Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196678,
        author = {M. Keerthana and K. Deepika and k. Ramakrishna Saketh and S. Ramanjaneyulu},
        title = {Enhancing Product Review Classification Using Quantum Inspired LSTM with Nature-Inspired Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11061-11068},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196678},
        abstract = {Customer reviews have become an important part of the e-commerce platform since they show the feeling of customers, which impacts product development, and competitiveness in the market. The present paper introduces a hybrid deep learning sentiment classification model of product review based on Quantum-Inspired Long Short-Term Memory (QLSTM) network and optimized with the aid of Nature-Inspired Red Deer Optimization (RDO) algorithm. The suggested system applies the contextual learning power of the QLSTM to obtain intricate semantic interdependences of textual data using probabilistic state models motivated by the quantum computing concept. RDO is also used in case of adaptive hyperparameter tuning, which further increases the performance, training speed, and eliminates local minima. The combined model is efficient in the modeling of stronger linguistic patterns and increases the ability to generalize using the method of evolutionary optimization. Benchmark product review datasets evaluated experimentally show that the proposed QLSTM-RDO model yields better classification results than the traditional models including Logistic Regression and Decision Trees, and the standard LSTM networks. The model has enhanced Accuracy, Precision, Recall, and F1-Score and thus can be applied in real-time sentiment-aware recommendation systems. The suggested solution will be very effective in assisting smart e-commerce decision-making as it will yield the accurate insights of customer feedbacks thus enhancing the product strategy as well as customer satisfaction in general.},
        keywords = {Sentiment Analysis, Product Review Classification, Quantum-Inspired LSTM, Red Deer Optimization, Natural Language Processing, Deep Learning.},
        month = {April},
        }