Mining of E-commerce Feedback Comments for Multi-dimensional Trust Evaluation
Journal: International Journal of Engineering Research (IJER) (Vol.5, No. 6)Publication Date: 2016-06-01
Authors : Priyanka Kumbhar; Manjushree Mahajan;
Page : 551-554
Keywords : NLP; Topic Modeling; Social network; Recommendation System; Similarity graph; etc.;
Abstract
Generally Electronic commerce or E-commerce applications such as EBay and Amazon use reputation reporting system for trust evaluation where they gather overall feedback ratings from the sellers to compute the reputation or trust score for a seller. The main issue raised with the reputation conduct system is “Excellent reputation” problem where most of feedback ratings are positive leading to high reputation scores for all sellers. In this case it is very difficult for buyers to select the best or accurate seller that he/she can buy from. So in order to overcome this issue we propose an approach called the Comm Trust which evaluates the multidimensional trust for seller by analyzing buyer’s opinions on free text feedback comments. The main idea behind reputation analyzer is an algorithm CommTrust algorithm which is a topic modeling technique proposed for mining the online feedback comments by grouping aspects into dimensions and compute dimension ratings for a seller.
Other Latest Articles
- A Refined Approach for Aspect Based Mining of Reviews using PAMM Model and DCRF Model
- A Review of Maximum Power Point Tracking Techniques for Photovoltaic System
- Recommendation System for Tree Structure Data Based on Fuzzy Preferences and Clustering
- Mapreduce Technique: Review and S.W.O.T Analysis
- Grid Computing: Review and S.W.O.T Analysis
Last modified: 2016-08-08 18:04:12