Customer Review Rating Analysis Using Opinion Mining
K. Sowmya1, K. Monika2, M. Radha3, V. Vijay Kumar4
1K. Sowmya, Pursuing B.Tech, Department of Computer Science and Engineering at Koneru Lakshmaiah Educational.
2K. Monika, Pursuing B.Tech, Department of Computer Science and Engineering at Koneru Lakshmaiah Educational Foundation.
3M. Radha, M. Tech, Assistant Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Educational Foundation
4V. Vijay Kumar, M. Tech, Assistant Professor, Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2444-2447 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5644058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The customer ratings and reviews is very important to the service providers. The customer rating will act as a feedback to the service provider. Sometimes, the customer may give the good review but he may give the bad rating to the service. So, the service provider will be in a confusion. So, we should predict the rating with the help of customer review. It can be done with the help of optional mining. We used logistic regression, Naive Bayes, SVM algorithms. We applied these algorithms on the data set containing of 1500 reviews and ratings of the customer. When we see above three algorithms logistic regression is giving 80.82% accuracy, Naive Bayes is giving 67.6% accuracy, where asSVM is giving 80.80% accuracy. When we compare the above classification algorithms accuracy logistic regression and SVM are having good accuracy and better performance.
Keyword: Opinion Mining, Stop Words, Reviews, Positive Words, Negative Words.
Scope of the Article: Data Mining