Model Recommendation System for Guided Tours based on Ubiquitous
and Context-Sensitive Computing
VICTOR DANIEL GIL-VERA1, JUAN CARLOS GIL-VERA2,
DEMETRIO ARTURO OVALLE-CARRANZA3
1Faculty of Engineering
Luis Amigo Catholic University
Transversal 51A #67B 90
COLOMBIA
2Department of Computer and Decision Sciences
National University of Colombia / Jaime Isaza Cadavid Polytechnic
Av. 80 #65 - 223, Villa Flora
COLOMBIA
3Department of Computer and Decision Sciences
National University of Colombia
Av. 80 #65 - 223, Villa Flora
COLOMBIA
Abstract: - The proposed model in this research, intended to work in a guided tour context, is based on developing
the tourist ontology in Python using the Owl-ready library, and describes the entities of the guided tour model.
The ontology allows us to apply the concepts of ubiquity and represent context sensitivity in three ways, with
geographical, temporal and environmental context. For the guided tour, the user's profile, preferences, emotional
state and evaluations of the visited places are considered, as well as the profile, itinerary and site characteristics,
the user's transportation preferences and the site's transportation characteristics. An ontology language was used
to model the concepts and characteristics of the guided tour system, which allows inferences to be made with
rules using the SWRL language with the Pellet reasoner. All models were evaluated using the RMSE metric and
the accuracy, recall and F1 score metrics have been used to evaluate the predictions. This paper concludes that,
among the recommender system models with collaborative filtering, the hybrid model obtained the best results
for RMSE and the other metrics of accuracy, recall, and F1 score. For this reason, it is one of the most widely
used recommender models in the industry.
Key-Words: - Context sensitivity, Guided tour, Recommendation model, Sentiment analysis, Ubiquity.
Received: June 11, 2024. Revised: September 13, 2024. Accepted: November 15, 2024. Published: December 19, 2024.
1 Introduction
This research aims to look for new ways to use the
information provided by mobile technologies in
information systems, to expand the range of
possibilities and actions by using the information of
the context in which the user is located and on which
the device where the system operates. People can
make use of environments that are conditioned to
support wireless network technologies, [1], not only
to connect with mobile devices but also to take
advantage of the benefits and novel aspects of
ubiquitous computing and artificial intelligence
approaches that are planned to be integrated into the
model of this research.
In recent years new approaches have emerged that
propose using a greater number of features and
properties that consider context information, as is the
case of ambient intelligence that aims to create
intelligent spaces where the environment adapts to
the demands and needs of people, [2]. The
information that comes from data sources such as
context has an intricate relationship that can be
puzzling for people, recommendation systems are
very useful information filtering tools to help in a
personalized way discover the information that may
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
238
Volume 6, 2024
be of interest within a space of possible options,
which facilitates the decision-making process, [3].
Mobile technologies allow people to be freely in
many connected places accessing various services,
this has become part of the spaces that we normally
attend and use daily. There is a paradigm called
context-sensitive computing that takes advantage of
this feature of the devices by taking information from
the environment surrounding the device, which is
constantly changing, to adapt it according to the
location of use, according to information from nearby
objects and people, and considering the changes of
these objects over time, [4]. The information
captured is known as context information and is
important because it allows the discovery of new
opportunities for the use of mobile technologies as
elements that can be integrated in different contexts
collaboratively and intelligently.
These new features offered by mobile
technologies are part of a very interesting behavior
that aims to make the interaction of the person with
the device and the system invisible, which changes
the way of seeing and using such devices. This
behavior is known as ubiquitous computing, [5].
Context-aware computing applied to information
systems is an object of study that covers a wide
multidisciplinary research space that has turned it
into a tool to understand and create system models
that adapt to the needs and profiles of users to provide
adequate services to the user within a dynamic
environment. Additionally, these models can be
applied transversally to various domains of interest in
systems that make use of the advantages and features
offered by mobile technologies in a personalized
way.
With the approaches and paradigms mentioned
above, belonging to mobile computing and artificial
intelligence, we seek to integrate them to propose a
recommendation model for guided tours that improve
the interaction of people with the surrounding
context, seeking that the system adapts to the
environment and the user in real-time and responds
intelligently and adaptively.
