Analyzing the Impact of Social Media and Influencer Endorsements on Game Revenue using Multiple Linear Regression in the Metaverse

Deshinta Arrova DewiInternational Journal Research on Metaverse 2025 · DOI

Abstract

The gaming industry, particularly within the metaverse, has seen significant transformations driven by the integration of social media, influencer marketing, and player engagement metrics. These elements are crucial in shaping the success and revenue generation of games. This study explores the role of social media mentions and influencer endorsements in influencing game revenue, applying DBSCAN clustering to segment player engagement into distinct groups. By analyzing the "Gaming Trend 2024" dataset, which includes key metrics such as social media mentions, influencer endorsements, in-game purchases, and game revenue, we identify patterns in player behavior that directly impact revenue generation. The DBSCAN clustering method was employed to group players based on their social media interactions and influencer influence, identifying key segments that contribute to game success. The results reveal that certain clusters, characterized by higher social media engagement and influencer endorsements, are associated with increased game revenue. In contrast, other segments showed lower engagement and contributed less to overall revenue. This research provides insights into how targeted marketing strategies, personalized influencer campaigns, and tailored engagement efforts can enhance game revenue in the metaverse.

Introduction

As the gaming industry shifts toward the metaverse—a collective of immersive, interactive virtual environments—traditional marketing models are being disrupted. Developers and marketers face a "black box" problem: they know social media and influencers are important, but they struggle to quantify how these digital echoes translate into actual revenue.

This study addresses the challenge of player segmentation in a complex digital ecosystem. Instead of treating all players as a monolith, the paper seeks to identify distinct behavioral patterns (clusters) that drive financial outcomes. This allows for more surgical precision in marketing spend and community management, moving beyond aggregate metrics to understand the specific drivers of high-value player behavior.

Methodology

The researchers employed a data-mining workflow to uncover latent patterns in player behavior using the "Gaming Trend 2024" dataset. This dataset is a comprehensive archive of gaming metrics, including engagement (Daily Active Users, New Registrations, Session Duration), marketing (Social Media Mentions, Influencer Endorsements), and financial data (In-game Purchases, Total Game Revenue).

The analytical pipeline consisted of several key stages:

  • Preprocessing: The team used StandardScaler to normalize numerical features and One-Hot Encoding for categorical data such as game genre and platform.
  • DBSCAN (Density-Based Spatial Clustering of Applications with Noise): Unlike K-Means, which requires a pre-defined number of clusters, DBSCAN identifies clusters based on the density of data points. This is particularly useful for gaming data, where player behavior often forms non-spherical groups.
  • PCA (Principal Component Analysis): To visualize the high-dimensional dataset, the authors used PCA to reduce the features into two principal components, allowing for a 2D representation of the identified clusters.
  • Statistical Analysis: While the study's framework includes Multiple Linear Regression, the primary focus of the analysis presented here is the interpretation of the characteristics and revenue averages of the resulting clusters.

Key Insights: The "Ripple Effect" of Influence

The analysis revealed several critical aspects of the relationship between social influence and revenue:

  • The "Ripple Effect" of Influence: The data suggests that influencer-driven visibility creates a feedback loop. High influencer activity correlates with higher social media mentions, which in turn drives both player retention and higher-value spending.
  • Revenue is Not Just About Volume: Interestingly, the "high-performing" segment (Cluster 0) isn't necessarily the largest in terms of player count, but it is the most engaged with monetization processes.
  • The "Mid-Tier" Opportunity: Cluster 1 represents a significant "mid-tier" group that generates substantial revenue (nearly as much as the top tier) despite having slightly lower engagement. This suggests that influencer marketing has a broad, stabilizing effect on revenue across multiple segments, not just the "whales."
  • Noise Identification: By using DBSCAN, the authors were able to isolate "noise"—outlier players whose behavior is erratic—ensuring the marketing insights remain focused on representative player types.

Results and Segmentation

The clustering analysis yielded three distinct segments:

  • Cluster 0 (High-Value): Characterized by the highest average revenue, approaching $80,000. This group shows the strongest correlation between social media mentions and spending.
  • Cluster 1 (Mid-Tier): Generated substantial revenue, also just under $80,000. This group is influenced by social media but perhaps less intensely than Cluster 0.
  • Cluster 2 (Underperforming): The lowest average revenue, around $60,000. These players are less influenced by external social factors and influencer endorsements.

The model achieved a Silhouette Score of 0.16. While this indicates some overlap between clusters, it confirms a measurable structure within the data.

Conclusion and Future Work

This research provides practical applications for game developers and marketers in the metaverse, emphasizing the need to leverage clustering insights to optimize marketing strategies. However, the authors acknowledge several areas for improvement:

  • Sentiment Analysis: Future iterations could integrate Natural Language Processing (NLP) to distinguish between positive and negative social media sentiment.
  • Model Robustness: The authors suggest exploring hierarchical clustering or hybrid models to improve cluster separation.
  • Predictive Forecasting: Future work aims to develop models that can forecast revenue trends based on real-time social media and influencer data, moving from descriptive to predictive analytics.

Summary updated

Abstract

The gaming industry, particularly within the metaverse, has seen significant transformations driven by the integration of social media, influencer marketing, and player engagement metrics. These elements are crucial in shaping the success and revenue generation of games. This study explores the role of social media mentions and influencer endorsements in influencing game revenue, applying DBSCAN clustering to segment player engagement into distinct groups. By analyzing the "Gaming Trend 2024" dataset, which includes key metrics such as social media mentions, influencer endorsements, in-game purchases, and game revenue, we identify patterns in player behavior that directly impact revenue generation. The DBSCAN clustering method was employed to group players based on their social media interactions and influencer influence, identifying key segments that contribute to game success. The results reveal that certain clusters, characterized by higher social media engagement and influencer endorsements, are associated with increased game revenue. In contrast, other segments showed lower engagement and contributed less to overall revenue. The clustering analysis highlights the power of social media and influencers in driving player behavior, which in turn drives financial outcomes for game developers. This research provides insights into how targeted marketing strategies, personalized influencer campaigns, and tailored engagement efforts can enhance game revenue. This study offers practical applications for game developers and marketers in the metaverse, emphasizing the need to leverage clustering insights to optimize marketing strategies and increase revenue. Future research could expand on these findings by integrating sentiment analysis of social media mentions, exploring alternative clustering methods like hierarchical clustering, and developing hybrid models that combine clustering with predictive analytics to forecast game revenue trends.
BibTeX
@article{dewi2025analyzing,
  author = {Deshinta Arrova Dewi},
  title = {{Analyzing the Impact of Social Media and Influencer Endorsements on Game Revenue using Multiple Linear Regression in the Metaverse}},
  journal = {International Journal Research on Metaverse.},
  year = {2025},
  doi = {10.47738/ijrm.v2i2.29},
}
Figure