Text Analysis American Airline Reviews Using Sas em
Text Analysis American Airline Reviews Using Sas em
Text Analysis American Airline Reviews Using Sas em
Article
Understanding Customer Experience and Satisfaction
through Airline Passengers’ Online Review
Hyun-Jeong Ban and Hak-Seon Kim *
School of Hospitality and Tourism Management, Kyungsung University, 309 Suyoungro, Nam-Gu,
Busan 48434, Korea
* Correspondence: kims@ks.ac.kr; Tel.: +82-51-663-4473
Received: 8 June 2019; Accepted: 18 July 2019; Published: 27 July 2019
Abstract: This study was conducted to understand customer experience and satisfaction through
airline passengers’ online review. To achieve the purpose of this study, the semantic network
analysis was conducted qualitatively by collecting reviews in top 10 airlines selected by Skytrax
(airlinequality.com). In addition, this study quantitatively identified the relationship among six
evaluation factors (seat comfort, staff, food and beverage (F&B), entertainment, ground service,
and value for money), customer satisfaction and recommendation. This study collected 9632 reviews
from the Skytrax. Through a CONCOR (CONvergence of iterated CORrelation) analysis, keywords
were grouped into six clusters (seat comfort, staff, entertainment, ground service, value for money,
and airline brand). Through the linear regression analysis, all evaluation factors except ‘entertainment’
factor significantly had impact on customer satisfaction and recommendation. These results showed
that understanding online review can provide both academic implication and practical implication to
develop sustainable strategy in the airline industry.
Keywords: customer experience; customer satisfaction; online review; skytrax; big data; semantic
network analysis
1. Introduction
Due to fierce competition in the airline industry, the airline company needs to focus on the
passenger’s experience and satisfaction [1]. Customer feedback, in particular, is critical since it is
an outcome measurement for business performance [2]. According to the international air transport
association (IATA) [3], numbers of airline passengers were increasing by about 7% every year since
2015. However, the net profit per airline passenger was decreasing by $10 for 2015, $9 for 2016 and 2017,
and it was estimated at only $7.4 for 2018. This is mainly due to intense competition, and also airline
costs have been rising recently. The major expenses that affect companies in the airline industry are
labor, fuel and other maintenance costs. The airline industry continues to be competitive, even though
many people are traveling by aircraft. The Internet has also created greater price transparency, reducing
margins [4].
Many studies have employed survey methods to measure service quality in the airline
industry [2,5–9]. However, a few recent studies have highlighted the advantages of analyzing online
review data for studying customers’ satisfaction or their experience of the airline [10,11]. Online reviews
are critical since it is a significant source for business growth, performance and improvement of
customer experience, and allow airline companies to conduct two-way communication with airline
passengers [12]. Moreover, electronic word of mouth (eWOM) shared by other airline passengers are
considered trustworthy, fast and widespread [13].
In the previous study, the service quality of airline passenger has been measured in various ways.
Elliott and Roach [5] used on-time performance, baggage handling, food quality, seat comfort, check-in
service, and in-flight service as the criteria for evaluating airline service quality. Aksoy et al. [6]
explored the differences in consumer expectations of airline services between passengers on the
Turkish domestic airline and those on four foreign airlines on the same routes. They found that
service expectations differed between the two groups. Gilbert and Wong [7] developed a 26-items
questionnaire incorporating reliability, assurance, facilities, employees, flight patterns, customization,
and responsiveness dimensions to measure and compare the differences in passengers’ expectations of
the desired airline service quality. Significant differences were found among passengers from different
ethnic groups and among passengers who travel for different purposes. However, there were limited
studies on the understanding experience and satisfaction of airline passengers using both qualitative
and quantitative methods to analyze over 9000 online reviews.
The main contribution of this study is the understanding of customer experience and satisfaction
through the airline passengers’ online review. In order to reach the purpose, large amounts of customer
reviews were collected from Skytrax (airlinequality.com). The analysis can be divided into two parts.
One was to analyze the meaning of words extracted from the review data using the semantic network
analysis by qualitative analysis. The other was conducted using the quantitative analysis method to
understand relationships among six evaluation factors, customer satisfaction and recommendation.