With the model of this proposal, we plan to
develop functional prototypes applied in the search
for solutions to problems of different categories of
interest, such as guided school visits to museums
oriented to learning, guided tours that need to orient
the motivation of visitors by showing sites and
information different from the exhausted traditional
tourist product such as the rich heritage, architecture
and landscape of the place and that differentiates it
from other sites. It is proposed to address the issue of
the management of procedures in a service provider
institution, since managers claim that management
can be facilitated and improved, through the use of
cell phones and e-mails, the assignment of
appointments and resources to users promptly.
2 Problem Formulation
One of the many possibilities for people to interact
with information systems is in the area of education.
When mobile technologies are available and
ubiquitous, students can access, share and build
knowledge easily in various places with different
adaptations. It is necessary to design and create new
models that facilitate this new way of learning and
that are different from the learning acquired with
traditional systems used in desktop computers.
Ubiquitous computing is an alternative to provide a
notion of learning motivated by mobility, ubiquity
and context sensitivity supported by the use of mobile
technologies.
This form of learning happens in a specific
context and fosters deeper and more meaningful
learning. There is a lot of promise and potential of
mobile and ubiquitous computing applied to the area
of learning, but this field is still little studied. In terms
of implementation, there is still a lot of ground to
cover, also in terms of reducing the barrier to
adoption and sustained use in learning practices, as
well as possible, [6].
Mobile devices are common in our daily lives, but
using them for education and learning may still take
a long time in our environment. The task of a
recommender system is to offer the user only what is
relevant to him and the concept of relevant
information has a relationship between the user's
profile and the content of the object of interest, [7]. It
is difficult to determine what is relevant to the user
and for this, some measures or factors must be
defined to help determine that relevance, for
example, the most searched and updated information
of the object of interest, specific information of the
object of interest, such as the lowest cost and best
quality, information of an object that belongs to
another person with similar characteristics to those of
the person who is looking for the object and
information of a similar object that the user has
already tried to search for in the past.
The problem here lies in the need to make many
decisions to arrive at a good recommendation. It is at
this point where the integration of ubiquitous and
context-sensitive computing with Artificial
Intelligence techniques is useful to obtain
information from the person and the context, and not
only from a set of data based only on the person's
preferences and profile.
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
239
Volume 6, 2024
2.1 Hypothesis
The possibilities of interaction that people have with
information systems can be expanded and enhanced
through a recommender system model using mobile
technologies and artificial intelligence techniques
that facilitate the decision-making process by using
context information based on ubiquitous and context-
sensitive computing to capture data, create models
and infer knowledge to reason and act according to
people's goals and needs.
2.2 Objective
Develop a ubiquitous, context-sensitive personalized
recommender system model for guided tour decision-
making. In the context-sensitive component of the
proposed model, for the user, the context related to
the user's preferences and emotional state was
considered; for the context of the environment, the
functionalities and features found in mobile devices
and their incorporation in the acquisition of context
information were considered. A recommendation
system model was created for guided tours that apply
context-sensitive computing on mobile devices.
The model has a customization component based
on the user model and the model of the sites of
interest. The prototype testing considered two or
three test cases applied to guided tours in the
educational, tourism, or service sectors. The
functional prototype of the recommendation system
based on the context-sensitive model personalized to
the user and the points of interest was implemented.
A performance evaluation of the prototype was
performed based on metrics applied to the case
studies.
The proposed model did not consider aspects
related to the planning of routes to recommend them
in the tours of a guided visit, it only recommends
points of interest that match the information of the
context and the user in a personalized way. In the
context-sensitive component of the proposed model,
for the user context, the context related to the
dynamic behavior and physiological state of the user
was not considered. In the context-sensitive
component of the proposed model, for the context of
the environment, the application of computer vision
techniques and the Internet of Things was not
considered. In the recommender system, aspects
related to user privacy management were not
considered.
3 Proposed model
This section presents the characterization of the
entities and concepts that are part of the model of the
recommendation system for guided tours such as the
user, their generic preferences, the user's reviews
about a site of interest, the site of interest and the
schedule of activities that are done at the site of
interest. In this characterization, we will expose the
user model and its personalization, the place model
(point of interest POI), [8], and the context model
applied to the contextualized guided tour model.
Then, the tourist ontology is presented, which forms
the set of concepts and categories in the
contextualized guided tour model indicating their
properties and relationships, in addition to the
definition of inference rules that validate the
ontology in the proposed scenarios.
