Review comments from digital platform such as Facebook, Twitter and YouTube used for identification of emotional tones from text. Nowadays, reviews are posted in different languages such as English, French, Chinese, and Indian regional languages such as Tamil, Telegu, and Hindi. Identification of emotional tones from text written in Indian regional language is challenging. During the translation of the regional language to the English language for sentiment analysis, lexical and pragmatic ambiguity are the major problem. The above problem arises due to dialects in language such as regional, standard, and social dialects. In this paper, dialect-based ambiguity problems solve through proposed Hybrid optimized deep learning transformer Models like M-BERT, M-Roberta, and M-XLM-Roberta for Tamil language dialects recognise and classified. The proposed algorithms provide better sentimental analysis after Hybrid optimization due to adaptation mechanisms, dynamic changes in the parameters and strategies in fine-tuning the search. The proposed Hybrid optimized algorithms perform better than existing algorithms such as SVM, Naïve Bayes, and LSTM with an accuracy of 95%.
Keywords
NLP, LSTM, Dialect, Lexical Ambiguity, Hyperparameter, Fine Tuning.
M. Sangeetha and K. Nimala, “Exploration of Sentiment Analysis Techniques on a Multilingual Dataset Dealing with Tamil-English reviews,”2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Jan. 2022, doi:10.1109/accai53970.2022.9752612.
P. Kannadaguli, “A Code-Diverse Kannada-English Dataset For NLP Based Sentiment Analysis Applications,” 2021 Sixth International Conference on Image Information Processing (ICIIP), Nov. 2021, doi: 10.1109/iciip53038.2021.9702548.
R. Subha, A. Haldorai, and A. Ramu, “An Optimal Approach to Enhance Context Aware Description Administration Service for Cloud Robots in a Deep Learning Environment,” Wireless Personal Communications, vol. 117, no. 4, pp. 3343–3358, Feb. 2021, doi: 10.1007/s11277-021-08073-3.
J. Li, M. Ott, C. Cardie and E. Hovy, “Dialect-aware Language Models for Code-Switching,” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, 2019.
S. Wu, Y. Yang, F. Wei, M. Zhou, C. Zhang and G. Zhou, “Bert for dialectal Arabic sentiment analysis,” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 2019.
S. Al-Saqqa and A. Awajan, “The Use of Word2vec Model in Sentiment Analysis,” Proceedings of the 2019 International Conference on Artificial Intelligence, Robotics and Control, Dec. 2019, doi: 10.1145/3388218.3388229.
J. Xu, M. W. Chang, and D. Jurafsky, “Towards dialectal Arabic text classification: Insights from Modern Standard Arabic and Egyptian tweets,” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 2019.
A. Razavi, X. He, S. Upadhyay, L. Li, D. Roth and Y. Li, “Pre-training for dialectal Arabic sentiment analysis: A comparative study,” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 2019.
O. Habimana, Y. Li, R. Li, X. Gu, and G. Yu, “Sentiment analysis using deep learning approaches: an overview,” Science China Information Sciences, vol. 63, no. 1, Dec. 2019, doi: 10.1007/s11432-018-9941-6.
Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of NAACL-HLT2019, Minneapolis, Minnesota, June 2 - June 7, Association for Computational Linguistics, 2019.
H. Tayyar Madabushi, E. Kochkina, and M. Castelle, “Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data,”Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, 2019, doi: 10.18653/v1/d19-5018.
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer and Veselin Stoyanov, “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” 2019, arXiv:1907.11692.
Saptarshi Sengupta, Sanchita Basak and Richard Alan Peters II, “Particle Swarm Optimization: A survey of historical and recent developments with hybridization perspectives” Neural and Evolutionary Computing, 2018, arXiv:1804.05319.
Mihael Petac, Piero Ullio and Mauro Valli, “On velocity-dependent dark matter annihilations in dwarf satellites,” 2018, arXiv:1804.05052.
Yikun Hu, Yuanyuan Zhang, Juanru Li, Hui Wang, Bodong Li and Dawu Gu, “BinMatch: A Semantics-based Hybrid Approach on Binary Code Clone Analysis” 2018, arXiv:1808.06216.
A. Sabetta and I. Tiddi, “Predicting Review Helpfulness through Deep Learning: A Unified Model and Explanations,” In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium, 2018
R. Padmamala and V. Prema, “Sentiment analysis of online Tamil contents using recursive neural network models approach for Tamil language,” 2017 IEEE International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), Aug. 2017, doi: 10.1109/icstm.2017.8089122.
E. Cambria, D. Das, S. Bandyopadhyay, and A. Feraco, “Affective Computing and Sentiment Analysis,” Socio-Affective Computing, pp. 1–10, 2017, doi: 10.1007/978-3-319-55394-8_1.
A. Rosenfeld, S. Schweter and H. Schütze, “Dialect Identification in Social Media Content,” In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 2017.
Acknowledgements
We would like to thank Reviewers for taking the time and effort necessary to review the manuscript. We sincerely appreciate all valuable comments and suggestions, which helped us to improve the quality of the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
The data that support the findings of this study are available from the corresponding author upon reasonable request.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Sangeetha M
Sangeetha M
SRM Institute of Science and Technology, SRM Institute of Science and Technology, Kattankulathur, TamilNadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Sangeetha M and Nimala K, “Unravelling Emotional Tones: A Hybrid Optimized Model for Sentiment Analysis in Tamil Regional Languages”, Journal of Machine and Computing, pp. 114-126, January 2024. doi: 10.53759/7669/jmc202404012.