2. Literature Review
2.2. Skytrax
Skytrax is an airline quality assessment website that performs an online assessment after the
customer directly used each airline [1]. Skytrax has worked for over 150 airlines across the globe,
from the world’s largest airlines through to small domestic carriers and it is a world-recognized brand
that provides professional audit and service benchmarking programs for airlines on product and
service quality. They employ professional auditors to assess the quality of the work done in an airline,
both onboard and in the airport terminals. These evaluations are based on consistent standards [9].
The best airlines in the world highly recognize these quality awards presented by the Skytrax.
When an airline is awarded a ‘Skytrax star-ranking’ or advances to a higher ranking, they immediately
announce this news by publishing press releases and posting it on their websites’ most visible spots.
Both overall star rankings and detailed quality assessment results are publicly available on the Skytrax
website [25]. This data has also been used in various academic studies as shown in Table 1.
to see at a glance the structure of the network or the associativity between nodes [43]. The approach
and visualization for the semantic network analysis of this study was performed by Ucinet 6.0.
3. Methodology
The results of the analysis of variance among customer satisfaction with brands showed the
following results, in decreasing order of satisfaction level: Garuda Indonesia (8.301), Hainan Airways
(8.238), EVA Air (8.030), All Nippon Airways (7.765), Singapore Airlines (7.501), Qatar Airways
(7.477), Cathay Pacific Airways (6.908), Thai Airways (6.796), Lufthansa (6.652) and Emirates (5.766).
The results showed that there were significant differences between the customer satisfaction and
numbers of reviews.
data analysis, Ucinet 6.0 packaged with Netdraw, which is a visualization tool. The Netdraw is
an illustration
Sustainability program
2019, 11, to REVIEW
x FOR PEER express how the frequent words are related and make an impact 5 ofwith
17
certain interaction. It is mainly concentrated on the semantic network analysis about the extracted top
frequent keywords
100 frequent keywords fromfrom
raw raw
data.data.
After that,that,
After the the
centrality analysis
centrality of of
analysis Freeman’s degree
Freeman’s has
degree hasbeen
been
worked
workedout outfor
forrefining
refiningthe
themeanings
meaningsofofconnection
connectionbetween
betweenthethetop
top100
100frequent
frequentwords.
words.
Qualitative
Figure1.1.Qualitative
Figure researchprocess.
research process.
AccordingtotoLiLiand
According andSun
Sun[45],
[45],different
differentmeasures
measuressuch
suchasascentrality
centralityand
andproximity
proximitycan
canbebederived
derived
totomeasure
measurethethestructure
structureofofthe
thesemantic
semanticnetwork
networkand
andtotocompare
comparedifferences
differencesbetween
betweentwo
twosemantic
semantic
structures. The last step of the analysis is CONCOR analysis. It helps segments of
structures. The last step of the analysis is CONCOR analysis. It helps segments of upper frequent upper frequent
words and visualizes the segmentation of higher frequent words so that frequently
words and visualizes the segmentation of higher frequent words so that frequently used words used words belong
to anyto
belong particular category
any particular and other
category and words belongbelong
other words to anytogroup.
any group.
3.3. Quantitative Data Analysis
3.3. Quantitative Data Analysis
For the quantitative analysis, the evaluation data on six factors (seat comfort, staff, F&B,
For the quantitative analysis, the evaluation data on six factors (seat comfort, staff, F&B,
entertainment, ground service, value for money) with customer satisfaction and recommendation
entertainment, ground service, value for money) with customer satisfaction and recommendation
from Skytrax (airlinequality.com) were collected. Using the SPSS (IBM, Armonk, NY, USA) Statistics
from Skytrax (airlinequality.com) were collected. Using the SPSS (IBM, Armonk, NY, USA) Statistics
program, it conducted a linear regression analysis and verified the impact of each factor and the
program, it conducted a linear regression analysis and verified the impact of each factor and the
customer satisfaction. In addition, the relationship between customer satisfaction and recommendation
customer satisfaction. In addition, the relationship between customer satisfaction and
was analyzed. For verification, a research model was established as shown in Figure 2.
recommendation was analyzed. For verification, a research model was established as shown in Figure
There were thirteen hypotheses suggested as follows:
2.
Hypotheses 1-1. Seat comfort positively influences the customer satisfaction of the airline.
Hypotheses 1-2. Staff positively influences the customer satisfaction of the airline.
Hypotheses 1-3. F&B positively influences the customer satisfaction of the airline.
Hypotheses 1-4. Entertainment positively influences the customer satisfaction of the airline.
Hypotheses 1-5. Ground service positively influences the customer satisfaction of the airline.
