Autore: Gauvin, Stephane
Titolo: Algorithmic analysis of YouTube music comments: measurement and applications
Periodico: Economia della cultura
Anno: 2025 - Fascicolo: 1 - Pagina iniziale: 81 - Pagina finale: 90

Algorithmic sentiment analysis, which automatically detects the emotional tone of textual data, is an important tool for understanding users' opinions. Recent advances in machine learning have greatly improved model accuracy. We show that a carefully trained BERT model outperforms Generative Pretrained Transformers (GPTs) - and humans - in inferring the sentiment of comments left on YouTube music videos, with an almost perfect FI-score of 0.99. We apply this model to a corpus of 700 million English-language comments left on YouTube's Official Artist Channels, showing that inferences are valid and that, counter-intuitively, sentiment towards superstars is lower than the global average.




SICI: 1122-7885(2025)1<81:AAOYMC>2.0.ZU;2-F
Testo completo: https://www.rivisteweb.it/download/article/10.1446/118111
Testo completo alternativo: https://www.rivisteweb.it/doi/10.1446/118111

Esportazione dati in Refworks (solo per utenti abilitati)

Biblioteche ACNP che possiedono il periodico