EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing sentiment analysis of online comments: a novel approach integrating topic modeling and deep learning

Yan Zhu, Rui Zhou, Gang Chen, Baili Zhang

PeerJ Computer Science · 05.12.2024 · 10 · e2542

DOI: 10.7717/peerj-cs.2542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 05.12.2024. Verfasst von Yan Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Design and Art, Shanghai Dianji University, Shanghai, Shanghai, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Industry-university cooperation and collaborative education project of the Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional statistical learning-based sentiment analysis methods often struggle to effectively handle text relevance and temporality. To overcome these limitations, this paper proposes a novel approach integrating Latent Dirichlet Allocation (LDA), Shuffle-enhanced Real-Valued Non-Volume Preserving (RealNVP), a double-layer bidirectional improved Long Short-Term Memory (DBiLSTM) network, and a multi-head self-attention mechanism for sentiment analysis. LDA is employed to extract latent topics within comment texts, revealing text relevance and providing fine-grained user feedback. Shuffle enhancement is applied to RealNVP to effectively model the distribution of text topic features, enhancing performance while avoiding excessive complexity in model structure and computational overhead. The double-layer bidirectional improved LSTM, through the coupling of forget and input gates, captures the dynamic temporal changes in sentiment with greater flexibility. The multi-head self-attention mechanism enhances the model’s ability to select and focus on key information, thereby more accurately reflecting user experiences. Experimental results on both Chinese and English online comment datasets demonstrate that the proposed integrated model achieves improved topic coherence compared to traditional LDA models, effectively mitigating overfitting. Furthermore, the model outperforms single models and other baselines in sentiment classification tasks, as evidenced by superior accuracy and F1 scores. These results underscore the model’s effectiveness for both Chinese and English sentiment analysis in the context of online comments.

Schlagwörter

Stichwörter der Autor:innen

Double-Layer improved BiLSTMLDARealNVP with ShuffleSentiment analysisTemporalityText relevance

Autor:innen und Institutionen

  • School of Design and Art, Shanghai Dianji University, Shanghai, Shanghai, China.
  • Infrastructure Technology Business Group, Ant Group, Hangzhou, Zhejiang, China.
  • School of Computer Science and Engineering, Southeast University, Nanjing, Jiangsu, China.

Förderung

  • Industry-university cooperation and collaborative education project of the Ministry of Education

Zitieren

APA

Zhu, Y., Zhou, R., Chen, G., & Zhang, B. (2024). Enhancing sentiment analysis of online comments: a novel approach integrating topic modeling and deep learning. PeerJ Computer Science, 10, e2542. https://doi.org/10.7717/peerj-cs.2542

Vancouver

Zhu Y, Zhou R, Chen G, Zhang B. Enhancing sentiment analysis of online comments: a novel approach integrating topic modeling and deep learning. PeerJ Computer Science. 2024;10:e2542. doi:10.7717/peerj-cs.2542

BibTeX
@article{Zhu2024,
  author = {Zhu, Yan and Zhou, Rui and Chen, Gang and Zhang, Baili},
  title = {Enhancing sentiment analysis of online comments: a novel approach integrating topic modeling and deep learning},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2542},
  doi = {10.7717/peerj-cs.2542}
}
Kostenlos starten →