Aspect-based sentiment analysis on multi-domain reviews through word embedding

• Published in: Journal of intelligent systems 2023-06, Vol.32 (1), p.102092-51
• Main Authors: Venu Gopalachari, Mukkamula, Gupta, Sangeeta, Rakesh, Salakapuri, Jayaram, Dharmana, Venkateswara Rao, Pulipati
• Format: Article
• Language: English
• Subjects: aspect-based sentiment analysis; cold start; Customer satisfaction; Data mining; Domains; Embedding; Information retrieval; Machine learning; Product reviews; Sentiment analysis; Websites; word embedding
• ISSN: 2191-026X; 0334-1860; 2191-026X
• DOI: 10.1515/jisys-2023-0001

The finest resource for consumers to evaluate products is online product reviews, and finding such reviews that are accurate and helpful can be difficult. These reviews may sometimes be corrupted, biased, contradictory, or lacking in detail. This opens the door for customer-focused review analysis methods. A method called “Multi-Domain Keyword Extraction using Word Vectors” aims to streamline the customer experience by giving them reviews from several websites together with in-depth assessments of the evaluations. Using the specific model number of the product, inputs are continuously grabbed from different e-commerce websites. Aspects and key phrases in the reviews are properly identified using machine learning, and the average sentiment for each keyword is calculated using context-based sentiment analysis. To precisely discover the keywords in massive texts, word embedding data will be analyzed by machine learning techniques. A unique methodology developed to locate trustworthy reviews considers several criteria that determine what makes a review credible. The experiments on real-time data sets showed better results compared to the existing traditional models.