A Novel Approach to Sentiment Analysis using GMM-Enhanced N-gram LSTM Networks

Authors

  • K. Dhana Sree Devi Department of CSE, GITAM School of Technology, GITAM Deemed to be University, Hyderabad Campus, Telangana, India
  • V. Sireesha Department of CSE, GITAM School of Technology, GITAM Deemed to be University, Hyderabad Campus, Telangana, India
  • C. Sudha Department of CSE, GITAM School of Technology, GITAM Deemed to be University, Hyderabad Campus, Telangana, India
  • Malladi Ravisankar Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur District, Andhra Pradesh, India
  • P. Dileep Kumar Reddy Department of CSE, Narsimha Reddy Engineering College (Autonomous), Secunderabad, Telangana State, India
Volume: 15 | Issue: 3 | Pages: 23068-23073 | June 2025 | https://doi.org/10.48084/etasr.10640

Received: 20 February 2025 | Revised: 11 March 2025 and 26 March 2025 | Accepted: 28 March 2025 | Online: 4 June 2025


Corresponding author: K. Dhana Sree Devi

Abstract

Most e-commerce market platforms are improving their competitive benchmarks with continuously improving AI-based review analysis tools. Today, product review analysis is being prioritized from small to large companies to achieve parallel goals. Working with user text reviews that are coupled with diversifying sentiments, the market is now facing the real challenge of finding a perfect sentiment analysis approach that can meet business needs. This work presents a Gaussian Mixture Model (GMM) tokenizer to perform N-gram analysis on text. The proposed approach was compared with the LSTM baseline classifier on Amazon product reviews, and the experimental results showed that the GMM N-gram LSTM model outperformed the baseline LSTM. The accuracy of the proposed model was 85%, significantly better than the baseline LSTM (77%).

Keywords:

tokenizer, sentiment analysis, text mining, NLP, n-gram, word vector, GMM, LSTM

Downloads

Download data is not yet available.

References

M. D. Devika, C. Sunitha, and A. Ganesh, "Sentiment Analysis: A Comparative Study on Different Approaches," Procedia Computer Science, vol. 87, pp. 44–49, Jan. 2016. DOI: https://doi.org/10.1016/j.procs.2016.05.124

J. Seror, "VADER Natural Language Processing in Market Sentiment Analysis," SSRN Electronic Journal, 2020. DOI: https://doi.org/10.2139/ssrn.3676706

M. T. F. A. Islami, A. R. Barakbah, and T. Harsono, "Social Media Engineering for Issues Feature Extraction using Categorization Knowledge Modelling and Rule-based Sentiment Analysis," JOIV : International Journal on Informatics Visualization, vol. 5, no. 1, pp. 83–93, Mar. 2021. DOI: https://doi.org/10.30630/joiv.5.1.397

S. Poria, E. Cambria, G. Winterstein, and G. B. Huang, "Sentic patterns: Dependency-based rules for concept-level sentiment analysis," Knowledge-Based Systems, vol. 69, pp. 45–63, Oct. 2014. DOI: https://doi.org/10.1016/j.knosys.2014.05.005

B. l. Velammal, "Development of knowledge based sentiment analysis system using lexicon approach on twitter data," International Journal of Knowledge Management Studies, vol. 10, no. 1, pp. 58–68, Jan. 2019. DOI: https://doi.org/10.1504/IJKMS.2019.097125

C. S. Khoo and S. B. Johnkhan, "Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons," Journal of Information Science, vol. 44, no. 4, pp. 491–511, Aug. 2018. DOI: https://doi.org/10.1177/0165551517703514

A. Mudinas, D. Zhang, and M. Levene, "Combining lexicon and learning based approaches for concept-level sentiment analysis," in Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining, New York, NY, USA, May 2012, pp. 1–8. DOI: https://doi.org/10.1145/2346676.2346681

C. Kaushik and A. Mishra, "A Scalable, Lexicon Based Technique for Sentiment Analysis." arXiv, Oct. 08, 2014. DOI: https://doi.org/10.5121/ijfcst.2014.4504

