=Paper=
{{Paper
|id=Vol-2482/paper2
|storemode=property
|title=User Profile Ontology to Support Personalisation for E-Coaching Systems
|pdfUrl=https://ceur-ws.org/Vol-2482/paper2.pdf
|volume=Vol-2482
|authors=Puspa Pratiwi,Yue Xu,Yuefeng Li,Stewart G. Trost,Kelly M. Clanchy,Dian Tjondronegoro
|dblpUrl=https://dblp.org/rec/conf/cikm/Pratiwi0LTCT18
}}
==User Profile Ontology to Support Personalisation for E-Coaching Systems==
https://ceur-ws.org/Vol-2482/paper2.pdf
User Profile Ontology to Support Personalization for
E-Coaching Systems
Puspa S. Pratiwi∗ Yue Xu Yuefeng Li
Queensland University of Technology Queensland University of Technology Queensland University of Technology
Brisbane, Australia Brisbane, Australia Brisbane, Australia
p.pratiwi@qut.edu.au
Stewart G. Trost Kelly M. Clanchy Dian Tjondronegoro
Queensland University of Technology Griffith University Southern Cross University
ABSTRACT the working definition for the use of Information and Communica-
In recent years, e-coaching systems have played an increasingly tion Technologies (ICTs) to support or improve health and health-
significant role in promoting a healthy lifestyle and positive behav- care[26]. These technologies were used in promoting physical
ior change. Research efforts have grown to provide more useful activity[10], providing personalized feedback for eating behavior[23],
and effective e-coaching systems for research or other purposes. as well as other clinical domains such as treating insomnia[2]. E-
The implementation of e-coaching systems resulting from these coaching systems were inspired, firstly, by the need to model the
efforts utilizes several techniques including Artificial Intelligence human "intelligence" in a technology which can continuously mon-
(AI) methodologies. This study proposes a personalised approach to itor its users’ activities and surroundings, detects situations where
support an e-coaching system that is tailored to the user’s charac- intervention would be desirable and offers prompt assistance [19].
teristics. A key component of this system comprises an ontological Previous works in e-coaching systems are based on a one-size-fits-
model of the user profile. The objective of this research was to all approach to delivering the coaching actions irrespective of the
propose an ontology that is able to collect and analyze the user user’s conditions, goals, knowledge, abilities, or preferences. This
related information as well as customize the profiles with the most problem of delivering the same coaching actions to all users can be
appropriate coaching recommendation or materials. The ontology addressed by using personalization strategies to adapt the coaching
employed in this study was developed using the OWL (Ontology process or plan to the user’s requirements. Therefore, one of the key
Web Language), a knowledge representation language for author- issues in the next generation of e-coaching systems is to identify the
ing ontologies. The effectiveness of this approach will be enhanced user’s characteristics(e.g., health conditions, goals). However, these
by filtering the information that was presented to the users. systems are limited in their ability to provide adequate personaliza-
tion of the e-coaching activities. Thus, this raises the challenge of
KEYWORDS how to design for a user profile model which is lacking in current
e-coaching systems.
Ontology engineering, User profile, Knowledge representation
In the light of the above challenges to current e-coaching systems,
this study aims to address some of the challenges of providing per-
sonalized e-coaching for users with a specific condition, such as
users with impairments, through the ontological user profiling. User
profiling is the process of designing a structure that will capture
1 INTRODUCTION the attributes determined from the relevant user’s characteristics.
Researchers have started to explore the potential benefit of coaching The result of user profile modeling is the definition of a user model,
to facilitate the promotion of healthy behaviors and help individu- a uniform template of the attributes that should be included for
als to achieve health-related goals[13]. Coaching that is applied in each user[22]. The task of representing user profiles in a model
health domain is often referred to as health coaching, consequently that integrates diverse kinds of data provided by various sources
defined as the practice of the health education and promotion within motivates the employment of ontological technologies within this
a coaching context to improve the well-being of individuals and to study. Specifically, ontologies are recognized in supporting the flex-
facilitate the achievement of their health-related goals[8]. ible use and reuse of captured information also the integration of
With the proliferation of digital technologies, coaching has taken collected information.
place as a potential strategy that was used in technologies which To address the limitations of previous e-coaching systems, the sys-
facilitate healthy behavior change. E-health or electronic health is tem proposed in this paper solves the problem that was only par-
tially addressed in the models previously discussed in the literature.
