餐廳使用者評論之大數據分析-運用大數據與文字分析探討景觀餐廳關鍵成功因素、線上受歡迎程度與顧客滿意度之影響

The magnificent growth of big data including click-through-rate, mobile transactions and the consumer-generated contents (CGCs) on the Internet has motivated the development of the so-called big data analytics to identify the critical success factors in the hospitality industry. However, the literature gap existed in the restaurant industry because the extant research focused on CGCs analysis in the hotel industry. The study 1 of this project aims to identify the determinants of on-line popularity of landscape restaurants. The study 2 of this project applied the collectivism cultural perspective to demonstrate the collective customer behaviour intention on the social network as well as to identify the CSFs of landscape restaurants based on CGCs in the on-line restaurant review platform. Study 1 of this project retrieved 558 valid data from 750 observed landscape restaurants from the Ipeen platform. Study 2 of this project retrieved 614 landscape restaurants from the ifoodie.tw platform in Taiwan. Through the literature review, the study 1 of this project identified influencing factors of page views of landscape restaurant including food rating, service quality rating, environment rating, number of posting, score given, overall rating and average spending in the review platform. Using the truncated regression with 2000 bootstrapped procedure to explore the significant impact factors of on-line popularity of landscape restaurants. The empirical results indicated that service quality rating and score given had significantly positive impact on the page views. This result had argued that the beautiful environment and delicious cuisine could not get more page views in the landscape restaurants in contrast to the service quality. The viewers who are willing to give the rating are the major browsers. The study 2 of this project is to generate measurement items from content analysis of online UGCs from the top five and last five ranked landscape restaurants in ifoodie.tw using the python crawling language. This project further invited five experts for content validity. The pilot test for 100 customers who had consumed in the landscape restaurants was conducted, wherein reliability and exploratory factor analysis were examined. The revised Importance and Performance analysis (RIPA) further identified the CSFs of landscape restaurants. The managerial implication and future research are also discussed.