Review authenticity verification using supervised learning and reviewer personality traits
Sonu Liza Christopher, H A Rahulnath · 2016
Social media has increasingly promoted users to provide customer feedback on shopping experiences in the form of online product reviews. Many major ecommerce sites are collecting revenue from advertisements of products and creating better shopping experiences for customers with the help of such reviews. The problem of accurately verifying review authenticity steadily grows and can help in making or breaking the good name of a product. Feature engineering performed on the reviews assist in extracting the useful features that help in identifying actual fake reviews. Supervised machine learning algorithms help in classifying reviews into authentic and fake. The newly emerging phenomenon of personality prediction has taken hold of social media and this is being employed in the case of reviewer traits which will help identify key personality traits of fake reviewers. The Big 5 model is used for this which will be useful in tracking such people through their associated social media accounts.