Aspect-oriented extraction and sentiment analysis using optimized hybrid deep learning approaches

Aspect-oriented extraction involves the identification and extraction of specific aspects, features, or entities within a piece of text. Traditional methods often struggled with the complexity and variability of language, leading to the exploration of advanced deep learning approaches. In the realm of sentiment analysis, the conventional approaches often fall short when it comes to providing a nuanced understanding of sentiments expressed in textual data. Traditional sentiment analysis models often overlook the specific aspects or entities within the text that contribute to the overall sentiment. This limitation poses a significant challenge for businesses and organizations aiming to gain detailed insights into customer opinions, product reviews, and other forms of user-generated content.In this research, we propose an innovative approach for aspect-oriented extraction and sentiment analysis leveraging optimized hybrid deep learning techniques. Our methodology integrates the powerful capabilities of deep learning models with the efficiency of Reptile Search Optimization. Furthermore, we introduce an advanced sentiment analysis framework employing the state-of-the-art Extreme Gradient Boosting Algorithm. The fusion of these techniques aims to enhance the precision and interpretability of aspect-oriented sentiment analysis. The proposed approach first utilizes deep learning architectures to extract and comprehend diverse aspects within textual data. Through the incorporation of Reptile Search Optimization, we optimize the learning process, ensuring adaptability and improved model generalization across various datasets. Subsequently, the sentiment analysis phase employs the robust Extreme Gradient Boosting Algorithm, known for its effectiveness in handling complex relationships and patterns within data. Our experiments, conducted on diverse datasets, demonstrate the superior performance of the proposed methodology in comparison to traditional approaches. The optimized hybrid deep learning approach, coupled with the Reptile Search Optimization and Extreme Gradient Boosting Algorithm, showcases promising results in accurately capturing nuanced sentiments associated with different aspects. This research contributes to the advancement of aspect-oriented sentiment analysis techniques, offering a comprehensive and efficient solution for understanding sentiment nuances in textual data across various domains. The ResNet 50 and EfficientNet B7 architecture of the modified pre-trained model is proposed for the aspect extraction function. The Reptile Search Optimization based Extreme Gradient Boosting Algorithm (RSO-EGBA) is proposed to analyze and predict customer sentiments. The execution of this study is carried out using python software. It has been observed that the overall accuracy of our proposed method is 99.8%, while that of the other state-of-the-art. The overall accuracy of our proposed method shows an increment of 9–16% from that of the state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.