期刊名称:International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN:2347-6710
电子版ISSN:2319-8753
出版年度:2016
卷号:5
期号:2
页码:1415
DOI:10.15680/IJIRSET.2016.0502033
出版社:S&S Publications
摘要:Opinion mining and sentiment analysis is the process of analysing the text about a topic written in anatural language and classify them as positive, negative or neutral based on the humans sentiments, emotions, opinionsexpressed in it. Most of the previous work is in the field of document or sentence level opinion mining. Currently thework is going on to implement this work using aspect level opinion mining. Aspect-level opinion mining is also wellknownas phrase-level (or feature level or word level) opinion mining. This paper proposes an alternative model toimplement aspect-level opinion mining. The model proposed is a syntactic unsupervised approach for explicit aspectsfor achieving aspect level opinion mining. Using this approach, we can extract most important aspects of the productalong with the opinion words describing that aspect. The sheer volume of online reviews makes it difficult for a humanto process and extract all meaningful information in order to make an educated and informed decision. This approachdoes not require any seed word or domain-specific knowledge of the product. The result of the proposed model willshow the extracted aspects from the reviews, various opinion words describing that aspect and its rating. The rating ofaspects will be done with the help of sentiment scores from the lexical resource, SentiWordNet.