Feature Extraction Amazon Customer Review to Determine Topic on Smartphone Domain

Abstract

The growth of information affects social development. It makes long distance become shorter so that it is not a problem, it also changes someone of doing business activity through internal media or often called as electronic commercial or more popular with the name of e-commerce. Information about a particular product is called a review, whereas information about certain products obtained from other customer is customer review. Review is useful for consumers and manufacturing industries because determine consumer decisions in choosing a particular product. To determine a sentence that contains a particular feature of extraction on a sentence can be seen from words that contain product features directly is explicit, but there are some words that indirectly product feature or show characteristic of features is implicit. This paper aims to extract product features both explicit and implicit features to a review sentence on the mobile phone domain. The review format used is free text from the amazon e-commerce website but it raises ambiguous words to the product features, therefore takes dummy data to separate the word on product features. The method used to extract the feature is called SLTM (Sentence Level Topic Model) in previous [7] on online review. The dummy dataset, the system performance to extract the explicit feature is 76% and the implicit feature is 92.59%. While in the dataset amazon customer review, system performance to extract explicit features of 88.24% and implicit features of 60%.