From the ontology developed, several models of
recommender systems are shown that are based on
simulated data that starting from the ontology are
adapted to data models in pandas to be processed in
Python to be applied in the different approaches of
recommender systems addressed in the proposal. In
this work we will consider the application of the
model in several recommender system approaches,
such as; user-based collaborative filtering,
knowledge-based filtering using user profile
information, filtering using a K-means algorithm and
filtering based on singular value decomposition and
finally filtering in a hybrid recommender system.
The model offers the possibility of using user
reviews in the machine learning technique of
sentiment analysis to determine the level of user
acceptance of the site of interest. Finally, we will
expose the metrics used with the results obtained that
allow us to validate the model.
3.1 Model of the recommendation system for
guided tours
This situation shows the need for tourism systems to
know the needs of users and be prepared to receive
them with a variety of personalized and updated
services according to this characteristic, [9].
Responding to this need, we intend to make a
representation of a model for visits that, in addition
to considering the place and the user, considers the
user's preferences and the characteristics of the place,
such as the schedules of its events, so that they can be
considered in a more personalized recommendation
according to the user's needs. The proposed model
considers the following elements as a starting point:
Generic preference: Constitutes the general
preferences of the user to represent his itinerary since
it constitutes the time he would like to leave, the
money he is willing to spend, the time he would like
to return and the date of such preference. For each
Generic Preference, it is necessary to clarify that this
is different for each day, so the date must be defined.
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
240
Volume 6, 2024
User: This concept represents the user's
information; it also indicates the current location of
the place where the user is. The user can make many
reviews and ratings of each place visited.
Location: Represents the point of interest, in
addition to its basic data it considers the sum of all
the ratings made by all the users, as well as the total
number of users that have voted. This data is used to
calculate the metrics of the best-rated places to show
them in the recommendations. It also has a textual
overview for use in collaborative filtering using an
algorithm that calculates the distance between the
places that have the most similar overview to
recommend them according to that characteristic.
Schedule: This concept contains the properties to
represent an event or an activity performed in a place.
A place can have many schedules. It is important to
clarify that in this model we consider whether an
event can be attended by minors with underage
property. Fig. 1, shows the initial model for the
recommendation system model for guided tours. This
model makes it possible to represent the places that
are outside in the open space, inside another larger
place, and the places that represent a service inside an
organization. It is necessary to clarify that, to model
the user and the way to personalize it, this work will
deepen in the representation of their preferences that
include their emotional state, their social state with
their company to travel, their preferences to transport
themselves to a place, the topics of interest to visit a
particular place and the preferences of the context.
Likewise, to model the place and how to adapt it
to the user, this work will include the characteristics
of the place that are shaped by the transportation
preferences to get to the place, the topic of interest
that labels the place, and the information of the
current context at the time of visiting the place.
Fig. 1: Model of the recommendation system for
guided tours.
3.2 User model and its customization
Mobile applications allow access almost anytime and
anywhere, to the user's information and preferences,
as well as their location, this information can be used
and filtered avoiding congestion in the process of
accompaniment during all the activity related to a
visit to a particular place, [10].
This model seeks to represent the user's
preferences, considering his emotional state with the
Emotional State concept, his social state with the
Companion concept, to represent the transportation
preferences with the Transportation Pref concept, to
know the user's topic of interest to search for a place
that has this topic, this is represented with the Topic
concept and finally to represent the context which can
be geographic, temporal and environmental,
represented in the concepts; Geographical, Temporal,
and Environmental respectively as shown below.
These concepts will allow to personalize the user's
recommendations, to have a more complete profile,
which considers both their availability and their
emotional state, as well as their interests and
preferences to move and the environmental
conditions of the places they wish to visit at a given
time. As mentioned in the previous model, it allows
the user to rate and generate reviews of the places
visited. All this enriches the proposed model and
allows the application of recommendation systems
and machine learning techniques.
The user model and its customization are shown
in Fig. 2. Each of its concepts and attributes are
detailed below. Starting from the concepts previously
explained in the previous section, namely; User and
Generic Preference, which have already been
mentioned.
Fig. 2: User profile model.
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
241
Volume 6, 2024
Preference: This concept represents the user's
preferences which can be; Companion, Context,
Transportation Pref, Emotional State and Topic.
Companion: This concept is used to indicate the
social status of the user in his surrounding
environment, this can be divided into three types;
Single, to indicate that he is traveling alone, Group to
indicate that he is traveling in a group, and Couple to
indicate that he is traveling as a couple.
