantic alignment between videos. Our analysis reveals patterns of amplification, drift, and topic generalization, with significant implications for content diversity and platform accountability. By bridging perspectives from computer science, media studies, and political communication, this work contributes a multidisciplinary understanding of how engagement cues influence algorithmic pathways in short-form content ecosystems. |
| title | Simulating User Watch-Time to Investigate Bias in YouTube Shorts Recommendations |
| topic | Social and Information Networks |
| url | https://arxiv.org/abs/2507.04534 |