TY - JOUR
T1 - Role of Emotions in Fine Dining Restaurant Online Reviews: The Applications of Semantic Network Analysis and a Machine Learning Algorithm
AU - Oh, Munhyang
AU - Kim, Seongseop
N1 - Publisher Copyright:
© 2021 Taylor & Francis Group, LLC.
PY - 2022/10
Y1 - 2022/10
N2 - This study attempts to investigate basic emotions incorporated in online reviews of fine dining Cantonese restaurants in Hong Kong and to investigate antecedents and consequences according to each emotion. This study adopts semantic network analysis and a machine learning algorithm to achieve its research objectives. A total of 2,118 reviews were used for the analysis. Five emotions–joy, sadness, disgust, surprise, and anger–accounted for 72% of prediction accuracy. Given that the five types of emotions in this study were closely associated with service, food, and reputation, the three components are considered the core elements of a fine dining restaurant experience. Results of this study imply that restaurants should understand customers’ emotion based on big data analysis. The integration of emotion theory and practical implications can provide meaningful evidence on how to capitalize on big data.
AB - This study attempts to investigate basic emotions incorporated in online reviews of fine dining Cantonese restaurants in Hong Kong and to investigate antecedents and consequences according to each emotion. This study adopts semantic network analysis and a machine learning algorithm to achieve its research objectives. A total of 2,118 reviews were used for the analysis. Five emotions–joy, sadness, disgust, surprise, and anger–accounted for 72% of prediction accuracy. Given that the five types of emotions in this study were closely associated with service, food, and reputation, the three components are considered the core elements of a fine dining restaurant experience. Results of this study imply that restaurants should understand customers’ emotion based on big data analysis. The integration of emotion theory and practical implications can provide meaningful evidence on how to capitalize on big data.
KW - machine learning
KW - online review
KW - Restaurant
KW - semantic network
KW - text analytics
UR - http://www.scopus.com/inward/record.url?scp=85100861404&partnerID=8YFLogxK
U2 - 10.1080/15256480.2021.1881938
DO - 10.1080/15256480.2021.1881938
M3 - Journal article
AN - SCOPUS:85100861404
SN - 1525-6480
VL - 23
SP - 875
EP - 903
JO - International Journal of Hospitality and Tourism Administration
JF - International Journal of Hospitality and Tourism Administration
IS - 5
ER -