According to Li and Sun [45], different measures such as centrality and proximity can be derived
Sustainability 2019, 11, 4066 6 of 17
to measure the structure of the semantic network and to compare differences between two semantic
structures. The last step of the analysis is CONCOR analysis. It helps segments of upper frequent
Hypotheses 1-6. Value for
words and visualizes themoney positively influences
segmentation of higher the customer
frequent satisfaction
words of the
so that airline. used words
frequently
belong to any particular category and other words belong to any group.
Hypotheses 2-1. Seat comfort positively influences the recommendation of the airline.
Hypotheses 2-2. Staff
3.3. Quantitative Data positively
Analysis influences the recommendation of the airline.
Hypotheses
For the2-3. F&B positively
quantitative influences
analysis, the the recommendation
evaluation data onof the
six airline.
factors (seat comfort, staff, F&B,
entertainment, ground service, value for money) with customer satisfaction and recommendation
Hypotheses 2-4. Entertainment positively influences the recommendation of the airline.
from Skytrax (airlinequality.com) were collected. Using the SPSS (IBM, Armonk, NY, USA) Statistics
Hypotheses
program, it 2-5. Ground aservice
conducted linearpositively influences
regression theand
analysis recommendation
verified theofimpact
the airline.
of each factor and the
Hypotheses 2-6. Value for money positively influences the recommendation of the airline. satisfaction and
customer satisfaction. In addition, the relationship between customer
recommendation was analyzed. For verification, a research model was established as shown in Figure
Hypotheses
2. 3. Customer satisfaction positively influences the recommendation of the airline.
.
Figure 2. Quantitative research model.
Figure 2. Quantitative research model.
4. Results
Table 3. Top 100 frequent words from the online airline review.
1000
900
800
700
600
500
400
300
200
100
0
inflight
aircraft
experience
cabin
time
drink
ground
class
space
meal
economy
quality
plane
hour
money
smile
crew
seat
service
staff
airport
premium
lounge
expectation
food
attendant
star
entertain
leg
value
The CONCOR analysis analyzes the connection of the relationship and patterns between words
to see their similarity, and the greater the similarity of the connection relationship patterns, the greater
the degree of structural equivalence of the two words. It forms clusters that include keywords with
similarities [10]. One of the most natural methods is the cluster analysis, which is a statistical technique
that binds them into similarity groups based on interrelationships [48]. In other words, the CONCOR
analysis is a method of repeatedly analyzing correlations to find appropriate levels of similarity groups.
This study identifies the blocks of nodes according to the correlation coefficient of the matrices of the
concurrent keywords and forms clusters that include keywords with similarities [18]. The keywords
extracted from the frequency histogram according to the frequency ranking were used and a [keywords
× keywords] matrix were constructed. To visualize the analysis results, NetDraw in UCINET 6.0
program was used. The nodes are presented as blue squares and their sizes indicate their frequency;
the network shows the connectivity between them.
The result of the CONCOR analysis has been shown in Figure 5 with visibility. There are six groups
that were intricately interwoven with each other. After looking at the words in the group, the group
was named as seat comfort, staff, entertainment, airline brand, value for money and ground service.
Interestingly, the CONCOR results were very similar to the evaluation factors (seat comfort, staff, F&B,
entertainment, ground service and value for money) presented by Skytrax (airlinequality.com).
Sustainability 2019, 11, 4066 10 of 17
Sustainability 2019, 11, x FOR PEER REVIEW 10 of 17
The ‘Value for money’ factor holds the highest standardized coefficients, which mean this
experience aspect of the passenger is the most important factor associated with customer satisfaction
significantly. Reviews like “It’s value for money and it’s best if you compare to other airlines based
on travel duration and price.” and “First time trying the premium economy of Singapore Airlines,
must I say I was really impressed by the offering and the value for money.” are related to the airline
experience based upon ‘Value for money’ attributes.
Sustainability 2019, 11, 4066 12 of 17
Unstandardized Standardized
Collinearity Statistics
Model Coefficient Coefficient t Sig.
