Advancing Sentiment Analysis: A Novel LSTM Framework with Multi-head Attention
Preprint
Abstract
This work proposes an LSTM-based sentiment classification model with multi-head attention mechanism and TF-IDF optimization. Through the integration of TF-IDF feature extraction and multi-head attention, the model significantly improves text sentiment analysis performance. Experimental results on public data sets demonstrate that the new method achieves substantial improvements in the most critical metrics like accuracy, recall, and F1-score compared to baseline models. Specifically, the model achieves an accuracy of 80.28% on the test set, which is improved by about 12% in comparison with standard LSTM models. Ablation experiments also support the necessity and necessity of all modules, in which the impact of multi-head attention is greatest to performance improvement. This research provides a proper approach to sentiment analysis, which can be utilized in public opinion monitoring, product recommendation, etc.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies2025
- A Hybrid Transformer Model for Fake News Detection: Leveraging Bayesian Optimization and Bidirectional Recurrent Unit2025
- Challenges and Innovations in LLM-Powered Fake News Detection: A Synthesis of Approaches and Future Directions2025
- Optimization of Transformer Heart Disease Prediction Model Based on Particle Swarm Optimization Algorithm2024
- Text-Based Emotion Recognition Using Deep Learning ApproachComputational Intelligence and Neuroscience, 2022
- An emotional classification method of Chinese short comment text based on ELECTRAConnection Science, 2021
- Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification2021