Hotel room personalization via ontology and rule-based reasoning

• DOI: https://doi.org/10.1108/IJWIS-02-2022-0045
• Published date: 01 September 2022
• Date: 01 September 2022
• Pages: 369-387
• Subject Matter: Information & knowledge management,Information & communications technology,Information systems,Library & information science,Information behaviour & retrieval,Metadata,Internet
• Author: Ronald Ojino,Luisa Mich,Nerey Mvungi

Hotel room personalization via

ontology and rule-based reasoning

Ronald Ojino

College of Information and Communication Technologies,

University of Dar es Salaam, Dar es Salaam, United Republic of Tanzania

Luisa Mich

Department of Industrial Engineering, University of Trento, Trento, Italy, and

Nerey Mvungi

College of Information and Communication Technologies,

University of Dar es Salaam, Dar es Salaam, United Republic of Tanzania

Abstract

Purpose –The increasingly competitive hotel industry and emerging customer trends where guests are

more discerning and want a personalized experience has led to the need of innovative applications.

Personalization is much more important for hotels, especially now in the post-COVID lockdown era, as it

challenges their businessmodel. However, personalization is difficult to design and realize due to the variety

of factors and requirements to be considered. Differences are both in the offer (hotels and their rooms) and

demand (customers’profiles and needs) in the accommodation domain. As for the implementation, critical

issues are in hardware-dependent and vendor-specific Internet of Things devices which are difficult to

program.Additionally, there is complexity in realizing applicationsthat consider varying customer needs and

context via existingpersonalization options. This paper aims to propose an ontologicalframework to enhance

the capabilities of hotels in offering their accommodation and personalization options based on a guest’s

characteristics,activities and needs.

Design/methodology/approach –A research approach combining both quantitative and qualitative

methods was used to developa hotel room personalization framework. The core of the frameworkis a hotel

room ontology (HoROnt) that supports well-definedmachine-readable descriptions of hotel rooms and guest

profiles. Hotel guest profiles are modeled via logical rules into an inference engine exploiting reasoning

functionalitiesused to recommend hotel room services and features.

Findings –Both the ontology andthe inference engine module have been validated with promisingresults

which demonstrate high accuracy. The framework leverages user characteristics, and dynamic contextual

data to satisfy guests’needsfor personalized service provision. The semantic rulesprovide recommendations

to both new andreturning guests, thereby also addressing thecold start issue.

Originality/value –This paper extends HoROntin two ways, to be able to add: instances of the concepts

(room characteristics and services; guest profiles), i.e. to create a knowledge base, and logical rules into an

inference engine, to model guests’profiles and to be used to offer personalized hotel rooms. Thanks to the

standards adopted to implementpersonalization, this framework can be integrated into existing reservation

systems. It can also be adapted for any type of accommodation since it is broad-based and personalizes

varying featuresand amenities in the rooms.

Keywords Personalization, Semantic rules, Ontology, Tourism, Guest, Sensors

Paper type Research paper

1. Introduction

The hotel industry is a critical part of the travel and tourism sectors. Its impact on the

economic and social development of a nation can be quite huge, given that it presents

Ontology- and

rule-based

reasoning

369

Received28 February 2022

Revised26 May 2022

13July 2022

Accepted8 August 2022

InternationalJournal of Web

InformationSystems

Vol.18 No. 5/6, 2022

pp. 369-387

© Emerald Publishing Limited

1744-0084

DOI 10.1108/IJWIS-02-2022-0045

The current issue and full text archive of this journal is available on Emerald Insight at:

https://www.emerald.com/insight/1744-0084.htm

opportunities such as creation of jobs, opening a nation to investments, protecting cultural

values and promoting entrepreneurism (World Travel and Tourism Council [WTTC],2016).

The hotel room is a fundamental product in the travel cycle, and it greatly impacts the

experience of guests. Guestsdevote their time in the hotel rooms, also to relax and take time

off after a day of business work or tourism. Most travelers today seek hotel accommodations

with more independence, individualized attention in the services and experiences offered

and a homely atmosphere. Personalizationhelps hotels provide better services to customers

while improving efficiencies. The trend of guests seeking personalized hotel experiences

based on their unique preferencesrequires hotels to innovate to meet this need (AmadeusIT

Group, 2010). The demandfor personalization of hotel rooms is also driven bythe emerging

nations’burgeoning middle-class, which is more diverse and has discretionary income, as

well as the generation of millennials who crave instant gratification, exploration and smart

spending (Richard, 2017). However, many hotels still provide the same lodging experience

for all guests, a “one size-fits-all”approach, without taking into account the varying needs,

preferences, demographicsand backgrounds of the guests.

Hotel room personalization is challenging for many reasons. On one hand, new

technologies can be used to this end; among them, Internet of Things (IoT) solutions.

However, IoT devices are hardware dependent, vendor specific and not context aware (Du

et al.,2016), implying difficulty in programming and limitation of their adoption. On the

other hand, existing personalization systems do not always consider a user’s context (Lian

and Hui, 2014), which is keyin providing effective personalization solutions.The situation is

exacerbated with the many options available from various hotel service providers. A large

number of information and communication technology (ICT) systems and applications are

used in a hotel, supporting front-office, reservation, housekeeping, etc. (Quarshie and

Amenumey,2016). Given the high number of ICT systems and the large amounts of

heterogeneous data generated from various sources in hotels, there is a need for

interconnectionof these platforms, data integration and automated data processing.

The use of ontologies has emerged as an important component in offering personalized

services in a range of systems including e-learning, library, image retrieval, route-planning,

care for chronic patients,etc. However, in the hotel room domain, very few studies havebeen

carried out to personalize services. Existing hotel and accommodation ontologies, such as

Hontology (https://hdl.handle.net/21.11129/0000-000B-D314-0) and Acco (http://ontologies.

sti-innsbruck.at/acco/ns.html), model the hotel in general, and lack important concepts and

properties for the hotel room domain.This hampers the goal of ensuring that all involved in

communication within the hotel room, such as computing systems and humans, speak a

common language through shared and consistent meanings of terms. Furthermore,

ontologies alone do not enable all the knowledge related to a given domain to be modeled

(Boufrida and Boufaida,2020).

This paper proposes a hotel room personalization framework based on the hotel room

ontology (HoROnt), and an attached inference engine. To this end, the core ontology,

modeling the hotel room domain (Ojino et al., 2021),available at Github (https://github.com/

ronojinx/ontology/blob/main/HotelroomOnt%20(2).owl),is: populated to create a knowledge

base storing instancesof the ontology concepts; used as input for a new module,a rule-based

inference engine. The knowledge base allows to describe both room characteristics and

services, and guest profiles.To support hotel room personalization, the framework considers

individual guest characteristics, preferences and responds to changing contexts. Hotel

guests are modeled via logical rules into the inference engine exploiting reasoning

functionalities to be used to recommend hotel room services and features. Rules have been

defined by analyzingtextual documents and interviewing hotel domainexperts.

IJWIS

18,5/6

370