∗ The developed ontology is the module that will be used by an
e-coaching system to support an intervention program from our
Copyright © CIKM 2018 for the individual papers by the papers' domain experts [3].
This paper focuses on the modeling of user profiles to support spe-
authors. Copyright © CIKM 2018 for the volume as a collection
cific inference within a comprehensive ontology model of the users’
by its editors. This volume and its papers are published under
the Creative Commons License Attribution 4.0 International (CC
BY 4.0).
P.S.Pratiwi et al.
related knowledge for ontology. The remainder of the paper is or- from the user either explicitly by direct human intervention or im-
ganized as follows: Section 2 discusses existing related work within plicitly by automatically monitoring the user’s actions or behavior.
the area of ontological user profile modeling and personalization. In the profile construction phase, both types of data are combined
Section 3 explains how the proposed ontology was developed. Sec- to form information that is input to the system’s personalization
tion 4 focuses on the use of ontological user profile modeling for component. The user’s profile is, therefore, a record of his or her
user personalization. Section 5 introduces the area of rule-based unique characteristics such as:
personalization, where a new personalization component is de-
scribed. Section 6 discusses the system implementation, preceded • Impairment characteristics
by a case study presenting the potential of the ontology model • Motivation readiness characteristics
and personalization component. Section 7 concludes the paper and • Socio-demographic characteristics
provides a summary of future work. • Health condition characteristics
This information is then stored as a concept profile. By applying
2 RELATED WORKS the profile to a system or application, such as e-coaching system
2.1 Personalization in e-coaching systems [9], personalized e-coaching (e.g., strategies, goals, exercise) can
then be provided to the user to improve his or her health condition.
The main advantage of a personalized e-coaching system is the
ability to provide or offer feedback, question or advice that is tai-
lored to the individual’s characteristics in a specific situation[9]. 3 METHODOLOGY: ONTOLOGY
Personalization in e-coaching systems depends on the user’s profile ENGINEERING PROCESS
and contextual data, coaching plan and process, and also historical This section discusses the detailed development process of the
user’s feedback. When the available feedback or other contextual user profile ontology. An ontology engineering methodology[25]
data are not available, it becomes more difficult to produce accurate is adopted. The choice of this methodology for developing the
coaching actions[12]. Research into personalization has been car- ontologies in our e-coaching system is based on its scenario to facil-
ried out for some time in the fields of artificial intelligence (AI), data itate re-engineering of ontological and non-ontological resources
retrieval and data mining[6]. The implementation of e-coaching to build a complete and consistent ontology. Figure 1 depicts the
systems resulting from these efforts utilized AI techniques such ontological development methodology that was carried out in a set
as knowledge representation. Defining and representing data or of sequential steps. In this paper, we only focus on the first two
related domain knowledge is a fundamental approach to allow steps which are knowledge acquisition and ontology construction.
reasoning and to provide personalized e-coaching activities in e-
coaching systems [12].
3.1 Knowledge acquisition
2.2 Ontology-based representation In this phase, the knowledge required to build the ontology comes
from several reliable resources, including domain experts’ opinion,
Ontology has gained much popularity and importance in recent
existing data tables obtained from the previous participant case
years for knowledge representation. The ontology-based solution
studies, existing ontology repositories, relevant experts’ protocol
has been well known over the past few years in enabling a higher
documents, and recent literature and guidelines. Initially, we deter-
level of abstraction. Ontologies have been found to perform better
mine the source of information to construct the user profile.
in user profiling when they are compared with other methods
To determine the concepts and relationships among the terms,
used[22]. Also, ontologies are one of the most popular approaches
firstly, we conducted literature analysis through textbooks and
for representing actionable knowledge, such example can be found
research articles, however, the results are insufficient and incom-
in physical activity domain [11, 24, 28].
plete to fulfill the requirements of the e-coaching system. After
meeting with the domain experts, we obtained several knowledge
2.3 User profiling technique for sources(e.g., previous participant’s case studies and existing data
personalization tables) that were useful to generate the concepts and relationships.