B Std. Error Beta Tolerance VIF
(Constant) −0.843 0.049 −17.253 0.000
Seat Comfort (SC) 0.172 0.016 0.080 10.828 0.000 0.449 2.227
Staff (S) 0.349 0.016 0.176 21.643 0.000 0.375 2.670
Food & Beverage (FB) 0.203 0.016 0.102 12.420 0.000 0.366 2.733
Entertainment (E) −0.005 0.011 −0.003 −0.501 0.617 0.676 1.480
Ground Service (GS) 0.058 0.007 0.042 8.026 0.000 0.890 1.123
Value for money (VM) 1.347 0.016 0.603 84.612 0.000 0.486 2.057
* Dependent variable: Customer Satisfaction (CS); R2 = 0.762; F = 5147.275; p < 0.001.
Table 7 displays the results of the linear regression analysis with ‘Recommendation (R)’ as the
dependent variable and it has six independent variables: ‘Seat comfort (SC)’, ‘Staff (S)’, ‘Food &
Beverage (FB)’, ‘Entertainment (E)’, ‘Ground service (GS)’ and ‘Value for money (VM)’. The overall
variance explained by the six predictors was 60.5% (R2 = 0.605) and the standard error of the estimated
value was calculated as 0.2773. All factors are significant at the p < 0.001 level except ‘Entertainment
(E, β = −0.015, p = 0.053)’ factor. Five factors are positively related to the recommendation, according
to their standardized coefficient values: ‘Seat comfort (SC, β = 0.045, p < 0.05)’, ‘Staff (S, β = 0.197,
p < 0.05)’, ‘Food & beverage (FB, β = 0.040, p < 0.05)’, ‘Ground service (GS, β = 0.014, p < 0.05) and
‘Value for money (VM, β = 0.577, p < 0.05)’0. Therefore, hypothesis 2-1, 2-2, 2-3, 2-5 and 2-6 was
supported, however hypothesis 2-4 was rejected. Therefore, based on unstandardized β, the regression
equation can be expressed as:
Unstandardized Standardized
Collinearity Statistics
Model Coefficient Coefficient t Sig.
B Std. Error Beta Tolerance VIF
(Constant) −0.325 0.010 −33.886 0.000
Seat Comfort (SC) 0.015 0.003 0.045 4.4741 0.000 0.449 2.227
Staff (S) 0.059 0.003 0.197 18.794 0.000 0.375 2.670
Food & Beverage (FB) 0.012 0.003 0.040 3.807 0.000 0.366 2.733
Entertainment (E) −0.004 0.002 −0.015 −1.936 0.053 0.676 1.480
Ground Service (GS) 0.003 0.001 0.014 2.032 0.042 0.890 1.123
Value for Money (VM) 0.196 0.003 0.577 62.722 0.000 0.486 2.057
* Dependent variable: Recommendation (R); R2 = 0.605; F = 2451.601; p < 0.001
To verify the part corresponding to hypothesis 3, the third linear regression analysis was
performed. The result is shown in Table 8 with a recommendation as the dependent variable and it has
independent variables as customer satisfaction. The overall variance explained by the predictor was
69.4% (R2 = 0.694) and the standard error of the estimated value was calculated as 0.244. The customer
satisfaction is significant and positively related to the recommendation, according to their standardized
coefficient values: β = 0.833, p < 0.001). Therefore, hypothesis 3 was supported.
Sustainability 2019, 11, 4066 13 of 17
Standardized
Unstandardized Coefficient
Model Coefficient t Sig.
B Std. Error Beta
(Constant) −0.158 0.007 −24.173 0.000
Customer Satisfaction (CS) 0.127 0.001 0.833 147.592 0.000
* Dependent variable: Recommendation(R); R2 = 0.694; F = 21783.469; p < 0.001.
5. Discussion
This study was conducted to enhance the customer’s experience, satisfaction and recommendation
by qualitatively and quantitatively analyzing the reviews of airline passengers. For the airline
passengers’ review data analysis, the first process is extracting keywords by text mining and the second
is grouping them using the CONCOR analysis. In addition, the study conducted three consecutive linear
regression analyses to understand the relationship between evaluation factors, customer satisfaction,
and recommendations presented on the customer review website. Interestingly, six clusters (airline
brand, seat comfort, staff, entertainment, ground service and value for money) derived from qualitative
semantic network analysis were very similar to the six evaluation factors (seat comfort, staff, F&B,
entertainment, ground service and value for money) that Skytrax is asking customers to evaluate on
the website. Therefore, this study quantitatively analyzed the impact relationships among the six
evaluation factors of Skytrax, customer satisfaction and recommendation.
