On sentiment recognition mechanism in Black Myth: Wukong player communication on Youtube

As digital games become an important medium for global cultural dissemination, social media platforms have gradually become the primary space for players to express emotions and interact. However, systematic research on emotional expression and communication mechanisms within gaming communities is still relatively weak, particularly in cross-cultural contexts, where the impact of opinion leaders and abnormal interaction behaviors has not been thoroughly explored.

Based on user comments of Black Myth: Wukong on YouTube, this study uses natural language processing (NLP) and social network analysis methods, combined with sentiment analysis and topic modeling (LDA), to analyze 7,604 comments in terms of sentiment distribution, interaction intensity, and identification of potential manipulation behaviors.

The results show that the majority of comments are neutral to positive in sentiment, with discussions focusing on game mechanics and cultural narratives. Some high-engagement comments display signs of opinion guidance or "water army" interference, particularly in discussions on specific topics and storylines.

This study further expands the application of social network theory and sentiment assessment theory in gaming community research, providing theoretical support and practical value for cross-cultural acceptance studies, false interaction detection, and digital community governance.