Mining Interesting Aspects of a Product using Aspect-based Opinion Mining from Product Reviews

As the internet and its applications are growing, E-commerce has become one of its rapid applications. Customers of E-commerce were provided with the opportunity to express their opinion about the product on the web as a text in the form of reviews. In the previous studies, mere founding sentiment from reviews was not helpful to get the exact opinion of the review. In this paper, we have used Aspect-Based Opinion Mining to get more interesting aspects of a product’s sentiment from unlabelled textual data. First, noun phrases algorithm was used to get all the aspect term of a review sentence. Secondly, the sentiment algorithm was applied on the result of the noun-phrase algorithm and also applied on adjectives and on adverbs. Finally, using relative importance algorithm important aspects were presented to the user. Our proposed methodology has achieved 77.03% of accuracy compared to previews studies. The proposed methodology can be applied for any product reviews in the form of text without any label, and it does not require any training dataset

Keywords:

Sentiment Analysis , Opinion Mining , Aspect Term , Aspect Based Analysis , Customer Review