FLORA: a hierarchical fuzzy system for online accommodation review analysis
| Published date | 12 August 2019 |
| Pages | 347-367 |
| Date | 12 August 2019 |
| DOI | https://doi.org/10.1108/JSIT-03-2018-0046 |
| Author | Thara Angskun,Jitimon Angskun |
| Subject Matter | Information & knowledge management,Information systems,Information & communications technology |
FLORA: a hierarchical fuzzy
system for online accommodation
review analysis
Thara Angskun and Jitimon Angskun
Suranaree University of Technology, Nakhon Ratchasima, Thailand
Abstract
Purpose –This paper aims to introduce a hierarchicalfuzzy system for an online review analysis named
FLORA. FLORA enables tourists to decide their destination without reading numerous reviews from
experienced tourists. It summarizes reviews and visualizes them through a hierarchical structure. The
visualization doesnot only present overall quality of an accommodation, but it alsopresents the condition of
the bed, hospitalityof the front desk receptionist and much more in a snap.
Design/methodology/approach –FLORA is a complete system which acquires online reviews,
analyzes sentiments, computes feature scores and summarizes results in a hierarchical view. FLORA is
designed to use an overallscore, rated by real tourists as a baseline for accuracycomparison. The accuracy of
FLORA has achievedby a novel sentiment analysis process (as part of a knowledgeacquisition engine) based
on semantic analysis and a novel rating technique, called hierarchical fuzzy calculation, in the knowledge
inferenceengine.
Findings –The performancecomparison of FLORA against related work has beenassessed in two aspects.
The first aspect focuses on review analysis with binary format representation. The results reveal that the
hierarchical fuzzy method, with probability weighting of FLORA, is achieved with the highest values in
precision, recall and F-measure. The second aspect looks at review analysis with a five-point rating scale
rating by comparing with one of the most advanced research methods, called fuzzy domain ontology. The
results reveal that the hierarchical fuzzy method, with probability weighting of FLORA, returns the closest
resultsto the tourist-defined rating.
Research limitations/implications –This research advances knowledge of online review analysis
by contributing a novel sentiment analysis process and a novel rating technique. The FLORA system
has two limitations. First, the reviews are based on individual expression, which is an arbitrary
distinction and not always grammatically correct. Consequently, some opinions may not be extracted
because the context free grammar rules are insufficient. Second, natural languages evolve and
diversify all the time. Many emerging words or phrases, including idioms, proverbs and slang, are
often used in online reviews. Thus, those words or phrases need to be manually updated in the
knowledge base.
Practical implications –This research contributes to the tourism business and assists travelers by
introducing comprehensive and easy to understand information about each accommodation to travelers.
Although the FLORA system was originally designed and tested with accommodation reviews, it can
also be used with reviews of any products or services by updating data in the knowledge base. Thus,
businesses, which have online reviews for their products or services, can benefit from the FLORA
system.
Originality/value –This research proposes a FLORA system which analyzes sentiments from online
reviews,computes feature scores and summarizes resultsin a hierarchical view. Moreover,this work is able to
use the overall score, rated by real tourists, as a baseline for accuracy comparison. The main theoretical
implication is a novel sentiment analysis process based on semantic analysis and a novel rating technique
called hierarchicalfuzzy calculation.
Keywords Tourist preference, Accommodation reviews, Semantic analysis,
Hierarchical fuzzy system
Paper type Research paper
Hierarchical
fuzzy system
347
Received26 March 2018
Revised12 December 2018
11May 2019
20June 2019
Accepted22 August 2019
Journalof Systems and
InformationTechnology
Vol.21 No. 3, 2019
pp. 347-367
© Emerald Publishing Limited
1328-7265
DOI 10.1108/JSIT-03-2018-0046
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1328-7265.htm
Introduction
Currently, most tourismbusinesses have transformed themselves into electronicbusinesses,
called e-tourism. E-tourism is so popular that a dedicated top-level domain name called “.
travel”has been introduced as an alternativeto “.com”. E-tourism enables tourists to reserve
a hotel, book a flight or rent a car more easily and quickly. In addition, e-tourism is alsoan
important factor in increasing world travel because tourists have a greater opportunity to
learn tourism information (ITB Berlin,2015). There are many e-tourism systems that collect
data from tourists. Unfortunately, those data have rarely been processed in a meaningful
way according to the tourist’s requirement. For example, e-tourism systems store
experienced tourists’reviews about tourist attractions, travel accommodation or
restaurants. These reviews are useful for other tourists in helping to develop their travel
plans (Wang, 2015). However, they must read many reviews by themselves and decide
whether they should go based on their preferences(Alaei et al., 2019;Budhi et al., 2017). The
existing e-tourism systems provided only an overall rating of each destination from these
reviews (Nysveen and Pedersen, 2014). There is no breakdown of rating, i.e. the overall
rating of a hotel cannot inform about air conditioning in the guest room, cleanliness of the
bathroom, etc. These details are needed for decision-making by tourists to select their
destinations (Burke,2002).
Hence, this article presentsa hierarchical fuzzy system for online review analysis named
FLORA (Fuzzy Logic-based Online Review Analysis). FLORA focuses on the design of a
semantic analysis approach for natural language understanding of the accommodation
reviews. This systemintroduces a fuzzy-based method for calculatinga tourist’s satisfaction
level on each extracted feature and on the entire review in the numeric score (five-point
rating scale). The system visualizes the accommodationfeature relationships in a hierarchy
as illustrated in Figure 1.
Figure 1.
An example of
FLORA output in a
hierarchicalview
Location
Accommodation
Service
Room
Overall rating = 3.2
(From 122 criticisms)
Location = 4.82
(From 79 criticisms)
Service = 1.78
(From 8 criticisms)
Room = 2.1
(From 35 criticisms)
-Bellboy = 2.2 (From 1 criticism)
-Concierge = 1 (From 2 criticisms)
-Employee = 2 (From 2 criticisms)
-EnglishNewspaper = 0 (From 0 criticism)
-FaxMachine = 0 (From 0 criticism)
. . .
-AirCondition = 1.2 (From 2 criticisms)
-AlarmClock = 0 (From 0 criticism)
-Area = 2 (From 4 criticisms)
-Balcony = 0 (From 0 criticism)
-Bed = 3 (From 2 criticisms)
JSIT
21,3
348
To continue reading
Request your trial