텍스트마이닝 기법을 활용한 레스토랑 유형별 선택속성 차이에 관한 연구: 외래 관광객을 중심으로

Online reviews directly show various emotions of customers; they can be used as a valuable resource for understanding customer experiences. The purpose of this study is to identify customer satisfaction and dissatisfaction emotional factors for each restaurant type using text mining techniques for online restaurant review data and to verify whether there is a significant difference in the importance of selection attributes by restaurant type. Various reviews were collected from the hotel & restaurant review community. After pre-processing reviews, the sentiment analysis was used to calculate the sentiment polarity values for each selected attribute and to analyze the differences by restaurant type. As a result, food, service, and atmosphere selection attributes were the highest in fine dining restaurants, and the price was the highest in quick self-service restaurants. Analysis of variance was performed to verify whether there was a significant difference in the selection attributes by restaurant type, and all selection attributes showed significant differences. The implications of this study are that it is possible to overcome the physical limitations of the traditional survey methods by using online review big data, and to quantify the customer experience of text reviews using the sentiment analysis technique, enabling in-depth analysis of satisfaction by restaurant type.