Personalization is usually based on a user’s profile. Such profile cap- Consultation meetings were arranged with our domain experts to
tures the user’s preferences and other characteristics that enable clarify the relevant types of user’s impairments, rules, and flow of
a system to present information that is relevant to them. Previ- the processes that need to be performed by the users. The extracted
ous studies have defined or reused ontologies to represent users information provides an initial outline of user-related concepts,
in health-care environments such as: monitoring users in ambient conditions, and relationships to be included in the ontology.
assisted living [21], providing individualized nutrition recommenda-
tion [1], as well as providing tailored coaching message to promote 3.1.1 Re-engineering non-ontological resources. The re-engineering
physical activities [27]. Finally, the work in [5] includes the user’s process was carried out to obtain an ontology from the gathered
profile and behavior to retrieve personalized food and health rec- information. We defined our selected non-ontological resources,
ommendations. and then, we analyzed these resources to identify a sequence of
According to Schiaffino and Amandi[18], a user profile is vital in- the coaching phases(which are made up of a collection of barriers,
formation about an individual person. In the context of our system, strategies, and goals). In the case of impairments, the impairment
to gather the data for user profiling, the system collects raw data types were identified and were classified.
User Profile Ontology to Support Personalization for E-Coaching Systems ,,
Figure 1: Methodology for ontology development
3.1.2 Reusing and re-engineering ontological resources. We had etc.). The main concept, U ser , represents any user of the e-coaching
considered existing user profile ontologies and imported some parts system and the U serPro f ile. It links semantically to a number of
of the following ontologies: key concepts and decomposes into more detailed or specialized
(1) For the impairment concept, some characteristics are im- attributes or properties. This ontology enables a dynamic profile of
ported from Accessibility ontology [17]. This ontology links the user to be stored and maintained. For instance, the user’s can
the characteristics of users with disabilities, functional limi- be updated continuously as he or she achieves the targeted goals.
tations, and impairments. We use an object property to link Also the MotivationReadiness stages can be updated dynamically
this ontology to the ImpairmentPro f ile concept when an activity progress occurs or when a change is noted in
(2) For the personal profile concept, the demographic informa- the ActivityPro f ile. The important concepts in the user profile
tion is imported from GUMO ontology[7] ontology are as follows:
(3) For exercises and lifestyle, the ontology imported some terms
(1) ImpairmentProfile: this concept defines the core impairments
related to physical activity from the Semantic Mining of Ac-
considered important for delivering the e-coaching, in the
tivity, Social, and Health (SMASH) [4] ontology. This on-
context of our system is the promotion of physical activity
tology escribes the semantic features of health-care data,
participation. We used numbers to identify each impairment
specifically data related to physical activities.
category as follows: 1.Impairments in Sensation; 2.Impair-
None of the previous ontologies offers a complete user profile ac- ments of Physical Structure; 3.Impairments of Physical Func-
cording to our e-coaching system’s requirements: user’s personal tion; 4.Behavioral and Emotional Impairments; and 5.Cogni-
details, health-related conditions, impairments and method from tive Impairments. The naming system to identify each com-
the physical activity promotion program in [3]. Thus, to model the bination of impairment categories to which a user belongs
user profile, we organized and extended these ontologies according consists of all impairment identifiers in numerical order. The
to our requirements. category of impairment was identified as one of the most im-
portant determinants for the mechanism of personalization.
3.2 Ontology construction (2) MotivationalReadiness: this concept defines the individual’s
Ontology construction is the core phase, which involves the creation stage of change, which described in [15]. The concept is
of an ontology framework. The next section shows the construction based on a behavior change technique(Trans-Theoretical
process of this new ontology to model the user profile. Model) [16].