J. Graovac, "A variant of n-gram based language-independent text categorization," Intelligent Data Analysis, vol. 18, no. 4, pp. 677–695, Jul. 2014. DOI: https://doi.org/10.3233/IDA-140663

A. Dey, M. Jenamani, and J. J. Thakkar, "Senti-N-Gram: An n-gram lexicon for sentiment analysis," Expert Systems with Applications, vol. 103, pp. 92–105, Aug. 2018. DOI: https://doi.org/10.1016/j.eswa.2018.03.004

S. Koshy and R. Padmajavalli, "Text Categorization of Multi-Label Documents For Text Mining," International Journal of Data Mining Techniques and Applications, vol. 4, no. 2, pp. 52–58, Dec. 2015. DOI: https://doi.org/10.20894/IJDMTA.102.004.002.001

M. Suzuki and S. Hirasawa, "Text Classification Using the Sum of Frequency Ratios of Word andN-gram Over Categories," IEEJ Transactions on Electronics, Information and Systems, vol. 129, pp. 118–124, Jan. 2009. DOI: https://doi.org/10.1541/ieejeiss.129.118

Q. Zhou, W. Zhou, and S. Wang, "Semantic adaptation network for unsupervised domain adaptation," Neurocomputing, vol. 454, pp. 313–323, Sep. 2021. DOI: https://doi.org/10.1016/j.neucom.2021.05.041

M. Wankhade, A. C. S. Rao, and C. Kulkarni, "A survey on sentiment analysis methods, applications, and challenges," Artificial Intelligence Review, vol. 55, no. 7, pp. 5731–5780, Oct. 2022. DOI: https://doi.org/10.1007/s10462-022-10144-1

P. Sundarreson and S. Kumarapathirage, "SentiGEN: Synthetic Data Generator for Sentiment Analysis," Journal of Computing Theories and Applications, vol. 1, no. 4, pp. 461–477, Apr. 2024. DOI: https://doi.org/10.62411/jcta.10480

A. R. Pathak, M. Pandey, and S. Rautaray, "Topic-level sentiment analysis of social media data using deep learning," Applied Soft Computing, vol. 108, Sep. 2021, Art. no. 107440. DOI: https://doi.org/10.1016/j.asoc.2021.107440

L. Xu and M. I. Jordan, "On Convergence Properties of the EM Algorithm for Gaussian Mixtures," Neural Computation, vol. 8, no. 1, pp. 129–151, Jan. 1996. DOI: https://doi.org/10.1162/neco.1996.8.1.129

O. Cappé and E. Moulines, "On-Line Expectation–Maximization Algorithm for latent Data Models," Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 71, no. 3, pp. 593–613, Jun. 2009. DOI: https://doi.org/10.1111/j.1467-9868.2009.00698.x

J. J. Verbeek, N. Vlassis, and B. Kröse, "Efficient Greedy Learning of Gaussian Mixture Models," Neural Computation, vol. 15, no. 2, pp. 469–485, Feb. 2003. DOI: https://doi.org/10.1162/089976603762553004

B. Gunter, N. Koteyko, and D. Atanasova, "Sentiment Analysis: A Market-Relevant and Reliable Measure of Public Feeling?," International Journal of Market Research, vol. 56, no. 2, pp. 231–247, Mar. 2014. DOI: https://doi.org/10.2501/IJMR-2014-014

C. P. Li, L. H. Guo, and N. Lin, "Value Mining of Product Reviews Based on Sentiment Analysis," Applied Mechanics and Materials, vol. 713–715, pp. 2528–2531, 2015. DOI: https://doi.org/10.4028/www.scientific.net/AMM.713-715.2528

W. He, H. Wu, G. Yan, V. Akula, and J. Shen, "A novel social media competitive analytics framework with sentiment benchmarks," Information & Management, vol. 52, no. 7, pp. 801–812, Nov. 2015. DOI: https://doi.org/10.1016/j.im.2015.04.006

M. El Marrakchi, H. Bensaid, and M. Bellafkih, "Scoring reputation in online social networks," in 2015 10th International Conference on Intelligent Systems: Theories and Applications (SITA), Rabat, Oct. 2015, pp. 1–6. DOI: https://doi.org/10.1109/SITA.2015.7358420

R. Jayasanka, T. Madhushani, E. Marcus, I. Aberathne, and S. Premaratne, "Sentiment analysis for social media," in Information Technology Research Symposium, 2013, vol. 11, Art. no. 22.