The following implications can be suggested by combining qualitative and quantitative analysis:
First of all, the group representing the highest beta coefficient was ‘Value for money’ in the linear
regression analysis, and the related words were ‘value’, ‘price’, ‘money’ and ‘cost’ through the semantic
network analysis. The group contains fewer words than the other group. Even though customers are
not frequently mentioning the words related with ‘Value for money’ on the online review, it is still the
most important factor to figure out the customer experience of airlines. According to Brochado, Rita,
Oliveira, & Oliveira [12], ‘Value for money’ is the key factor as a criterion for positive and negative
eWOM. In other words, the airline passengers who classify ‘Value for money’ as very good or excellent
also provide positive eWOM about the airlines’ seats, staff, entertainment and food. In addition,
Rajaguru [50] examined the effect of value for money and service quality on customer satisfaction and
behavioral intention. The results of this study show the same results as most prior studies show that
Value for Money has the greatest impact on customer satisfaction and recommendation. Therefore,
the airline should focus its most essential tangible and intangible resources on the value for money.
The second highest beta value was ‘Staff’ in the linear regression analysis, and the related words
were ‘crew’, ‘cabin’, ‘staff’, ‘attendant’, ‘smile’, ‘kind’ and ‘attitude’ through the semantic network
analysis. Service performing by staff was an essential key factor to create a good image in the service
industry and can still be seen as a part of the company that must be managed at all times to keep up
the image of the company. Therefore, it is important to improve the attitude of employees through
systematic service training. In addition, providing an environment to enhance employee satisfaction to
produce better service to customers can be another way.
Third, the entertainment group derived from the CONCOR analysis includes two factors
(Entertainment, F&B) of passenger evaluation factors on the Skytrax website. Based on the words
relating with ‘entertainment’ were mentioned in the online review text such as ‘service’, ‘food’,
‘class’, ‘meal’, ‘economy’, ‘quality’, ‘entertain’, ‘drink’, ‘premium’, ‘breakfast’, ‘wine’, ‘movie’ and
‘dinner’ through the semantic network analysis. As the result of regression analysis, evaluation
factor on the Skytrax ‘Entertainment’ had no impact on customer satisfaction and recommendation.
However, the other evaluation factor ‘F&B’ had impact on customer satisfaction and recommendation.
In particular, the results related to F&B are significant, and have been found in the recent study as
a critical customer satisfaction factor in the Tourism industry [38,51,52].
Sustainability 2019, 11, 4066 14 of 17
Fourth, ‘seat’ recorded rank 15 in the top 100 frequent words, and related words were ‘flight’, ‘seat’,
‘time’, ‘hour’, ‘way’, ‘leg’, ‘plane’, ‘journey’, ‘legroom’, ‘comfort’, ‘board’, ‘room’, ‘route’ and ‘option’
through semantic network analysis. In addition, ‘Seat comfort’ had impact on customer satisfaction
and recommendation through linear regression analysis. The airline industry has the characteristic
of sharing a narrow space with many people, therefore ‘Seat comfort’ can have a significant impact
on customer satisfaction and recommendation. According to the meta-analysis conducted by Lim
& Tkaczynski [53], seating comfort is among the most frequent items mentioned in airline service
quality studies. The current results also confirmed that ‘Seat comfort’ is an important dimension in
airline industry.
Lastly, words related to ground service are ‘lounge’, ‘bag’, ‘bus’ and ‘ticket’. If the ‘Seat comfort’
is the indoor physical environment, the ‘Ground service’ can be the outdoor physical environment
to provide a comfortable environment outside of the aircraft. So the airlines need to take care of
the condition of the lounge. Especially, the lounge is the space used while waiting, and the time for
waiting will be a chance to provide impressive service to the passengers. F&B provided in the lounge is
absolutely important to have quality rest in the lounge. Ground services are shown in linear regression
results that have a significant positive influence on both customer satisfaction and recommendation.
Airline companies can satisfy passengers and create a positive image by paying attention to the quality
of their baggage claim service, the ticketing service required to board the aircraft, and the quality of
service provided on limousine buses.
