<![CDATA[The growing demand for culturally immersive experiences in virtual environments has highlighted the importance of integrating narrative-driven content into metaverse design. This study applies a data-driven clustering approach to categorize 2,000 anime titles based on genres, themes, audience demographics, and user engagement metrics such as score, number of users, and member count. Using K-Means clustering and Principal Component Analysis (PCA), five distinct clusters were identified, each reflecting unique narrative typologies and audience preferences. The resulting clusters reveal meaningful thematic patterns: Cluster 0 emphasizes action and adventure with an average score of 8.56 and over 1 million members; Cluster 1 is centered around fantasy and supernatural elements with a dominant Shounen demographic; Cluster 2 comprises psychological and sci-fi anime with high intellectual engagement; Cluster 3 features emotionally resonant titles like romance and slice of life with the highest average score of 8.78; and Cluster 4 presents genre-diverse content with a focus on comedy and school life. PCA visualization confirmed the coherence of these groupings in two-dimensional space, and genre frequency analysis showed that Action, Comedy, and Drama were the most prevalent across the dataset. The findings offer actionable insights for culturally intelligent metaverse development, proposing each genre cluster as a thematic blueprint for designing distinct virtual environments. These results demonstrate how narrative clustering can bridge media analytics with user-centered virtual worldbuilding.]]>
Copyrights © 2025