By using the information in ImpairmentProfile and Moti-
4 ONTOLOGICAL USER PROFILE vationalReadiness concepts, the system is able to identify
MODELLING the user’s possible barriers, which is stored in the Barrier
In knowledge-based systems, concepts are used not just as terms, concept.
but also as computable objects with logical definitions, which en- (3) Barrier: this concept related to difficulties or obstacles needed
able knowledge for inductive and deductive reasoning. The data to overcome by the individuals to adopt or maintain the
captured in the user model is represented by the concepts. The main delivered e-coaching.
concepts of the ontology are shown in Figure ??. This follows a top- (4) Goal: this concept defines the targeted goal of the user
down design approach, where "high level" or general concepts re- (5) Value: this concept related to the identified value that moti-
lating to the user are captured (e.g. "Impairments","PersonalProfile" vates a user. Individuals were required to select values that
P.S.Pratiwi et al.
related specifically to their situation. This information is Table 1: Examples of the Definition of Concepts in the On-
used to determine the individual relevance of the goal that tology
was set.
(6) PersonalProfile: this concept is related to the personal char- Concept Attribute Name Range
acteristics associated with a user profile. This is useful for
Personal
categorizing or classifying individuals or for identifying par-
Profile hasPersonalProfile UserProfile
ticular user needs or requirements.
hasPersonalInfo PersonalInformation
(7) HealthConditionProfile: this concept defines any existing
hasAge (int)
health conditions associated with a user.
hasName (string)
(8) Preference: this concept defines any existing information re-
hasEducation (string)
garding an individual’s preferences, such as physical activity
hasTechnologyUsage (string)
preferences.
HealthCondition
(9) ActivityProfile: this concept captures the related informa-
Profile hasHealthConditionProfile UserProfile
tion regarding individual activity objectives, for example
health_relatedAttributes (string), (double)
maintaining weekly or daily physical activities.
isHighRisk (boolean)
There is a hierarchical relationship between the top and second isObese (boolean)
level classes and the object and data properties for the top-level WeightProfile hasBMI (float)
classes. For instance, each Goal hasStartTime and hasFinishTime Goal hasGoal Goal
, and each "ActivityProfile" links to "PhysicalActivity" which has Barrier hasBarrier Barrier
physicalActivityDataProperty. This enables the ontology to keep a barrierAttributes (string), (double)
record of the user’s physical activities and the goal within which Impairment
they occur, allowing the ontology to be refined. Profile hasImpairmentProfile ImpairmentProfile
hasImpairment Impairment
4.1 Constructing the ontology Preference hasPreference Preference
The next stage is to construct the ontological structure as shown in ActivityProfile hasActivityProfile ActivityProfile
Figure ??, linking the key concepts in the ontology. The first step hasActivity PhysicalActivity
is to define the classes using the names from the concepts defined hasPreferredActivity PhysicalActivity
previously. We include uniques identifier names and the narrative
for all the classes. Finally a number of possible attributes can be
listed in Table 1. We have built a schema by joining all the concepts 5 CONCLUSIONS
in a unique user profile. This schema is shown in Figure 3. The user In this paper, we developed an ontological model that aims to gain
profile ontology was formally described in OWL using the Protégé relevant information (e.g. demographic, health, impairment and
editor to define these basic elements: 1) classes, 2)properties, and 3) preference) from individuals in order to provide tailored physical
individuals. These elements are used to describe concepts, members activity promotion. Such an ontology provides a major step toward
of a class, relationships between individuals of two classes (object the development of a more intelligent e-coaching system. Our sys-
properties) or to link individuals with data-type values (datatype tem explores ontologies mainly for user profiling purposes. The
properties), which are shown in Figure 4 and 5. knowledge used in the ontology can be used to provide a complete
picture of the user profile. For future work, as we have designed the
Object (Class) Properties. In this stage, we defined the object prop- system architecture described in [14], we aim to create a prototype
erties so that the classes can be related to each other classes. for enabling the delivery of the e-coaching solution. The next stage
of development includes implementation of the communication
Data Properties. To efficiently develop the ontology, we carefully infrastructure between the architecture components.
defined the data properties in such a way that it could provide more
information. After carefully studying from the knowledge sources
described in 3.1. 6 ACKNOWLEDGEMENT
This research has received QUT Ethical Clearance Application Num-
4.2 Completing the ontology ber 1700000392
To complete the process of the ontology construction, we have
performed several procedures to check the consistency and to test
the anomalies within the ontology. We have used the Pellet rea-
soner [20] that allows the reasoning with the created instances.
