In recent times, online shopping has become commonly used method for consumers to make purchases and engage in consumption with the rapid advancement of Internet technology. Enhancing user satisfaction is achievable through sentiment analysis (SA) of the enormous user evaluations found on e-commerce platforms. However, accurately predicting the sentiment orientations of these user reviews remains a challenge due to varying sequence lengths, text arrangements, and intricate logic. Nowadays, sentiment analysis is widely employed to assess customer feedback, which holds great significance in determining a product's success. In the past, people relied on word-of-mouth reviews to judge a product's quality. This practice of sentiment analysis is extensively applied in social media. Natural language processing (NLP) plays a crucial role in deciphering sentiment, also referred to as opinion mining or emotion AI, as it encompasses the collective perception of customers. In this manuscript, a Hamiltonian Deep Neural Networks-based Sentiment Analysis on Product Recommendation System (HDNN-SCOA-SA-PR) is proposed. First, the data are gathered from Amazon Product Reviews dataset. Then the data are pre-processed utilizing adaptive self-guided filtering for space tokenization, Gensim lemmatization, and Snowball stemming. By using Structured Optimal Graph-Based Sparse Feature Extraction, the features are extracted. Extracted features are selected using Single Candidate Optimization Algorithm. Finally, the classification process is done using Hamiltonian deep neural network and classified sentiment analysis as positive, negative, neutral. The proposed HDNN-SCOA-SA-PR method is activated in Python, and the efficiency of the proposed method is analyzed with different metrics, such as accuracy, sensitivity, RoC, precision, error rate, F1-score,computation time. ROC is evaluated and compared to the existing methods, such as sentiment analysis based upon machine learning of online product reviews with term weighting including feature selection (SAPR-FS-ENN), sentiment analysis of product reviews depend upon weighted word embeddings along deep neural networks (SAPR-WWE-DNN), improving sentiment analysis for social media applications utilizing an ensemble deep learning language (ISA-SMA-ECN-PR), respectively.

近年来，随着互联网技术的飞速发展，网上购物已成为消费者购物、消费的常用方式。通过对电子商务平台上大量用户评价进行情感分析（SA）可以提高用户满意度。然而，由于序列长度、文本排列和复杂的逻辑各不相同，准确预测这些用户评论的情感倾向仍然是一个挑战。如今，情感分析被广泛用于评估客户反馈，这对于决定产品的成功具有重要意义。过去，人们依靠口碑来判断产品的质量。这种情感分析实践广泛应用于社交媒体。自然语言处理 (NLP) 在解读情感方面发挥着至关重要的作用，也称为意见挖掘或情感人工智能，因为它涵盖了客户的集体感知。在本手稿中，提出了一种基于哈密顿深度神经网络的产品推荐系统情感分析（HDNN-SCOA-SA-PR）。首先，数据是从亚马逊产品评论数据集中收集的。然后，利用自适应自引导过滤进行空间标记化、Gensim 词形还原和 Snowball 词干提取，对数据进行预处理。通过使用基于结构化最优图的稀疏特征提取来提取特征。使用单候选优化算法选择提取的特征。最后，使用哈密顿深度神经网络完成分类过程，并将情感分析分类为积极、消极、中性。在Python中激活了所提出的HDNN-SCOA-SA-PR方法，并使用不同的指标（例如准确度、灵敏度、RoC、精度、错误率、F1分数、计算时间）分析了所提出方法的效率。 ROC 被评估并与现有方法进行比较，例如基于在线产品评论的机器学习的情感分析，包括特征选择的术语加权（SAPR-FS-ENN），产品评论的情感分析取决于深度神经网络的加权词嵌入(SAPR-WWE-DNN)，分别利用集成深度学习语言 (ISA-SMA-ECN-PR) 改进社交媒体应用程序的情感分析。