Context: This concept represents the context
information. It is divided into Environmental,
Geographical and Temporal.
Transportation Pref: This concept is used to
indicate the user's preferences to travel to a place. It
has as properties; required time, to indicate the time
he is willing to spend to get to a place and cost_transp
to indicate the amount of money he is willing to
spend on transportation. This concept has the
following types of means of transportation to get to a
place; Walking, for walking, Public to indicate that
you would like to travel by a public means of
transportation, Bike to indicate that you would like to
arrive by motorcycle and Private to indicate that you
would like to travel by a private means of
transportation.
Emotional State: Indicates the user's emotional
state, and is divided into the following types; Happy,
Sad, Angry, Calm, Surprised and Tired. This model
allows adding new emotional states such as Normal.
Topic: This concept is intended to be managed as
a label to identify places of interest and is divided into
the following types: Accommodation, Services,
Transportation, Food, National Culture, Activity,
Shopping, Entertainment, Natural Landscape and
Cultural Landscape. It is possible to add new topics.
3.3 Model of the site and its adaptation
Modern smartphones offer very interesting
functionalities that allow taking advantage of
location-based services or LBS, which determine the
user's location to provide personalized services based
on that location, [11]. This indicates that it is very
important to have location information not only with
its location but also with information that enriches a
better adaptation with the user. In the proposed
model, an adaptation of the place is presented
according to a set of characteristics that are
concentrated in the concept called Characteristic, and
that correspond with the user's preferences to allow
obtaining a better recommendation, that is to say that
the user's preferences are considered in terms of
transportation and topic preferences of the place and
the context information that corresponds with that of
the place and the user to better adapt such
personalization. Let's look at the components that
make up the place model, see Fig. 3. Each of its
concepts and attributes are detailed below. Starting
from the concepts previously explained in the
previous section, namely; Location and Schedule,
which have already been mentioned.
Location: In addition to considering what has
already been explained in the initial model about this
concept. It is added that this concept can be of three
types; Inside, Outside and Service.
Characteristic: This concept represents the
characteristics of the place which can be; Context,
Transportation Pref and Topic.
Context: This concept represents the information
of the context of the place. It is divided into;
Environmental, Geographical and Temporal.
Transportation Pref: This concept is used to
indicate the characteristics of arriving at a place. It
has as properties; required time, to indicate the time
required to get to a place and cost_transp to indicate
the cost to get to that place using the selected means
of transportation. This concept has the following
types of means of transportation to get to a place;
Walking, for walking, Public to indicate that you
would like to travel by a public means of
transportation, Bike to indicate that you would like to
arrive by motorcycle and Private to indicate that you
would like to travel by a private means of
transportation.
Topic: This concept is intended to be managed as
a label to identify places of interest and is divided into
the following types: Accommodation, Services,
Transportation, Food, National Culture, Activity,
Shopping, Entertainment, Natural Landscape and
Cultural Landscape. It is possible to add new topics.
Fig. 3: Model of the site and its adaptation
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
242
Volume 6, 2024
4 Ontology
The conceptualization of the proposed ontology
consists of the following activities: construction of
the glossary of terms, construction of the taxonomy
of concepts, construction of the diagram of binary
relations, construction of the dictionary of concepts,
description of the binary relations in detail,
description of the instance attributes in detail,
definition of rules, and definition of instances. Table
1 presents the concepts belonging to the domain of
the recommendation model for guided tours and
composes the ontology.
Table 1. Ontology concepts
Category
Concepts
User
User, identity, current_location, name_user,
gender, age, education, income_level,
GenericPreference, departure_time, budget,
arrival_time, date, Review, id_location, review
Location
Location, name_location, address, image,
sum_scores, vote_count, overview, Schedule,
date_schedule, opening_time, closing_time, event,
cost, underage, InsideLocation, OutsideLocation,
ServiceLocation.
Preference
EmotionalState, Happy, Sad, Angry, Calm,
Surpriced, Normal, Tired.
The knowledge representation of the proposed
system was given the name of tourist ontology (Fig.
4), and represents the knowledge in detail, to relate it
with its defined elements and reason about this
knowledge, in this case, Owl ready was used and 2
classes were created to manage the user, 3 classes to
manage the user's history. 7 classes were created to
manage the types of tourist places. 2 classes were
created to manage the scheduling of the events of the
places.
