Conference Paper2025Cited by 4

Emotion Recognition in Bangla Text: An Ensemble Approach with Data Augmentation using BanglaBERT and MultiBERT

Nabarun Halder, Armun Alam, Jahanggir Hossain Setu, Ashraful Islam, M. Ashraful Amin

2025 17th International Conference on Computer and Automation Engineering (ICCAE)

IEEE, pp. 6-11

DOI: 10.1109/iccae64891.2025.10980496URL

Abstract

Recognizing emotions from text is challenging, but transformers have greatly improved Natural Language Processing (NLP), making emotion detection more accurate. In this study, we performed a multi-class classification to recognize human emotion from Bangla text by developing an ensemble model combining the strengths of two models, BanglaBERT and MultiBERT, thereby enhancing the classification performance. We addressed the class imbalance in the dataset by applying back-translation to the minority classes, doubling their size. We evaluated the ensemble model on original and augmented datasets, comparing its performance with individual models. Results show that the ensemble approach significantly improves performance. Without data augmentation, the ensemble model achieves an accuracy of 0.68, with macro precision, recall, and F1-scores of 0.65, 0.59, and 0.61, respectively. After applying back-translation, accuracy improves to 0.74, with macro precision, recall, and F1-scores rising to 0.74. Especially, the “Anger” and “Disgust” classes showed significant F1-score improvements, rising from 0.48 to 0.70 and 0.39 to 0.66.

Keywords

  • class imbalance
  • data augmentation
  • BanglaBERT
  • back-translation
  • Bengali language
  • multi-class emotion classification
  • Ensemble learning

CCDS Authors

Nabarun Halder
Nabarun Halder

Nabarun Halder

  • Research Assistant, CCDS

Published at

UbiComp, IJCNN, HCII, Pattern Recognition, IEEE Access

Armun Alam
Armun Alam

Armun Alam

  • Alumni, CCDS

  • Master's Student

    McGill University, Canada

  • BSc

    Independent University, Bangladesh (IUB)

Published at

ECCV, Scientific Reports

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, Pattern Recognition, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, Pattern Recognition, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

References

  1. 1.Paul Ekman. (1992). Facial Expressions of Emotion: New Findings, New Questions. Psychological Science, 3(1), 34–38[10.1111/j.1467-9280.1992.tb00253.x]
  2. 2.Erdenebileg Batbaatar, Meijing Li, Keun Ho Ryu. (2019). Semantic-Emotion Neural Network for Emotion Recognition From Text. IEEE Access, 7, 111866–111878[10.1109/access.2019.2934529]
  3. 3.Haji Binali, Chen Wu, Vidyasagar Potdar. (2010). Computational approaches for emotion detection in text. , 172–177[10.1109/dest.2010.5610650]
  4. 4.Jia Guo. (2022). Deep learning approach to text analysis for human emotion detection from big data. Journal of Intelligent Systems, 31(1), 113–126[10.1515/jisys-2022-0001]
  5. 5.Santosh Kumar Bharti, S Varadhaganapathy, Rajeev Kumar Gupta, Prashant Kumar Shukla, Mohamed Bouye, Simon Karanja Hinga, Amena Mahmoud. (2022). Text-Based Emotion Recognition Using Deep Learning Approach. Computational Intelligence and Neuroscience, 2022, 1–8[10.1155/2022/2645381]
  6. 6.Shadi Ibrahim Shaheen, Wassim El-Hajj, Hazem Hajj, Shady Elbassuoni. (2014). Emotion Recognition from Text Based on Automatically Generated Rules. , 383–392[10.1109/icdmw.2014.80]
  7. 7.Amane Sugiyama, Naoki Yoshinaga. (2019). Data augmentation using back-translation for context-aware neural machine translation. , 35–44[10.18653/v1/d19-6504]
  8. 8.Tahmina Akter, Mst. Sharmin Akter, Tanjim Mahmud, Dilshad Islam, Mohammad Shahadat Hossain, Karl Andersson. (2024). Evaluating Machine Learning Methods for Bangla Text Emotion Analysis. , 1–6[10.1109/apcit62007.2024.10673544]
  9. 9.María Lucía Barrón Estrada, Ramón Zataraín Cabada, Raúl Oramas Bustillos. (2019). Emotion Recognition for Education using Sentiment Analysis. Research in Computing Science, 148(5), 71–80[10.13053/rcs-148-5-8]
  10. 10.Asmita De, Sushruta Mishra. (2022). Augmented Intelligence in Mental Health Care: Sentiment Analysis and Emotion Detection with Health Care Perspective. Studies in computational intelligence, 205–235[10.1007/978-981-19-1076-0_12]
  11. 11.Farhan Sadaf, Abdul Muntakim, K. M. Azharul Hasan. (2024). Building an Affective Database for Emotion Detection from Natural Bangla Text. Lecture notes in networks and systems, 621–635[10.1007/978-981-99-8937-9_42]

Cited By

  1. 1.Rabeya Islam Mumu, Tashfia Hossain, Oindrila Saha Badhan, MD Morshed Alam Lipson, Ms. Syeda Shabnam Hasan. (2025). Emotion Recognition in Bengali Text: A Computational Approach for Six Emotions. , 3998–4003[10.1109/iccit68739.2025.11491714]
  2. 2.Md Shohanur Rahman Shohan, Khondoker Muntahin Hassan Ankur, Md Nasit Jakoan, Md Farukuzzaman Khan, Md Ibrahim Abdullah, Md Habibur Rahman. (2025). RBEC: A Dataset for Emotion Detection in Resource-Constrained Bengali Language Using Optimized Transformers and Machine Learning Approaches. , 4891–4896[10.1109/iccit68739.2025.11491758]
  3. 3.MD. Tahidul Islam, Nakib Aman, Md. Abu Johab, Md. Sadikul Islam, Md. Roton Ahmed. (2025). Distinguishing Between Saint(Sadhu) and Common(Cholit): A Bangla BERT Approach to Bengali Language Classification. , 2157–2162[10.1109/iccit68739.2025.11490255]
  4. 4.Aminun Nahar, Md. Ezharul Islam. (2025). Dual-Task Learning with XLM-RoBERTa: A Unified Model for Bangla Emotion and Hate Speech Classification. , 5437–5442[10.1109/iccit68739.2025.11490401]
← All publications