This study presents the academic implication that the study has extended its application area of
semantic network analysis. While given the significance of the airline segment in the tourism industry,
this study empirically explores among airline experience, customer satisfaction and recommendation
by big data analytics. Along the way, the airline has the opportunity to gain an understanding of
factors on the review web site, so as to infiltrate into this market and create corresponding marketing
strategies for their strong advantages. Understanding online reviews as a manifestation of passengers’
experiences can help airlines to identify the main attributes required to achieve positive post-purchase
behaviors and to minimize negative intentions. Thus, the online reviews not only provide an efficient
way for airlines to collect feedback from airline passengers, but also provide an opportunity to discover
how to generate positive intent after the experience. To create a high customer rating and a positive
eWOM, airlines should consider ‘Seat comfort’, ‘Staff’, ‘F&B’, ‘Ground service’ and ‘Value for money’.
Among them, ‘Value for money’ was the most influential attribute in the regression analysis. These key
factors may be used to examine the customer satisfaction or to test theoretical models to have a better
understanding of airline passenger behavior.
In practice, the analysis of online reviews can be used as a diagnostic tool by managers since
customer feedback is important for airlines to improve services and products, and to take action
regarding service. The analysis also provides the level of importance of these service attributes so
airlines can allocate their resources accordingly. Online review analyses can provide reliable satisfaction
assessment for airlines. Airlines can also use this method to analyze their competitors’ passenger
feedbacks so that they can benchmark themselves against competitors in terms of customer satisfaction.
These reviews can be used for sustainable strategic marketing decisions against competitors.
However, this study shows limitations in the area of the study as it focuses on airlines that are
mainly handled by the Skytrax (airlinequality.com). Therefore, in future studies, big data analysis using
social media data reviews, which is known all around the world, will be a better way to understand
consumer trends. Secondly, the collected text was analyzing based on the frequency of individual
words, therefore, it is difficult to understand the additional meaning of words. In future studies, further
analysis of positives and negatives, and sentimental analysis regarding airline recognition is expected
to be carried out to better understand the customer’s thoughts and to present stronger strategies to the
airline industry.
Author Contributions: H.-J.B. and H.-S.K. designed the research model, analyzed online review data and wrote
the paper.
Sustainability 2019, 11, 4066 15 of 17
Funding: This research was supported by Kyungsung University Research Grants in 2019 [grant number
KSU-Grants2019]. Additionally, this work was supported by the Ministry of Education of the Republic of Korea
and the National Research Foundation of Korea (NRF-2016S1A5A2A03928029).
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Siering, M.; Deokar, A.V.; Janze, C. Disentangling consumer recommendations: Explaining and predicting
airline recommendations based on online reviews. Decis. Support Syst. 2018, 107, 52–63. [CrossRef]
2. Li, W.; Yu, S.; Pei, H.; Zhao, C.; Tian, B. A hybrid approach based on fuzzy AHP and 2-tuple fuzzy linguistic
method for evaluation in-flight service quality. J. Air Transp. Manag. 2017, 60, 49–64. [CrossRef]
3. International Air Transport Association. Industry Statistics Fact Sheet. Available online: https://www.iata.
org/pressroom/facts_figures/fact_sheets/Documents/fact-sheet-industry-facts.pdf (accessed on 20 May 2019).
4. Beers, B. Investopedia. Available online: https://www.investopedia.com/ask/answers/040715/what-are-
major-expenses-affect-companies-airline-industry.asp (accessed on 3 July 2019).
5. Elliott, K.M.; Roach, D.W. Service quality in the airline industry: Are carriers getting an unbiased evaluation
from consumers? J. Prof. Serv. Mark. 1993, 9, 71–82. [CrossRef]
6. Aksoy, S.; Atilgan, E.; Akinci, S. Airline services marketing by domestic and foreign firms: Differences from
the customers’ viewpoint. J. Air Transp. Manag. 2003, 9, 343–351. [CrossRef]
7. Gilbert, D.; Wong, R.K. Passenger expectations and airline services: A Hong Kong based study. Tour. Manag.
2003, 24, 519–532. [CrossRef]
8. Park, J.W.; Robertson, R.; Wu, C.L. The effect of airline service quality on passengers’ behavioural intentions:
A Korean case study. J. Air Transp. Manag. 2004, 10, 435–439. [CrossRef]
9. Xu, X.; Liu, W.; Gursoy, D. The impacts of service failure and recovery efforts on airline customers’ emotions
and satisfaction. J. Travel Res. 2018, 58, 1034–1051. [CrossRef]
10. Zhang, Y.; Cole, S.T. Dimensions of lodging guest satisfaction among guests with mobility challenges:
A mixed-method analysis of web-based texts. Tour. Manag. 2016, 53, 13–27. [CrossRef]
11. Liau, B.Y.; Tan, P.P. Gaining customer knowledge in low cost airlines through text mining. Ind. Manag.
Data Syst. 2014, 114, 1344–1359. [CrossRef]
12. Saha, G.C.; Theingi. Service quality, satisfaction, and behavioural intentions: A study of low-cost airline
carriers in Thailand. Manag. Serv. Qual. Int. J. 2009, 19, 350–372.
