Optimizing long short-term memory hyperparameter for cryptocurrency sentiment analysis with swarm intelligence algorithms

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Comparative analysis optimizes LSTM accuracy in cryptocurrency sentiment analysis, highlighting swarm intelligence techniques.

The PSO-LSTM model achieved the highest accuracy of 86.08% and lowest loss at 0.57, outperforming others.
Results demonstrated that using swarm intelligence algorithms could significantly improve LSTM model performance.
Comparative analysis involved evaluating LSTM models optimized with PSO, ACO, and CSO algorithms based on key metrics.
These findings suggest that optimizing LSTM hyperparameters with PSO can enhance real-time sentiment analysis effectiveness.

Ekachandra et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis optimizes LSTM accuracy in cryptocurrency sentiment analysis, highlighting swarm intelligence techniques.

The PSO-LSTM model achieved the highest accuracy of 86.08% and lowest loss at 0.57, outperforming others.
Results demonstrated that using swarm intelligence algorithms could significantly improve LSTM model performance.
Comparative analysis involved evaluating LSTM models optimized with PSO, ACO, and CSO algorithms based on key metrics.
These findings suggest that optimizing LSTM hyperparameters with PSO can enhance real-time sentiment analysis effectiveness.

Ekachandra et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark