Price Prediction of PFP NFT Based on User Sentiments on Social Media
With blockchain technology and the rise of non-fungible tokens (NFTs), users can securely prove ownership of digital content by tokenizing their creations, allowing digital content trading.
Although many studies have explored factors influencing user transactions, the direct link between user sentiment and NFT prices remains underexamined.
Study Objective and Methodology
This research employs a multi-layer perceptron (MLP) to analyze factors affecting the price of profile picture (PFP) NFTs. It incorporates collectible market indicators, technical indicators, and sentiment indicators from social media posts.
Key Findings
- PFP NFTs show strong correlations with multiple market and sentiment indicators.
- The developed MLP model predicts price fluctuations with accuracies of 81.49% for BAYC and 93.39% for Cryptopunks.
- Stock indices positively influence NFT prices, while rises in cryptocurrency values, interest rates, and discussion volume tend to negatively affect prices.
- Positive and objective sentiment interaction contributes positively to price formation.
The empirical results demonstrate that the proposed MLP model achieved prediction accuracies of 81.49% for BAYC and 93.39% for Cryptopunks.
Stock indices were found to exert a positive influence on NFT prices, whereas increases in cryptocurrency values, interest rates, and discussion volume acted as negative determinants.
By contrast, the interaction of positive and objective sentiment contributed positively to price formation.
Author's summary: The study reveals that combining market data with user sentiment from social media enables reliable prediction of PFP NFT prices, highlighting the significant role of sentiment in digital asset valuation.