Multi-Attribute Online Decision-Making Driven by Opinion Mining

With the evolution of data mining systems, acquisition timely insights from unstructured text is an organizational demand which gradually increasing. The existing opinion systems have a variety properties, such as ranking products’ features and feature level visualizations; however, organizations require decision-making based upon customer feedback. Therefore, system proposed in this work that ranks reviews on novel schemes with innovative opinion-strength-based feature-level visualization, are tightly coupled to empower users spot imperative product their enormous reviews. Enhancements made at different phases pipeline, ways evaluate review quality, rank visualize summary. target user groups business analysts customers who want explore comments gauge strategies purchase decisions. Finally, evaluated real dataset, usability study conducted for visualization. results demonstrate incorporation can improve process.