Several instances of the U serPro f ile class were defined, each of
these instances holds specific attributes or properties concerning
a particular individual. In this work, instances of the user profile
class were created, where all of the concepts regarding the user are
held and linked via various object and data properties.
User Profile Ontology to Support Personalization for E-Coaching Systems ,,
Figure 2: The Conceptual Model of the User Model
Figure 5: Data Properties
Figure 4: Object Properties
Figure 3: Ontology class hierarchy
P.S.Pratiwi et al.
REFERENCES [24] Chuan-Jun Su, Chang-Yu Chiang, and Meng-Chun Chih. 2014. Ontological
[1] Ahmed Al-Nazer, Tarek Helmy, and Mohammed Al-Mulhem. 2014. User’s pro- knowledge engine and health screening data enabled ubiquitous personalized
file ontology-based semantic framework for personalized food and nutrition physical fitness (ufit). Sensors 14, 3 (2014), 4560–4584.
recommendation. Procedia Computer Science 32 (2014), 101–108. [25] Mari Carmen Suárez-Figueroa, Asunción Gómez-Pérez, and Mariano Fernández-
[2] Robbert Jan Beun, Willem-Paul Brinkman, Siska Fitrianie, Fiemke Griffioen-Both, López. 2012. The NeOn methodology for ontology engineering. In Ontology
Corine Horsch, Jaap Lancee, and Sandor Spruit. 2016. Improving Adherence engineering in a networked world. Springer, 9–34.
in Automated e-Coaching. In Persuasive Technology. Springer, Cham, 276–287. [26] JEWC van Gemert-Pijnen, Oscar Peters, and Hans C Ossebaard. 2013. Improving
https://doi.org/10.1007/978-3-319-31510-2_24 eHealth. Eleven international publishing The Netherlands.
[3] Kelly M. Clanchy, Sean M. Tweedy, and Stewart G. Trost. 2016. Evaluation of a [27] Claudia Villalonga, Hermie Hermens, Luis Javier Herrera, Hector Pomares, Igna-
Physical Activity Intervention for Adults With Brain Impairment: A Controlled cio Rojas, Olga Valenzuela, Oresti Banos, et al. 2017. Ontological modeling of
Clinical Trial. Neurorehabilitation and Neural Repair 30, 9 (Oct. 2016), 854–865. motivational messages for physical activity coaching. In Proceedings of the 11th
https://doi.org/10.1177/1545968316632059 EAI International Conference on Pervasive Computing Technologies for Healthcare.
[4] Dejing Dou. 2015. SMASH Ontology - Summary | NCBO BioPortal. http: ACM, 355–364.
//bioportal.bioontology.org/ontologies/SMASH [28] Wilko Wieringa, Harm op den Akker, Valerie M. Jones, Rieks op den Akker, and
[5] Mauro Dragoni, Tania Bailoni, Claudio Eccher, Marco Guerini, and Rosa Mai- Hermie J. Hermens. 2011. Ontology-Based Generation of Dynamic Feedback on
mone. 2017. A Semantic-enabled Platform for Supporting Healthy Lifestyles. In Physical Activity. In Artificial Intelligence in Medicine (Lecture Notes in Computer
Proceedings of the Symposium on Applied Computing (SAC ’17). ACM, New York, Science). Springer, Berlin, Heidelberg, 55–59.
NY, USA, 315–322. https://doi.org/10.1145/3019612.3019835
[6] Susan Gauch, Mirco Speretta, Aravind Chandramouli, and Alessandro Micarelli.
2007. User profiles for personalized information access. In The adaptive web.
Springer, 54–89.
[7] Dominik Heckmann, Tim Schwartz, Boris Brandherm, Michael Schmitz, and
Margeritta von Wilamowitz-Moellendorff. 2005. Gumo âĂŞ The General User
Model Ontology. In User Modeling 2005, Liliana Ardissono, Paul Brna, and
Antonija Mitrovic (Eds.). Number 3538 in Lecture Notes in Computer Science.
