• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2024, Volume: 17, Issue: 7, Pages: 625-634

Original Article

Deep Learning-Based Aspect Term Extraction for Sentiment Analysis in Hindi

Received Date:01 November 2023, Accepted Date:09 January 2024, Published Date:14 February 2024


Objectives: Aspect terms play a vital role in finalizing the sentiment of a given review. This experimental study aims to improve the aspect term extraction mechanism for Hindi language reviews. Methods: We trained and evaluated a deep learning-based supervised model for aspect term extraction. All experiments are performed on a well-accepted Hindi dataset. A BiLSTM-based attention technique is employed to improve the extraction results. Findings: Our results show better F-score results than many existing supervised methods for aspect term extraction. Accuracy results are outstanding compared to other reported results. Results showed an outstanding 91.27% accuracy and an F–score of 43.16. Novelty: This proposed architecture and the achieved results are a foundational resource for future studies and endeavours in the field.

Keywords: Sentiment analysis, Aspect based sentiment analysis, Aspect term extraction, Deep Learning, Bi LSTM, Indian language, Hindi


  1. Orvieto A, Smith S, Gu A, Fernando A, Gülçehre Ç, Pascanu R, et al. Resurrecting Recurrent Neural Networks for Long Sequences. 2023. Available from: https://doi.org/10.48550/arXiv.2303.06349
  2. Kumar D, Gupta A, Gupta VK, Gupta A. Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches. International Journal on Recent and Innovation Trends in Computing and Communication. 2023;11(5s):118–138. Available from: https://doi.org/10.17762/ijritcc.v11i5s.6636
  3. Bordoloi M, Biswas SK. Sentiment analysis: A survey on design framework, applications and future scopes. Artificial Intelligence Review. 2023;56(11):12505–12560. Available from: https://doi.org/10.1007/s10462-023-10442-2
  4. Shrivash BK, Verma D, Pandey P. An Effective Framework for Sentiment Analysis of Hindi Sentiments Using Deep Learning Technique. Wireless Personal Communications. 2023;132:2097–2110. Available from: https://doi.org/10.1007/s11277-023-10702-y
  5. Pathak A, Kumar S, Roy PP, Kim BG. Aspect-Based Sentiment Analysis in Hindi Language by Ensembling Pre-Trained mBERT Models. Electronics. 2021;10(21):1–15. Available from: https://doi.org/10.3390/electronics10212641
  6. Sahoo C, Wankhade M, Singh BK. Sentiment analysis using deep learning techniques: a comprehensive review. International Journal of Multimedia Information Retrieval. 2023;12(2). Available from: https://doi.org/10.1007/s13735-023-00308-2
  7. Dhasarathan C, Shrestha H. An NLP Based Sentimental Analysis and Prediction: A Dynamic Approach. In: International Conference on Communication, Networks and Computing CNC 2020, Communications in Computer and Information Science. Springer, Singapore. 1502:343–353.
  8. Akhtar MS, Ekbal A, Bhattacharyya P. Aspect based sentiment analysis in Hindi: resource creation and evaluation. In: Proceedings of the tenth international conference on language resources and evaluation (LREC'16). (pp. 2703-2709) European Language Resources Association (ELRA). 2016.
  9. Gandhi H, Attar V. Extracting Aspect Terms using CRF and Bi-LSTM Models. Procedia Computer Science. 2020;167:2486–2495. Available from: https://doi.org/10.1016/j.procs.2020.03.301
  10. Bhattacharya A, Debnath A, Shrivastava M. Enhancing Aspect Extraction for Hindi. In: Proceedings of The 4th Workshop on e-Commerce and NLP. (pp. 140-149) Association for Computational Linguistics. 2021.
  11. Yadav V, Verma P, Katiyar V. Long short term memory (LSTM) model for sentiment analysis in social data for e-commerce products reviews in Hindi languages. International Journal of Information Technology. 2023;15(2):759–772. Available from: https://doi.org/10.1007/s41870-022-01010-y
  12. Rani S, Kumar P. Aspect-based Sentiment Analysis using Dependency Parsing. ACM Transactions on Asian and Low-Resource Language Information Processing. 2021;21(3):1–19. Available from: https://doi.org/10.1145/3485243
  13. Khurana D, Koli A, Khatter K, Singh S. Natural language processing: state of the art, current trends and challenges. Multimedia Tools and Applications. 2023;82(3):3713–3744. Available from: https://doi.org/10.1007/s11042-022-13428-4
  14. Salmony MY, Faridi AR, Masood F. Leveraging attention layer in improving deep learning models performance for sentiment analysis. International Journal of Information Technology. 2023. Available from: https://doi.org/10.1007/s41870-023-01570-7
  15. Garbin C, Zhu X, Marques O. Dropout vs. batch normalization: an empirical study of their impact to deep learning. Multimedia Tools and Applications. 2020;79:12777–12815. Available from: https://doi.org/10.1007/s11042-019-08453-9
  16. Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geoscientific Model Development . 2022;15(14):5481–5487. Available from: https://doi.org/10.5194/gmd-15-5481-2022


© 2024 Gupta & Sharma. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.