13. Brochado, A.; Rita, P.; Oliveira, C.; Oliveira, F. Airline passengers’ perceptions of service quality: Themes in
online reviews. Int. J. Contemp. Hosp. Manag. 2019, 31, 855–873. [CrossRef]
14. Hunt, J.D. Image as a factor in tourism development. J. Travel Res. 1975, 13, 1–7. [CrossRef]
15. Walker, J.; Baker, J. An exploratory study of a multi-expectation framework for services. J. Serv. Mark. 2000,
14, 411–431. [CrossRef]
16. Tao, S.; Kim, H.S. Cruising in Asia: What can we dig from online cruiser reviews to understand their
experience and satisfaction. Asia Pac. J. Tour. Res. 2019, 24, 514–528. [CrossRef]
17. Gretzel, U. Consumer generated content–trends and implications for branding. E Rev. Tour. Res. 2006,
4, 9–11.
18. Kim, H.S.; Noh, Y. Elicitation of design factors through big data analysis of online customer reviews for
washing machines. J. Mech. Sci. Technol. 2019, 33, 2785–2795. [CrossRef]
19. Ban, H.J.; Kim, H.S. A study on the TripAdvisor review analysis of restaurant recognition in Busan 1:
Especially concerning English reviews. Culin. Sci. Hosp. Res. 2019, 25, 1–11.
20. Browning, V.; So, K.K.F.; Sparks, B. The influence of online reviews on consumers’ attributions of service
quality and control for service standards in hotels. J. Travel Tour. Mark. 2013, 30, 23–40. [CrossRef]
21. Dellarocas, C.; Zhang, X.M.; Awad, N.F. Exploring the value of online product reviews in forecasting sales:
The case of motion pictures. J. Interact. Mark. 2007, 21, 23–45. [CrossRef]
22. Minnema, A.; Bijmolt, T.H.; Gensler, S.; Wiesel, T. To keep or not to keep: Effects of online customer reviews
on product returns. J. Retail. 2016, 92, 253–267. [CrossRef]
23. Mudambi, S.M.; Schuff, D. What makes a helpful review? A study of customer reviews on Amazon.com.
MIS Q. 2010, 34, 185–200. [CrossRef]
Sustainability 2019, 11, 4066 16 of 17
24. Sotiriadis, M.D.; VanZyl, C. Electronic word-of-mouth and online reviews in tourism services: The use of
twitter by tourists. Electron. Commer. Res. 2013, 13, 103–124. [CrossRef]
25. Skytrax. World’s Top 100 Airlines 2018. Available online: https://www.worldairlineawards.com/worlds-top-
100-airlines-2019/ (accessed on 20 March 2019).
26. Adeniran, A.; Fadare, S.O. Relationship between passengers’ satisfaction and service quality in murtala
muhammed international airport, Lagos, Nigeria. Int. J. Res. Ind. Eng. 2018, 7, 349–369.
27. Jeong, E.Y. Analyze of Airlines Online-reviews: Focusing on Skytrax. J. Tour. Leis. Res. 2017, 2, 261–276.
28. Yayla-Kullu, H.M.; Tansitpong, P. A critical evaluation of US airlines’ service quality performance: Lower
costs vs. satisfied customers. J. Manag. Strategy 2013, 4, 1. [CrossRef]
29. Pérezgonzález, J.D.; Gilbey, A. Predicting Skytrax airport rankings from customer reviews. J. Air Transp. Manag.
2011, 5, 335–339.
