vioft2nntf2t|tblJournal|Abstract_paper|0xf4ffe47c22000000308d050001000100 Quality is referred as the degree of excellence that means the expected product or service being considered to achieve desired requirements. Whereas, Quality of Reviews (QoR) relates to the task of determining the quality, efficiency, suitability, or utility of each review by addressing Quality of Product (QoP) and Quality of Service (QoS). It is an essential task of ranking, the reviews based on the quality and efficiency of the reviews given by the users. Whatever the reviews are provided to the particular product or services are from user experiences. The Quality of Reviews (QoR) is one of a kind method that defines how the customer’s standpoint for the service or product that he/she experienced. The main issue while reviewing any product, the reviewer provides his/her opinion in the form of reviews and might be a few of those reviews are malicious spam entries to skew the rating of the product. Also in another case, many times customers provide the reviews which are quite common and that won’t helpful for the buyer to interpret the helpful feedback on their products because of too many formal reviews from distinct customers. Hence, we proposed novel approaches: i) to statistical analyzes the customer reviews on products by Amazon to identify top most useful or helpful reviewers; ii) to analyze the products and its reviews associated for malicious reviews ratings that skewed the overall product ranking. As this is one of the efficient approaches to avoid spam reviewers somehow from reviewing the products. With this, we can use this method for distinguishing between nominal users and spammers. This method helps to quest for helpful reviewers not only to make the product better from best quality reviewers, but also these quality reviewers themselves can able to review future products.
Sumit Kawate, Kailas Patil
Quaid-E-Millath Government College for women, India
Quality of Review, Opinion Mining, Sentiment Analysis, Quality of Product, Quality of Experience
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 1 | 0 | 0 | 5 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 7 , Issue: 2 , Pages: 1390-1401 )
Date of Publication :
January 2017
Page Views :
762
Full Text Views :
6
|