In this month’s research spotlight, we highlight recent research from COSMOS that focuses on symbolic content, a study named “Examining the Impact of Symbolic Content on YouTube’s Recommendation System.” This study was published and presented recently at the 2024 International Conference on Complex Networks & their Applications (CNA 2024), which took place from December 10 to 12, 2024, in Istanbul, Turkey.

The study examined how symbolic content (i.e. social, cultural, and political symbols) influences YouTube’s recommendation system, using the 2024 Taiwanese presidential election as a case study. The study analyzed videos that were categorized into “symbol” and “no symbol” groups based on their thumbnails. Key findings showed that content with symbols formed more cohesive communities and maintained better topic relevance, while content without symbols achieved broader reach and higher engagement over time. The research used social network analysis, statistical measurements, and generative AI to evaluate network dynamics, relevance, and user engagement patterns. This work provided insights into algorithmic content distribution and potential biases.