Attention-Augmented Hybrid CNN- BiLSTM Architecture for Real-Time Sentiment Classification of Twitter Text

Short, informal text on Twitter has become a major source of public-opinion data, yet extracting dependable sentiment signals from it is challenging because many existing models fail to jointly capture fine-grained word-level cues and broader contextual meaning. This study proposes a hybrid deep-learning framework that combines convolutional feature extraction with a bidirectional recurrent encoder and an attention mechanism to categories tweets as positive, neutral, or negative. Three parallel one-dimensional convolutional (Conv1D) branches first capture local n-gram patterns of varying width, after which a Bidirectional Long Short-Term Memory (BiLSTM) layer models dependencies across the whole sequence in both directions, and an additive attention component then highlights the specific tokens most responsible for the predicted polarity. The processing pipeline further incorporates a Twitter-specific preparation stage that performs emoji-to-text conversion, informal-language normalization, and hash tag decomposition, addressing noise patterns that generic NLP pipelines are not designed to handle. The architecture was evaluated on a curate collection of 50,000 manually annotated tweets spanning several topical domains. It achieved a test accuracy of 87.7% and a weighted F1-score of 0.877, outperforming a TF-IDF/SVM baseline (79.8%), a standalone CNN (85.1%), a single-direction LSTM (83.5%), a BiLSTM without attention (85.5%), and a fine-tuned BERT-base model (86.9%). The proposed model maintained consistent performance across politics-, e-commerce-, and health-related tweet subsets, indicating that the learned representations generalize reasonably well across domains rather than over fitting to a single topic. These findings suggest that combining local feature extraction, bidirectional context modeling, and attention-based token weighting can approach transformer-level accuracy while remaining considerably lighter computationally, making the approach attractive for real-time or resource-constrained deployment. Future work is outlined around integrating transformer-based embeddings, extending the framework to multilingual and code-switched text, and adapting the pipeline for continuous streaming inference.

Sentiment Analysis; Convolutional Neural Network; Bidirectional LSTM; Attention Mechanism; Social Media Text Mining

1. D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” in Proc. ICLR, 2015. [Google Scholar] [Crossref]

2. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186. [Google Scholar] [Crossref]

3. A. Graves, A. Mohamed, and G. Hinton, “Speech recognition with deep recurrent neural networks,” in Proc. IEEE ICASSP, 2013, pp. 6645–6649. [Google Scholar] [Crossref]

4. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [Google Scholar] [Crossref]

5. Y. Kim, “Convolutional neural networks for sentence classification,” in Proc. EMNLP, 2014, pp. 1746–1751. [Google Scholar] [Crossref]

6. classification,” in Proc. AAAI, 2015, pp. 2267–2273. [Google Scholar] [Crossref]

7. B. Liu, “Sentiment analysis and opinion mining,” Synthesis Lectures on Human Language Technologies, vol. 5, no. 1, pp. 1–167, 2012. [Google Scholar] [Crossref]

8. D. Q. Nguyen, T. Vu, and A. T. Nguyen, “BERTweet: A pre-trained language model for English tweets,” in Proc. EMNLP (System Demonstrations), 2020, pp. 9–14. [Google Scholar] [Crossref]

9. J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” in Proc. EMNLP, 2014, pp. 1532–1543. [Google Scholar] [Crossref]

10. P. D. Turney, “Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews,” in Proc. ACL, 2002, pp. 417–424. [Google Scholar] [Crossref]

11. Y. Wang, M. Huang, X. Zhu, and L. Zhao, “Attention-based LSTM for aspect-level sentiment classification,” in Proc. EMNLP, 2016, pp. 606–615. [Google Scholar] [Crossref]

12. Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, and E. Hovy, “Hierarchical attention networks for document classification,” in Proc. NAACL, 2016, pp. 1480–1489. [Google Scholar] [Crossref]

13. C. Zhou, C. Sun, Z. Liu, and F. Lau, “A C-LSTM neural network for text classification,” arXiv:1511.08630, 2015. [Google Scholar] [Crossref]

14. C. Du, H. Sun, J. Wang, Q. Qi, and J. Liao, “Adversarial and domain-aware BERT for cross-domain sentiment analysis,” in Proc. ACL, 2020, pp. 4019–4028. [Google Scholar] [Crossref]

15. L. Zhang, S. Wang, and B. Liu, “Deep learning for sentiment analysis: A survey,” WIREs Data Mining and Knowledge Discovery, vol. 8, no. 4, e1253, 2018. [Google Scholar] [Crossref]

• The Impact of Ownership Structure on Dividend Payout Policy of Listed Plantation Companies in Sri Lanka
• Urban Sustainability in North-East India: A Study through the lens of NER-SDG index
• Performance Assessment of Predictive Forecasting Techniques for Enhancing Hospital Supply Chain Efficiency in Healthcare Logistics
• The Fractured Self in Julian Barnes' Postmodern Fiction: Identity Crisis and Deflation in Metroland and the Sense of an Ending
• Impact of Flood on the Employment, Labour Productivity and Migration of Agricultural Labour in North Bihar