Algorithm for extracting product feature from e-commerce comment

<span>Reviews of e-commerce play an important role in online purchasing decisions. Consumers are likely to read reviews and comments on products from other consumers. In addition those opinions that reflect consumers' trust products, it also provides each product's distinctive properties. Today, there many reviews, resulting enormous suggestions. However, as fully reading is quite difficult, this article presents 3 algorithms for automatic extraction product features hidden reviews: a traditional frequency-based feature (F-PFE), syntax analyzer system (SAS), the hybrid approach called frequency syntax-based (FaS-PFE). The proposed were tested against 4 different types products: shampoo, skincare, mobile phone, tablet, using amazon.com. Based review used study, was found SAS can help improve performance terms precision by 15% when compared with F-PEE approach. When considering both word syntax, FaS-PFE clearly outperforms two approaches 94.00% 95.13% recall.</span>