Online review has become an important source of information for user before purchasing the product. Customer reviews are a form of customer feedback on electronic commerce and online shopping sites. The product lifetime is divided into three consecutive stages namely, early, majority and laggards. Product reviews contain useful opinion, comments and feedback towards their product. In the proposed work early reviews of product are using a machine learning algorithm followed by frequency based ranking and correlation based ranking. In Frequency based ranking, that extracts the positive review or positive feedback about the particular product and to give a frequency score. Based on frequency score and using correlation based ranking, to find the product sale. Finally, Aggregate positive review response and negative review response from the above ranking method to get a feedback. Feedback means, whether the product is trendy or non-trendy.
Published In : IJCSN Journal Volume 8, Issue 3
Date of Publication : June 2019
Pages : 235-238
Figures :02
Tables : 01
Cincy Raju :
is pursuing her Mtech degree on CSE at APJ Abdul Kalam Technological University. Her research interest are in image processing, data mining, Machine learning.
Deepa Rajan S :
is working as Assistant Professor in Computer Science and Engineering Department. She has 11 years' experience in teaching. Her research interests focuses on Data Security, Image Processing.
Dr. Radhakrishnan B :
is working as the Head of CSE department. He has more than 14 years experience in teaching and has published papers on data mining and image processing. His research interests include image processing, data mining, image mining.
Machine learning, Early reviewer, Early reviews, Multilayer perceptron
The online review's for a product has become an important source of information and get the details about it from the buyer before purchasing or ordering the product. The Product's review is being collected from online shopping site's and reviews contain useful opinion, comments and feedback towards their product. The feedback is predicted using a multilayer perceptron followed by frequency based ranking and correlation based ranking. Feedback means whether the product is trendy or non-trendy.
[1] Venkata Rajeev P and SmrithiRekhaV, Recommending Products to Customers using Opinion Mining of Online Product Reviews and Features. [2] Anindya Ghoseand Panagiotis G. Ipeirotis, Designing Novel Review Ranking Systems: Predicting Usefulness and Impact of Reviews.
[3] Jawad Khan And Byeong Soo Jeong, Summarizing Customer Review Based On Product Feature and Opinion. [4] Wiltrud Kessler, Roman Klinger, and Jonas Kuhn, Towards Opinion Mining from Reviews for the Prediction of Product Rankings. [5] Taysir Hassan A. Soliman and Mostafa A. Elmasry, Utilizing Support Vector Machines in Mining Online Customer Reviews.
