International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Automated Emotion Analysis on Twitter Using Machine Learning and Deep Learning

Abstract

Twitter has become a popular platform for expressing emotions and opinions. Emotion analysis can be useful in various fields such as marketing, politics, and healthcare. In this research paper, we propose an automated emotion analysis system using machine learning and deep learning techniques on Twitter data. We collect a large dataset of tweets and annotate them with six basic emotions: happy, sad, angry, surprised, disgusted, and fearful. We then preprocess the data by removing stop words and performing stemming. We extract features from the preprocessed data using techniques such as bag- of-words and TF-IDF. We experiment with several machine learning and deep learning algorithms and compare their performance. Our results show that deep learning algorithms such as LSTM and CNN outperform traditional machine learning algorithms such as SVM and Naive Bayes. Our proposed system achieves an accuracy of 80% in emotion classification, which is higher than the state-of-the-art methods.

Country : India

1 Rahul Bagal2 Aditya Gend3 Jalindar Gaikwad4 Sakshi Ghatage5 Prof. Aparna Thakre

  1. Student, Computer Engineering, Siddhant College of Engineering, Pune, Maharashtra, India
  2. Student, Computer Engineering, Siddhant College of Engineering, Pune, Maharashtra, India
  3. Student, Computer Engineering, Siddhant College of Engineering, Pune, Maharashtra, India
  4. Student, Computer Engineering, Siddhant College of Engineering, Pune, Maharashtra, India
  5. Professor, Siddhant College of Engineering, Pune, Maharashtra, India

IRJIET, Volume 7, Special Issue of ICRTET- 2023 pp. 10-12

IRJIET.ICRTET03

Full Paper
Download

References

  1. Li, X., & Lu, L. (2018). Emotion detection in Chinese social media using deep learning and machine learning. Information Processing & Management, 54(5), 824-839.
  2. Mohammad, S. M., & Kiritchenko, S. (2015). Using hashtags to capture fine emotion categories from tweets. Computational Intelligence, 31(2), 301-333.
  3. Wang, G., Wang, L., & Guo, L. (2019). Emotion classification of Chinese microblog texts based on BERT. Future Internet, 11(6), 130.
  4. Duan, Z., Yan, Y., Chen, Y., & Li, J. (2019). A novel deep learning approach for emotion detection in tweets. Future Generation Computer Systems, 92, 439-447.
  5. Bahuleyan, H., Rajendran, S., & Soman, K. P. (2017). Automated emotion classification using an ensemble of machine learning techniques. Expert Systems with Applications, 78, 146-156.
  6. Chen, T., Zhang, G., & Zhang, J. (2018). A new emotion classification model for tweets based on convolutional neural networks. International Journal of Computer Information Systems and Industrial Management Applications, 10, 14-22.
  7. Yin, Q., Xie, Y., Chen, X., & Yang, J. (2018). Emotion classification for Chinese social media using convolutional neural networks. IEEE Access, 6, 17469-17478.
  8. Zhang, H., Yu, Y., & Shen, Z. (2018). Emotion classification on social media with dual-channel convolutional neural network. Information Sciences, 465, 141-151.
  9. Zhou, Y., Huang, J., & Wang, Y. (2018). An improved emotion classification model for microblog based on deep learning. Journal of Intelligent & Fuzzy Systems, 35(2), 1737-1743.
  10. Li, Z., Li, Y., & Zhang, J. (2019). A novel feature representation model for emotion classification of Chinese microblogs based on transfer learning. IEEE Access, 7, 16890-16900.
  11. Wang, X., Chen, X., & Wang, W. (2020). Emotion classification for short text on social media based on multi-level attention LSTM network. IEEE Access, 8, 13749-13758.
  12. Liu, C., Li, H., Li, L., & Shi, Q. (2019). Attention-based LSTM for emotion detection in tweets. IEEE Access, 7, 42024-42033.
  13. Feng, Y., Zhang, C., & Su, J. (2019). Emotion classification of short texts using long short-term memory and support vector machine. Journal of Intelligent & Fuzzy Systems, 37(3), 4043-4053. 

Copyright @ 2026-2017 IRJIET. All Right Reserved.

Developed by Byzero Technologies