2 classes were created to represent the user's
preferences and the characteristics of the place. 8
classes were created to manage the user's emotional
state. 4 classes were created to manage the social
profile of the user. 5 classes were created to manage
the user's transportation preferences. 13 classes were
created for the accommodation topic.
12 classes were created for the Services topic. 17
classes were created for the Transportation topic. 9
classes were created for the Food topic. 9 classes
were created for the topic of National Culture. 9
classes were created for the Activity topic. 40 classes
were created for the Shopping topic. 25 classes were
created for the entertainment topic.
21 classes were created for the natural landscape
topic. 43 classes were created for the Cultural-
Landscape topic. 5 classes were created to manage
the geographic context. 2 classes were created to
manage the temporal context. 34 binary relationships
were created between all the defined classes. 37
object-property and datatype-property properties
were created. The implementation of the ontology
can be seen in the annex. The implementation of the
ontology can be seen in, [15].
Fig. 4: Tourist ontology
Fig. 5 shows the results of applying the 5-fold cross-
validation technique for the hybrid model composed
of a content-based recommender system and a
collaborative recommender system using singular
value decomposition, we obtained a mean RMSE
value of 1.2478, which exceeds that obtained in the
model using singular value decomposition with an
RMSE of 1.2490, and which had been the best so far.
In addition, in fold number 3 an F1-score of 0.96 was
obtained, the best of all and which corresponds to an
RMSE of 1.1936, thus it can be concluded that the
filtering model based on hybrid recommender
systems outperforms all previously seen models and
for this reason, it is one of the most used in the
industry.
(1)
(2)
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
243
Volume 6, 2024
(3)
Fig. 5: 5-fold cross-validation technique.
5 Conclusion
This research proposes a recommendation model that
can be applied in the field of tourism for guided tours,
which can be used in tours for visits to tourist centers
with places open to the outside, closed places such as
museums, and in tours in places that offer several
locations with services that involve search and
decision making by the user, such as a shopping mall.
The model allows making use of the user's
information and preferences, the information and
characteristics of the place, as well as the information
of the context at the time of the tour so that the model
makes use of ubiquitous computing, and can also be
adapted in models of recommendation systems that
work with collaborative filtering to recommend
places of interest.
The proposed model presents as one of the main
contributions the modeling based on ontologies and
proposes the tourist ontology for guided tours that
allows representing the knowledge related to the
user's profiles and preferences, the profiles and
characteristics of the place and contextual
information. The ontology allows considering the
emotional state, social and transportation preferences
of the user, as well as the topics of interest to label a
place to visit. Likewise, the ontology considers the
characteristics, events and transportation preferences
of the place. The ontology also considers context
information for both the user and the place; temporal,
geographic and environmental context.
Ubiquitous computing frees users from the
limitations of time and space, providing opportunities
for users to access and enjoy the services offered in
places no matter where they are physically by
accessing the technologies that allow mobile devices,
all these possibilities can be exploited with the ideas
presented in the proposed thesis model to develop
systems that depending on the current location of the
user, automatically displays information about the
different places nearby, their services and events. As
well as recommending other places of interest
according to the topics selected by the user and
having the advantage of knowing the information of
its context to get better recommendations.
As an artificial intelligence technique to
personalize recommendations based on the user's
context, profile and preferences, a knowledge-based
recommender system model has been used to obtain
intermediate recommendations of places by querying
datasets containing relevant information obtained
from the user either as a query or using an application
interface. In this way, the system searches through
the data, preferences and profile information to return
results that match a set of rules or guidelines on how
the results should be, or an example of a
recommended place.
References:
[1] S. E. Restrepo Medina, “Ambient intelligence
model based on the integration of wireless
sensor networks and intelligent agents,”
Bdigital, Vol. 1, No. 1, 2012, pp. 1-126.
https://repositorio.unal.edu.co/bitstream/handle/
unal/10956/43926734.2012.pdf?sequence=1&i
sAllowed=y
[2] B. Zhang, C. Yin, B. David, Z. Xiong, & W.
Niu, “Facilitating professionals’ work-based
learning with context-aware mobile system,”
Science of Computer Programming, Vol. 129,
No. 1, 2016, pp. 3-19.
https://doi.org/10.1016/j.scico.2016.01.008
[3] V. Santos, “Use of social paradigms in mobile
context-aware computing,” Procedia
Technology, Vol. 9, No. 1, 2013, pp. 100-113.
https://doi.org/10.1016/j.protcy.2013.12.011
[4] Y. Kano, & T. Nakajima, “A novel approach to
solve a mining work centralization problem in
blockchain technologies,” International Journal
of Pervasive Computing and Communications,
Vol. 14, No. 1, 2018, pp. 15-32.
https://doi.org/10.1108/IJPCC-D-18-00005
[5] S. Ansari, Building a recommendation engine
with Scala, Packt Publishing, 2016.
