|
Abstract:
|
User-generated-content (UGC) has been rapidly growing on online information sharing platforms and social networks. Its dynamic and spontaneous nature enables firms to immediately recognize customers' perception of the product or service quality which is one critical determinant of their satisfaction. However, it is challengeable to extract meaningful information source from the customer-generated review data, because the review data are generally unstructured and have various forms across all users. To make the structured data, we first change topic key words in each review to the pre-assumed words by linking online dictionary and then decompose each review into several components, sentences or phrases, to include only one topic in a component. After then, each component is scored using a machine learning method. The scored data are used to analysis customers' satisfaction in terms of assumed topic dimensions. The proposed approach is applied into Hawaii restaurant review data obtained from "Trip Advisor".
|
