Presentation done by Zheng Xiang, during "Intelligence & analytics" workshop, of the ENTER2015 eTourism conference.

1. ENTER 2015 Research Track Slide Number 1
What Types of Hotels Make Their Guests (Un)Happy?
Text Analytics of Customer Experiences in Online Reviews
Zheng Xiang
Virginia Tech, USA
philxz@vt.edu
Zvi Schwartz
University of Delaware, USA
zvi@udel.edu
Muzzo Uysal
Virginia Tech, USA
Samil@vt.edu

2. ENTER 2015 Research Track Slide Number 2
Introduction
• Understanding what drives hotel guest
satisfaction is an ongoing yet challenging task.
• Consumer-generated contents (the “big data”)
offer new directions for understanding core
variables in hospitality and tourism management.
• Building upon a previous study this study aims to
explore the usefulness of text analytics in a hotel
management setting.

3. ENTER 2015 Research Track Slide Number 3
Research background (1)
• Perspectives on customer satisfaction (e.g.,
Zeithaml, & Berry, 1985; Grönroos, 1984; Oliver,
1980).
• Antecedents of hotel guest satisfaction (Torres-
Sovero et al., 2012; Kotler, Bowen, & Mackens,
2006; Dolnicar & Otter, 2003; Noel & Uysal, 1997;
Chathoth et al., 2013)

4. ENTER 2015 Research Track Slide Number 4
Research background (2)
• User-generated content as sources for
understanding travel behavior incl. experience
and satisfaction (see Lu & Stepchenkova, in press
for a review).
• Limitations in existing research
– “small” data
– Thematic/sentiment analysis
• Experience as foundation to understand guest
satisfaction (Xiang et al., 2015)

5. ENTER 2015 Research Track Slide Number 5
Research Questions
• Can hotels be distinguished by guest
experience and satisfaction?
• If so, for what reasons do hotels make their
guests (un)happy?

6. ENTER 2015 Research Track Slide Number 6
Data
• Expedia.com
• Crawling was done during December 18-29, 2007
• All hotels (N=10,537) listed for the 100 largest US
cities
• 6,642 unique words with frequency ranging from
33,549 to 1
• 1.3 million word-review pairs (avg. 22 unique
words/review)

7. ENTER 2015 Research Track Slide Number 7
Analysis
• Data pre-processing: stemming, misspelling identification, stop words
identification/removal.
• Domain identification following a theory-driven coding schema.
• 416 primary words identified as the ‘dictionary’ of hotel guest
experience.
• Data table contains >5,000 hotel properties – quite sparse.
• Factor analysis was conducted ( frequency of words by hotel
properties) to identify guest experience dimensions
• Cluster analysis was conducted to identify hotel types in relation to
experience and satisfaction
• Correspondence analysis was used to examine hotel clusters’
association with words

8. ENTER 2015 Research Track Slide Number 8
80 primary words of guest experience
Word N
N/Hote
l Word N
N/Hote
l Word N
N/Hote
l Word N
N/Hote
l
room 5641 10.7 downtown 676 1.3 lobby 357 0.7 experience 240 0.5
clean 3104 5.9 airport 620 1.2 internet 344 0.7 suite 236 0.4
staff 2898 5.5 desk 609 1.2 trip 328 0.6 money 233 0.4
location 2865 5.4 view 569 1.1 pay 320 0.6 carpet 233 0.4
comfortable 2168 4.1 recommend 532 1.0 door 317 0.6 courteous 233 0.4
service 1707 3.2 noise 493 0.9 shops 316 0.6 city 231 0.4
friendly 1614 3.1 quiet 486 0.9 sleep 303 0.6 expensive 223 0.4
close 1594 3.0 food 468 0.9 business 301 0.6 dirty 221 0.4
breakfast 1524 2.9 distance 464 0.9 complaint 299 0.6 renovated 219 0.4
helpful 1378 2.6 shuttle 447 0.8 shower 296 0.6 tub 217 0.4
bed 1334 2.5 street 429 0.8 family 294 0.6 safe 216 0.4
price 1321 2.5 shopping 419 0.8 value 290 0.5 far 214 0.4
restaurants 1153 2.2 maintained 417 0.8 cheap 288 0.5 air 213 0.4
walking 1011 1.9 beach 398 0.8 smelled 284 0.5 refrigerator 205 0.4
area 863 1.6 access 398 0.8 kids 258 0.5 quality 203 0.4
parking 802 1.5 park 385 0.7 tv 256 0.5 decor 201 0.4
bathroom 764 1.4 floor 373 0.7 attractions 248 0.5 wait 200 0.4
pool 716 1.4 check in 369 0.7 water 247 0.5 freeway 198 0.4
free 712 1.3 spacious 365 0.7 coffee 244 0.5 elevator 196 0.4
convenient 708 1.3 bar 358 0.7 amenities 244 0.5 accommodation 114 0.2

9. ENTER 2015 Research Track Slide Number 9
Guest experience dimensions
Factor Loadings (N of Words = 34)
F1 Hybrid F2 Deals F3 Amenities F4 Family Friendliness F5 Core Product F6 Staff
clean 0.436 breakfast 0.517 close 0.39 family 0.509 room 0.552 helpful -0.462
smelled 0.423 airport 0.443 beach -0.366 kids 0.483 bathroom 0.42 friendly -0.511
dirty 0.395 free 0.435 pool -0.533 attractions 0.338 bed 0.322 staff -0.517
price 0.369 comfortable 0.409 suite 0.313 spacious 0.302
cheap 0.354 shuttle 0.393 service -0.338
carpet 0.349
sleep 0.323
expensive -0.313
shopping -0.326
view -0.377
restaurants -0.387
distance -0.459
location -0.492
walking -0.496

10. ENTER 2015 Research Track Slide Number 10
Hotel clusters by guest experience
Means of Cluster Centre
C1
(N=85)
C2
(N=101)
C3
(N=95)
C4
(N=87)
C5
(N=76)
C6
(N=85) F-ratio Sig.
Satisfaction
Rating
3.996 4.209 4.077 4.216 3.207 4.304 93.100 .000
Hybrid 0.575 -0.848 -0.170 0.548 1.054 -0.881 118.116 .000
Deals 0.969 -0.375 -0.261 0.739 -1.281 0.158 113.540 .000
Family
Friendliness
-0.976 0.311 -0.602 1.248 -0.081 0.075 102.835 .000
Core Product -0.863 -0.643 1.177 0.436 -0.291 0.126 102.267 .000
Staff 0.004 0.823 0.437 0.155 -0.372 -1.297 88.570 .000
Total N = 529

11. ENTER 2015 Research Track Slide Number 11
Hotel clusters in the semantic space

12. ENTER 2015 Research Track Slide Number 12
Hotel clusters by star ratings

13. ENTER 2015 Research Track Slide Number 13
Discussion
• Strong relationship exists between hotel guest satisfaction
and experience as reflected in online reviews.
• Hotel product can be distinguished by the combination of
satisfaction rating and guest experience.
• Terms/words that consumers use to express their
experiences certainly vary across different hotel clusters
and related segments.
• Offers a few insights for hoteliers to improve their
managerial strategies.

14. ENTER 2015 Research Track Slide Number 14
Conclusion, Limitations, and Future Research
• A promising direction to use CGC in hospitality
and tourism management – perceptual mapping
and segmentation.
• Limitations in the data
• Future research
– Structure of guest experience
– More meaningful hotel clusters