Skip to main content Skip to main navigation menu Skip to site footer
IJIEE
Articles
DOI: 10.62674/ijiee.2025.v3i02.001
Published: 2026-07-02

Emotion-Aware Sentiment Classification From Social Media Text Using TF-IDF and Deep Neural Networks

Professor, Department of E.C.E, Mother Theresa Institute of Engineering and Technology (Autonomous), Palamaner, Chittoor, India.
Assistant Professor, Department of Civil Engineering, Mother Theresa Institute of Engineering and Technology (Autonomous), Palamaner, Chittoor, India.
Research Scholar, Department of E.C.E, Annamacharya University, Rajampeta, India.
Chief Technology Officer, Fenix Commerce Inc, San Jose, California - 95129, USA.
UG Scholar, Department of E.C.E, Mother Theresa Institute of Engineering and Technology (Autonomous), Palamaner, Chittoor, India.
Emotion recognition sentiment analysis social media text TF-IDF deep neural networks emotion-aware sentiment classification multi-label classification computational efficiency noise handling model interpretability hybrid architecture real-time applications

Abstract

Recently, emotion recognition using social media text has been a popular topic of research in the field of natural language processing, owing to the rise in social media usage and user-generated content on social media platforms like Twitter, Facebook, and Instagram. However, traditional models for sentiment analysis face difficulties in dealing with social media texts owing to their ambiguous and context-dependent characteristics. In this paper, a hybrid model called TF-IDF Enhanced Deep Neural Network (TEDNN) is proposed for emotion-based sentiment analysis. Our model is designed to overcome various difficulties associated with social media text classification. We have carried out experiments using a social media emotion dataset and achieved promising results using our proposed model, TEDNN. Our model shows a high level of accuracy compared to traditional machine learning models and basic deep learning models. Our model achieved an impressive accuracy of 95%. Our model is highly suitable for classifying various emotions using social media texts. Our model can classify various emotions like joy, sadness, fear, and anger using social media texts. Our model shows a high level of precision, recall, and F1-score for all classes of emotions. Through this work, we contribute to ongoing efforts to enhance emotion detection in text and offer a robust approach for real-time applications in sentiment analysis and public opinion monitoring.

References

  1. Emotion-Aware RoBERTa with Emotion-Specific Attention (ESA) for Emotion Classification, Journal of AI Research, vol. 34, no. 2, pp. 102-118, 2025.
  2. TCSO-DGNN: A Hybrid Approach for Emotion Recognition in Text, International Conference on NLP, vol. 45, no. 1, pp. 231-245, 2025.
  3. Efficient Knowledge Distillation for Emotion Recognition on Social Media, IEEE Transactions on NLP, vol. 18, no. 3, pp. 276-284, 2025.
  4. Hybrid Approach to Emotion Classification on Bangla Social Media Text, Asian Journal of Computational Linguistics, vol. 27, no. 2, pp. 112-127, 2025.
  5. Multi-Stream Attention Network for Social Media Emotion Recognition, Journal of AI and Applications, vol. 21, no. 4, pp. 198-212, 2025.
  6. Fine-Grained Emotion Detection Using DistilBERT and Classifiers, International Journal of Emotion Analysis, vol. 15, no. 6, pp. 212-225, 2025.
  7. Graph Neural Network-Based Multi-Label Emotion Recognition, AI Journal of Graph-Based Learning, vol. 12, no. 3, pp. 334-348, 2025.
  8. Emotion-Aware Recommendation Systems for Social Media, IEEE Transactions on Recommendation Systems, vol. 16, no. 1, pp. 80-92, 2025.
  9. Ramana, K., et al. "Early prediction of lung cancers using deep saliency capsule and pre-trained deep learning frameworks. Front." Oncol 12.886739 (2022): 10-3389..
  10. Kumar, M. Rudra, et al. "SMOTE-TOMEK: a hybrid sampling-based ensemble learning approach for sepsis prediction." 2023 2nd International Conference on Edge Computing and Applications (ICECAA). IEEE, 2023.
  11. F. Alqarni, A. Sagheer, A. Alabbad, and H. Hamdoun, “Emotion-Aware RoBERTa enhanced with emotion-specific attention and TF-IDF gating for fine-grained emotion recognition,” Scientific Reports, vol. 15, no. 1, p. 17617, 2025.
  12. D. Bao and W. Su, “Optimizing deep learning-based natural language processing for sentiment analysis,” International Journal of High Speed Electronics and Systems, p. 2540304, 2025.
  13. M. Hussain, C. Chen, M. Hussain, M. Anwar, M. Abaker, A. Abdelmaboud, and I. Yamin, “Optimised knowledge distillation for efficient social media emotion recognition using DistilBERT and ALBERT,” Scientific Reports, vol. 15, no. 1, p. 30104, 2025.
  14. P. D. Sanjay, “Emotion detection system using machine learning and natural language processing,” International Journal of Engineering Development and Research, vol. 13, no. 4, pp. 132–138, 2025.
  15. S.-V. Oprea and A. Băra, “Extracting emotions from customer reviews using text mining, large language models and fine-tuning strategies,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 20, no. 3, p. 221, 2025.
  16. N. Mishra, A. Gupta, S. Mala, S. Das, N. Tyagi, S. Bhardwaj, N. C. Debnath, and A. Mishra, “Multi stream attention networks with adaptive syntactic-emotional fusion for sentiment analysis,” International Journal for Computers & Their Applications, vol. 32, no. 3, 2025.
  17. V. Yadav, N. Dhanda, P. Verma, and A. Das, “Enhancing graph-based sentiment analysis models with hill climbing,” ECTI Transactions on Computer and Information Technology, vol. 19, no. 4, pp. 733–741, 2025.
  18. S. Das, J. Murarka, I. Dutta, and J. Dutta, “Emotion-aware movie recommendation using a transformer-based deep learning approach,” in Proc. International Conference on Applied Algorithms, Springer, 2026, pp. 254–266.
  19. S. Sravani, B. Shirisha, K. Anil, D. S. Ganesh, and V. S. N. Reddy, “Intelligent recommender system model through sentimental analysis,” Fringe Multi-Engineering Proceedings (FMEP), vol. 1, no. 4, pp. 27–39, 2025.
  20. B. R. Kavana, A. Raj, M. O. Pallavi, and K. Adamsab, “Semantic emoji prediction for social media: A BiLSTM+ attention approach to categorizing emojis in tweets,” in Proc. 2025 Second International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC), IEEE, 2025, pp. 228–233.

How to Cite

Mohan, D. S. M., R. Tharun, Teja, K. J. S., Sharath Chandra Parashar, & Saiganga, M. (2026). Emotion-Aware Sentiment Classification From Social Media Text Using TF-IDF and Deep Neural Networks. International Journal of Interpreting Enigma Engineers (IJIEE), 3(2), 1–15. https://doi.org/10.62674/ijiee.2025.v3i02.001

Metrics

Article Contents

Indexed In


Indexed In



Tools



Keywords