Influence analysis and price prediction of digital asset social network based on graph neural network

Abstract

As a crucial component of the digital economy, the market price fluctuations of Non-Fungible Tokens (NFTs) are influenced by various factors, making accurate prediction extremely important. This paper leverages a Graph Neural Network (GNN) model to analyze features such as user interaction frequency, user influence, and the popularity of discussion topics within social networks, aiming to predict the volatility of NFT market prices. Experimental results demonstrate that the GNN model achieves a prediction accuracy of 92%, significantly outperforming traditional time series models and linear regression models in key metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R². The study finds that high-influence users and trending discussion topics in social networks are the primary drivers of price volatility. This research not only validates the effectiveness of the GNN model in processing complex social network data but also provides new theoretical insights and practical references for understanding and predicting market behaviors in the digital asset space. The findings offer a solid foundation for the design and optimization of price prediction models in the future digital economy.