Springer Berlin Heidelberg, 428–432. https://doi.org/10.1007/11527886_58
[8] Melinda Huffman. 2007. Health coaching: a new and exciting technique to
enhance patient self-management and improve outcomes. Home Healthcare Now
25, 4 (2007), 271–274.
[9] Bart A. Kamphorst. 2017. E-coaching systems. Personal and Ubiquitous Computing
(May 2017), 1–8. https://doi.org/10.1007/s00779-017-1020-6
[10] Michel C. A. Klein, Adnan Manzoor, and Julia S. Mollee. 2017. Active2Gether: A
Personalized m-Health Intervention to Encourage Physical Activity. Sensors 17,
6 (June 2017), 1436. https://doi.org/10.3390/s17061436
[11] Rosa Maimone, Marco Guerini, Mauro Dragoni, Tania Bailoni, and Claudio Eccher.
2018. PerKApp: A general purpose persuasion architecture for healthy lifestyles.
Journal of biomedical informatics 82 (2018), 70–87.
[12] Sergio F Ochoa and Francisco J Gutierrez. 2018. Architecting E-Coaching Systems:
A First Step for Dealing with Their Intrinsic Design Complexity. Computer 51, 3
(2018), 16–23.
[13] Stephen Palmer, Irene Tubbs, and Alison Whybrow. 2003. Health coaching to
facilitate the promotion of healthy behaviour and achievement of health-related
goals. International Journal of Health Promotion and Education 41, 3 (2003), 91–93.
[14] Puspa S. Pratiwi. 2018. Automated e-Coaching System Architecture Framework
for Promoting Physical Activity. In Proceeding of International Conference on
Intelligent Autonomous System (ICoIAS 2018).
[15] P. S. Pratiwi and D. Tjondronegoro. 2017. Towards personalisation of physical
activity e-coach using stage-matched behaviour change and motivational in-
terviewing strategies. In 2017 IEEE Life Sciences Conference (LSC). 5–8. https:
//doi.org/10.1109/LSC.2017.8268130
[16] James O Prochaska and Carlo C DiClemente. 1992. The transtheoretical approach.
Handbook of psychotherapy integration 300 (1992), 334.
[17] Brunil Dalila Romero-Mariño, Vanesa Espín, María José Rodríguez-Fórtiz,
María Visitación Hurtado-Torres, Luis Ramos, and Hisham M Haddad. 2017.
Ontology to Profile User Models with Disabilities. In International Conference on
Model and Data Engineering. Springer, 372–385.
[18] Silvia Schiaffino and Analía Amandi. 2009. Intelligent user profiling. In Artificial
Intelligence An International Perspective. Springer, 193–216.
[19] D. Siewiorek, A. Smailagic, and A. Dey. 2012. Architecture and Applications of
Virtual Coaches. Proc. IEEE 100, 8 (Aug. 2012), 2472–2488. https://doi.org/10.
1109/JPROC.2012.2200560
[20] Evren Sirin, Bijan Parsia, Bernardo Cuenca Grau, Aditya Kalyanpur, and Yarden
Katz. 2007. Pellet: A practical owl-dl reasoner. Web Semantics: science, services
and agents on the World Wide Web 5, 2 (2007), 51–53.
[21] Kerry-Louise Skillen, Liming Chen, Chris D. Nugent, Mark P. Donnelly, William
Burns, and Ivar Solheim. 2014. Ontological user modelling and semantic rule-
based reasoning for personalisation of Help-On-Demand services in pervasive
environments. Future Generation Computer Systems 34, Supplement C (May 2014),
97–109. https://doi.org/10.1016/j.future.2013.10.027
[22] Sergey Sosnovsky and Darina Dicheva. 2010. Ontological technologies for user
modelling. International Journal of Metadata, Semantics and Ontologies 5, 1 (2010),
32–71.
[23] Gerasimos Spanakis, Gerhard Weiss, Bastiaan Boh, Lotte Lemmens, and Anne
Roefs. 2017. Machine learning techniques in eating behavior e-coaching. Personal
and Ubiquitous Computing 21, 4 (Aug. 2017), 645–659. https://doi.org/10.1007/
s00779-017-1022-4