[6] Y. Hu, S. Gao, K. Janowicz, B. Yu, W. Li, & S.
Prasad, “Extracting and understanding urban
areas of interest using geotagged photos,”
Computers, Environment and Urban Systems,
Vol. 54, No. 1, 2015, pp. 240-254.
https://doi.org/10.1016/j.compenvurbsys.2015.
09.001
[7] D. Buhalis, & R. Law, “Progress in information
technology and tourism management: 20 years
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
244
Volume 6, 2024
on and 10 years after the Internet—the state of
eTourism research,” Tourism Management,
Vol. 29, No. 4, 2008, pp. 609-623.
https://doi.org/10.1016/j.tourman.2008.01.005
[8] W. Höpken, M. Fuchs, M. Zanker, & T. Beer,
“Context-based adaptation of mobile
applications in tourism,” Information
Technology & Tourism, Vol. 12, No. 2, 2010,
pp. 175-195.
https://doi.org/10.3727/109830510X128879710
02783
[9] C.-C. Chen, & J.-L. Tsai, “Determinants of
behavioral intention to use the personalized
location-based mobile tourism application: An
empirical study by integrating TAM with
ISSM,” Future Generation Computer Systems,
Vol. 96, No. 1, 2019, pp. 628-638.
https://doi.org/10.1016/j.future.2017.02.028
[10] S. Raza, & C. Ding, “Progress in context-aware
recommender systems—An overview,”
Computer Science Review, Vol. 31, 2019, pp.
84-97.
https://doi.org/10.1016/j.cosrev.2019.01.001
[11] D. Schürholz, S. Kubler, & A. Zaslavsky,
“Artificial intelligence-enabled context-aware
air quality prediction for smart cities,” Journal
of Cleaner Production, Vol. 271, 2020.
https://doi.org/10.1016/j.jclepro.2020.121941.
[12] N. M. Villegas, C. Sánchez, J. Díaz-Cely, & G.
Tamura, “Characterizing context-aware
recommender systems: A systematic literature
review,” Knowledge-Based Systems, Vol. 140,
2018, pp. 173-200.
https://doi.org/10.1016/j.knosys.2017.11.003.
[13] W. Zheng, Z. Liao, & Z. Lin, “Navigating
through the complex transport system: A
heuristic approach for city tourism
recommendation,” Tourism Management, Vol.
81, 2020.
https://doi.org/10.1016/j.tourman.2020.104162.
[14] P. T. Palomino, A. M. Toda, L. Rodrigues, W.
Oliveira, L. Nacke, & S. Isotani, “An ontology
for modelling user’ profiles and activities in
gamified education,” Research and Practice in
Technology Enhanced Learning, Vol. 18, p.
018, 2022.
https://doi.org/10.58459/rptel.2023.18018.
[15] V. D. Gil-Vera., J.C Gil-Vera, D. Ovalle-
Carranza, “Ontology”, 2024. [Online].
Available:
https://github.com/victorgil777/Ontology/blob/
main/Ontology.txt
Contribution of Individual Authors to the
Creation of a Scientific Article (Ghostwriting
Policy)
The authors equally contributed in the present
research, at all stages from the formulation of the
problem to the final findings and solution.
Sources of Funding for Research Presented in a
Scientific Article or Scientific Article Itself
No funding was received for conducting this study.
Conflict of Interest
The authors have no conflicts of interest to declare
that are relevant to the content of this article.
Creative Commons Attribution License 4.0
(Attribution 4.0 International, CC BY 4.0)
This article is published under the terms of the
Creative Commons Attribution License 4.0
https://creativecommons.org/licenses/by/4.0/deed.en
_US
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS,
COMPUTATIONAL SCIENCE AND SYSTEMS ENGINEERING
DOI: 10.37394/232026.2024.6.20
Victor Daniel Gil-Vera, Juan Carlos Gil-Vera,
Demetrio Arturo Ovalle-Carranza
E-ISSN: 2766-9823
245
Volume 6, 2024
