Abstrakt

Expressive Sentiment Analysis of Product Reviews Using Opinion Mining

Neha A. Kandalkar, Avinash P. Wadhe

Now a days posting reviews on products is one of the popular way for expressing opinions and grievances toward the products brought or services received. By making Analysis of those number of reviews available would produce useful as well as actionable knowledge that could be of economic values to vendors and other interested parties. From this the problem of mining reviews for product and predicting the sales performance are tackled. Currently, there are many challenges in translating human affect into explicit representations. The current and sentiment analysis algorithms uses simple terms to express opinions about a product or particular service. But the cultural factors, traditional linguistic barriors and differing contexts make it extremely difficult to turn a string of written text into a simple pro or con sentiments. The research in the field started with sentiment and subjectivity classification, which treated the problem as a text classification problem. Sentiment classification classifies whether product reviews or sentence expresses a positive or negative opinion. Subjectivity classification determines whether a sentence is subjective or objective. Many real-life applications, however, require more detailed analysis because users often want to know the subject of opinions. The present work focuses on the categorization of a plain input text to inform a Text To Speech system about the most appropriate sentiment to automatically synthesize expressive speech at the sentence level. In addition to this reviews are also evaluated using Text To Speech System with other language and consider a temporal analysis for the evolution of conversation. Text-to-speech system converts normal language text into speech.