M. S. Akhtar, D. Gupta, A. Ekbal, and P. Bhattacharyya, "Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis," Knowledge-Based Systems, vol. 125, pp. 116–135, Jun. 2017. DOI: https://doi.org/10.1016/j.knosys.2017.03.020

P. Patil and P. Yalagi, "Sentiment Analysis Levels and Techniques: A Survey," International Journal of Innovations in Engineering and Technology, vol. 6, no. 4, pp. 523–528, Apr. 2016.

D. I. H. Farias and P. Rosso, "Irony, Sarcasm, and Sentiment Analysis," in Sentiment Analysis in Social Networks, F. A. Pozzi, E. Fersini, E. Messina, and B. Liu, Eds. Boston, MA. USA: Morgan Kaufmann, 2017, pp. 113–128. DOI: https://doi.org/10.1016/B978-0-12-804412-4.00007-3

J. Zhu, H. Wang, B. K. Tsou, and M. Zhu, "Multi-aspect opinion polling from textual reviews," in Proceedings of the 18th ACM conference on Information and knowledge management, Aug. 2009, pp. 1799–1802. DOI: https://doi.org/10.1145/1645953.1646233

D. Vilares, C. Gómez-Rodríguez, and M. A. Alonso, "Universal, unsupervised (rule-based), uncovered sentiment analysis," Knowledge-Based Systems, vol. 118, pp. 45–55, Feb. 2017. DOI: https://doi.org/10.1016/j.knosys.2016.11.014

S. Kumar Singh, P. Verma, and P. Kumar, "Sentiment Analysis Using Machine Learning Techniques on Twitter: A Critical Review," Advances in Mathematics: Scientific Journal, vol. 9, no. 9, pp. 7085–7092, Aug. 2020. DOI: https://doi.org/10.37418/amsj.9.9.58

I. A. Kandhro, S. Z. Jumani, F. Ali, Z. U. Shaikh, M. A. Arain, and A. A. Shaikh, "Performance Analysis of Hyperparameters on a Sentiment Analysis Model," Engineering, Technology & Applied Science Research, vol. 10, no. 4, pp. 6016–6020, Aug. 2020. DOI: https://doi.org/10.48084/etasr.3549

M. R. R. Rana, A. Nawaz, T. Ali, A. M. El-Sherbeeny, and W. Ali, "A BiLSTM-CF and BiGRU-based Deep Sentiment Analysis Model to Explore Customer Reviews for Effective Recommendations," Engineering, Technology & Applied Science Research, vol. 13, no. 5, pp. 11739–11746, Oct. 2023. DOI: https://doi.org/10.48084/etasr.6278

K. D. S. Devi, "dhanasreek/Web_Scrapping." Jan. 03, 2022, [Online]. Available: https://github.com/dhanasreek/Web_Scrapping.

Downloads

How to Cite

[1]
K. D. S. Devi, V. Sireesha, C. Sudha, M. Ravisankar, and P. D. K. Reddy, “A Novel Approach to Sentiment Analysis using GMM-Enhanced N-gram LSTM Networks”, Eng. Technol. Appl. Sci. Res., vol. 15, no. 3, pp. 23068–23073, Jun. 2025.

Metrics

Abstract Views: 182
PDF Downloads: 262

Metrics Information

License

Copyright (c) 2025 K. Dhana Sree Devi, V. Sireesha, C. Sudha, Malladi Ravisankar, P. Dileep Kumar Reddy

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.