Computing Product Rating Using Real-Time Feedback Comments from E-Commerce Portal [ READ ]
Gaurav Kamble, Rohit Athare, Abhishek Kumar, Neha Upadhyay
Different models are used widely used in e-commerce to rate the products on the portal, but the comments are aggregated to compute seller reputation. The “All Good Reputation” problem is very prominent in the current e-commerce rating systems. However, these scores are universal and it is difficult for potential buyers to buy from trustworthy sellers. In this study, based on comments that buyers’ express in the feedback section, this paper proposes CommTrust, for evaluation by mining the feedback comments. The contribution include: (1) This paper proposes a multidimensional trust model for computing user feedback comments; (2) This paper also proposes an Algorithm for Mining Feedback Comments for Dimension Ratings, Combining techniques of NLP, LDA and PLSA. To the best of our knowledge, this study is the pioneer on trust evaluation by mining feedback comments.
Gaurav Kamble, Rohit Athare, Abhishek Kumar, Neha Upadhyay
Different models are used widely used in e-commerce to rate the products on the portal, but the comments are aggregated to compute seller reputation. The “All Good Reputation” problem is very prominent in the current e-commerce rating systems. However, these scores are universal and it is difficult for potential buyers to buy from trustworthy sellers. In this study, based on comments that buyers’ express in the feedback section, this paper proposes CommTrust, for evaluation by mining the feedback comments. The contribution include: (1) This paper proposes a multidimensional trust model for computing user feedback comments; (2) This paper also proposes an Algorithm for Mining Feedback Comments for Dimension Ratings, Combining techniques of NLP, LDA and PLSA. To the best of our knowledge, this study is the pioneer on trust evaluation by mining feedback comments.