Skip to content
DraconiticResearch
Search Sources API
190,851 studies31 sourcesUpdated 50 min ago
Peer-reviewedCC BY 4.0PLOS One

Sentiment classification optimization based on improved Senti-BERT and BiLSTM-Attention

  • Jie Zhang1
  • Jianbang Liu2
  • Zhaosheng Xu
  1. 1Faculty of Mathematics and Computer, Xinyu University, Xinyu, China
  2. 2Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Shah Alam, Malaysia
Open at sourcePDFDOICite

Abstract

This study focuses on the problem of insufficient accuracy in sentiment classification in complex texts and multimodal scenarios. A sentiment classification optimization method is proposed, which integrates a bidirectional encoder representation Transformer model for sentiment analysis (Senti-BERT)and a bidirectional Long Short-Term Memory with Attention (BiLSTM-Attention). Firstly, the Senti-BERT layer is introduced to optimize the generation of word vectors by introducing an emotion dictionary leading mechanism, and a dynamic weighting strategy is adopted to fuse multi-modal features such as text, emoticons, and images. Subsequently, the hierarchical attention mechanism of BiLSTM-Attention structure is used to enhance contextual modeling. Finally, the stacking method is adopted to integrate the advantages of multiple models. The experimental results show that this method performs well in multiple dimensions. This optimization method achieved an F1 score of 84.6% in verb sentiment word recognition and 90.1% in adjective recognition, which is 4.8% higher than the bidirectional encoder representation Transformer. The full modal fusion results in a classification accuracy of 89.4%, and the English accuracy exceeds 90% in cross language tasks. The accuracy of emotion segment localization using dynamic weight attention mechanism reaches 90%. The quantization model maintains a low latency of 92ms under 10000QPS concurrency, and the Stacking strategy increases the AUC value to 0.943. The research provides a high-precision solution for social media sentiment analysis through innovative multi-level architecture design.

Related

  1. IoT-enabled smart home activity classification using BiLSTM and attention mechanisms
    Sasmita Kumari Pradhan, Suryakanth V. Gangashetty
    PLOS OnePeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationNeurosciencePLOS
  2. A multi-attention mechanism-improved ResNet18 approach for lithology identification and classification
    Yan Zhang, Fan Zhang, Jiaming Li +2
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceGeology & geochemistryPLOSPMC
  3. An attention-enhanced hybrid CNN-BiLSTM framework for multiclass epileptic seizure recognition using EEG signals.
    Bobbinpreet Kaur, Sheenam Middha, Aleem Ali +3
    Frontiers in computational neurosciencePeer-reviewedCC BYFull textNeuroscienceEurope PMC
  4. Dynamic hypernode injection and graph attention fusion for multimodal sentiment analysis of behavioral signals
    Wenfei Cao, Jian Xu, Yinghao Li +3
    PLOS OnePeer-reviewedCC BY 4.0Full textBioinformatics & computational biologyNeurosciencePLOS
  5. Attention-LSTM Network for Improved Hysteresis Compensation of a Single-Port Surgical Robot
    Xiaohang Zhang, Di Wu, Matthias Tummers +1
    IEEE Transactions on Medical Robotics and BionicsPeer-reviewedLicence Ouverte 2.0Full textSystems & synthetic biologyObstetrics, gynaecology & paediatricsHAL

Cite

BibTeXRIS
BibTeX
@article{zhang2026sentiment,
  title = {{Sentiment classification optimization based on improved Senti-BERT and BiLSTM-Attention}},
  author = {Jie Zhang and Jianbang Liu and Zhaosheng Xu},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0358103},
  url = {https://doi.org/10.1371/journal.pone.0358103},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Sentiment classification optimization based on improved Senti-BERT and BiLSTM-Attention
AU  - Jie Zhang
AU  - Jianbang Liu
AU  - Zhaosheng Xu
PY  - 2026
DA  - 2026/09/15
JO  - PLOS One
DO  - 10.1371/journal.pone.0358103
UR  - https://doi.org/10.1371/journal.pone.0358103
AB  - This study focuses on the problem of insufficient accuracy in sentiment classification in complex texts and multimodal scenarios. A sentiment classification optimization method is proposed, which integrates a bidirectional encoder representation Transformer model for sentiment analysis (Senti-BERT)and a bidirectional Long Short-Term Memory with Attention (BiLSTM-Attention). Firstly, the Senti-BERT layer is introduced to optimize the generation of word vectors by introducing an emotion dictionary leading mechanism, and a dynamic weighting strategy is adopted to fuse multi-modal features such as text, emoticons, and images. Subsequently, the hierarchical attention mechanism of BiLSTM-Attention structure is used to enhance contextual modeling. Finally, the stacking method is adopted to integrate the advantages of multiple models. The experimental results show that this method performs well in multiple dimensions. This optimization method achieved an F1 score of 84.6% in verb sentiment word recognition and 90.1% in adjective recognition, which is 4.8% higher than the bidirectional encoder representation Transformer. The full modal fusion results in a classification accuracy of 89.4%, and the English accuracy exceeds 90% in cross language tasks. The accuracy of emotion segment localization using dynamic weight attention mechanism reaches 90%. The quantization model maintains a low latency of 92ms under 10000QPS concurrency, and the Stacking strategy increases the AUC value to 0.943. The research provides a high-precision solution for social media sentiment analysis through innovative multi-level architecture design.
SN  - 1932-6203
ER  -