30. Lohmann, G.; Albers, S.; Koch, B.; Pavlovich, K. From hub to tourist destination—An explorative study of
Singapore and Dubai’s aviation-based transformation. J. Air Transp. Manag. 2009, 15, 205–211. [CrossRef]
31. Mason, K.J.; Morrison, W.G. Towards a means of consistently comparing airline business models with
an application to the ‘low cost’airline sector. Res. Transp. Econ. 2008, 24, 75–84. [CrossRef]
32. Park, J.W.; Robertson, R.; Wu, C.L. The effects of individual dimensions of airline service quality: Findings
from Australian domestic air passengers. J. Hosp. Tour. Manag. 2006, 13, 161–176. [CrossRef]
33. Gillen, D.; Lall, A. Competitive advantage of low-cost carriers: Some implications for airports. J. Air
Transp. Manag. 2004, 10, 41–50. [CrossRef]
34. Davenport, T.H.; Barth, P.; Bean, R. How big data is different. MIT Sloan Manag. Rev. 2012, 54, 43.
35. He, W.; Xu, G. Social media analytics: Unveiling the value, impact and implications of social media analytics
for the management and use of online information. Online Inf. Rev. 2016, 40. [CrossRef]
36. Han, S.I.; Kim, T.H.; Lee, J.H.; Kim, H.S. A study on the application of SNS big data to the industry in the
fourth industrial revolution. Culin. Sci. Hosp. Res. 2017, 23, 1–10.
37. Oh, C.; Kim, H.S. Understanding of nutrition labelling use and related factors among Korean adults. Culin. Sci.
Hosp. Res. 2018, 24, 16–22.
38. Kim, Y.J.; Ban, H.J.; Kim, H.S. An exploratory study on the semantic network analysis of Busan tourism:
Using Google web and news. Culin. Sci. Hosp. Res. 2019, 25, 126–134.
39. Jo, A.; Kim, H.S. A comparison of Starbucks between South Korea and U.S.A. through big data analysis.
Culin. Sci. Hosp. Res. 2018, 23, 195–205.
40. Shuting, T.; Kang, B.; Kim, H.S. Understanding the food hygiene of cruise through the big data analytics
using the web crawling and text mining. Culin. Sci. Hosp. Res. 2018, 24, 34–43.
41. Kim, H.S.; Yim, H.R. An exploratory study on the semantic network analysis of ‘Culinary Science &
Hospitality Research’ through the Google Scholar. Culin. Sci. Hosp. Res. 2018, 24, 1–10.
42. Shuting, T.; Kim, H.S. A study of comparison between cruise tours in China and USA through big data
analytics. Culin. Sci. Hosp. Res. 2017, 23, 1–10. [CrossRef]
43. Oh, C.; No, J.K.; Kim, H.S. Dietary pattern classifications with nutrient intake and body composition changes
in Korean elderly. Nutr. Res. Pract. 2014, 8, 192–197. [CrossRef]
44. Hong, J.W.; Park, S.B. The identification of marketing performance using text mining of airline review data.
Mob. Inf. Syst. 2019, 19. [CrossRef]
45. Li, H.; Sun, J. Forecasting business failure: The use of nearest-neighbour support vectors and correcting
imbalanced samples—Evidence from the Chinese hotel industry. Tour. Manag. 2012, 33, 622–634. [CrossRef]
46. Kim, H.S. A semantic network analysis of big data regarding food exhibition at convention center. Culin. Sci.
Hosp. Res. 2017, 23, 257–270.
47. Bonacich, P. Some unique properties of eigenvector centrality. Soc. Netw. 2007, 29, 555–564. [CrossRef]
48. Lee, Y.J.; Yoon, J.H. Exploring ways to utilize SNS big data in the tourism sector. Int. J. Tour. Hosp. Res. 2014,
28, 5–14.
49. Kim, J.J.; Kim, K.; Hwang, J. Self-enhancement driven first-class airline travelers’ behavior: The moderating
role of third-party certification. Sustainability 2019, 11, 3285. [CrossRef]
50. Lim, S.S.; Tkaczynski, A. Origin and money matter: The airline service quality expectations of international
students. J. Hosp. Tour. Manag. 2017, 31, 244–252. [CrossRef]
51. Choi, H.Y.; Kwak, G.H.; Kim, H.S. A positioning study of national food: In perspective of Korean, American,
Chinese food tourists. Culin. Sci. Hosp. Res. 2017, 23, 86–94. [CrossRef]
Sustainability 2019, 11, 4066 17 of 17
52. Kim, H.S. An exploratory study on the semantic network analysis of food tourism through the big data.
Culin. Sci. Hosp. Res. 2017, 23, 22–32.
53. Rajaguru, R. Role of value for money and service quality on behavioural intention: A study of full service
and low cost airlines. J. Air Transp. Manag. 2016, 53, 114–122. [CrossRef]
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).