Adaptive Particle Grey Wolf Optimizer with Deep Learning-based Sentiment Analysis on Online Product Reviews

The increasing use of e-commerce websites and social networks is continually generating an immense amount data in various forms, such as text, images or sounds, videos, etc. Sentiment analysis (SA) online product reviews a method identifying the overall sentiment customers about specific service. This study used Natural Language Processing (NLP) Machine Learning (ML) algorithms to identify extract opinions emotions expressed text. Online are often written informal language, slang, dialects, making it difficult for ML models accurately classify sentiments. In addition, misspelled words incorrect grammar can further complicate analysis. recent developments Deep (DL) be accurate classification paper presents Adaptive Particle Grey Wolf Optimizer with Based Analysis (APGWO-DLSA) sentiments reviews. Initially, pre-processing was performed improve quality using word2vec embedding process. For classification, proposed Belief Network (DBN) model. Finally, hyperparameter tuning DBN APGWO algorithm. An extensive experimental demonstrated improved results APGWO-DLSA over other methods, showing maximum accuracy 94.77% 85.31% on Cell Phones And Accessories (CPAA) Amazon Products (AP) datasets.