Machine Learning in Recommender Systems for Streaming and Social Networking Platforms

• Autores: Zavaleta Mego, Luis Daniel, Venturo Ramos, Alexander Josué, Torres Villanueva, Marcelino
• Formato: artículo
• Fecha de Publicación: 2026
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/239
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/239; https://doi.org/10.48168/innosoft.s29.a239; https://n2t.net/ark:/42411/s29/a239
• Nivel de acceso: acceso abierto
• Materia: Recommendation systems; Machine learning; Sistemas de recomendación; aprendizaje automático

The use of live streaming platforms and social media has led to a rapid transformation of online content services, which converts a large amount of data for users. This makes it essential to use recommender systems, which rely on machine learning to filter and personalise the content to be displayed. This paper examines the computational methods employed in these systems, with a particular focus on platforms such as Netflix, Spotify, Facebook and Twitter. The research approach incorporated quantitative, qualitative and semiotic factors, resulting in a comprehensive evaluation that incorporates socio-cultural aspects and user experience. Throughout the article, various algorithmic techniques such as collaborative filtering, content-based filtering and hybrid models with deep learning will be evaluated. In the same way, the quality of recommendations and suggestions was evaluated through a combination of qualitative studies on their importance and user satisfaction. Finally, a semiotic and cultural study was carried out to investigate the effect of interfaces and algorithms on consumption practices and cultural identity formation. The findings indicate a shift towards more advanced models, but bring with them new challenges.