期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN:2320-9798
电子版ISSN:2320-9801
出版年度:2015
卷号:3
期号:4
DOI:10.15680/ijircce.2015.0304194
出版社:S&S Publications
摘要:Now a days posting reviews on products is one of the popular way for expressing opinions andgrievances toward the products brought or services received. By making Analysis of those number of reviews availablewould produce useful as well as actionable knowledge that could be of economic values to vendors and other interestedparties. 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 andsentiment analysis algorithms uses simple terms to express opinions about a product or particular service. But thecultural factors, traditional linguistic barriors and differing contexts make it extremely difficult to turn a string ofwritten text into a simple pro or con sentiments. The research in the field started with sentiment and subjectivityclassification, which treated the problem as a text classification problem. Sentiment classification classifies whetherproduct reviews or sentence expresses a positive or negative opinion. Subjectivity classification determines whether asentence is subjective or objective. Many real-life applications, however, require more detailed analysis because usersoften want to know the subject of opinions. The present work focuses on the categorization of a plain input text toinform a Text To Speech system about the most appropriate sentiment to automatically synthesize expressive speech atthe sentence level. In addition to this reviews are also evaluated using Text To Speech System with other language andconsider a temporal analysis for the evolution of conversation. Text-to-speech system converts normal language textinto speech.
关键词:Review mining; Sentiment analysis; Text To Speech; polarity; opinion mining