Data Intelligence Just Accepted MS. - Am MIT spezialisierte KI-Forschung

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Integrating Functional Status Information into Knowledge Graphs
to Support Self-Health Management

Mauro Dragoni

Fondazione Bruno Kessler, Trient, Italien

Tania Bailoni

Fondazione Bruno Kessler, Trient, Italien

Ivan Donadello

Free University of Bolzano, Bolzano, Italien

Jean-Claude Martin

LISN-CNRS, Universite Paris Saclay, Paris, Frankreich

Helena Lindgren

Umea University, Umea, Schweden

Abstrakt

Functional Status Information (FSI) describes physical and mental wellness at the whole-person
Ebene. It includes information on activity performance, social role participation, and environmen-
tal and personal factors that affect the well-being and quality of life. Collecting and analyzing
this information is critical to address the needs for caring for an aging global population, Und
to provide effective care for individuals with chronic conditions, multi-morbidity, and disabil-
ität. Personal knowledge graphs (PKGs) represent a suitable way for meaning in a complete and
structured way all information related to people’s FSI and reasoning over them to build tailored
coaching solutions supporting them in daily life for conducting a healthy living. In diesem Papier,
we present the development process related to the creation of a PKG by starting from the He-
LiS ontology in order to enable the design of an AI-enabled system with the aim of increasing,
within people, the self-awareness of their own functional status. Insbesondere, we focus on the
three modules extending the HeLiS ontology aiming to represent (ich) enablers and (ii) barriers
playing potential roles in improving (or deteriorating) own functional status and (iii) arguments
driving the FSI collection process. Endlich, we show how these modules have been instantiated
into real-world scenarios.

Email addresses: dragoni@fbk.eu (Mauro Dragoni), tbailoni@fbk.eu (Tania Bailoni),

ivan.donadello@unibz.it (Ivan Donadello), jean-claude.martin@u-psud.fr (Jean-Claude Martin),
helena@cs.umu.se (Helena Lindgren)

Preprint submitted to Data Intelligence
© 2023 Chinesische Akademie der Wissenschaft. Veröffentlicht unter einer Creative Commons Namensnennung 4.0
International (CC BY 4.0) Lizenz.

Februar 16, 2023

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

1. Einführung

There is a growing trend of developing virtual health and well-being assistants to support
lifestyle and disease management, partly due to the growing societal need for managing health
and preventing illness. To improve an individual’s situation, a change of behavior is typically
necessary, which puts focus on how a digital coach can act in collaboration with the individual
to support the individual’s ambition to improve their health through behavior change, z.B., von
adhering to medical guidelines or treatment protocols, increasing physical activity, changing
nutrition habits, reducing stress or intake of toxic substances. As a basis for deciding how to act,
the digital coach may explore the functional status information (FSI) of the monitored individual.
A necessary foundation for a medical and health-related system’s reasoning, decision mak-
ing and acting is (ich) the medical knowledge that the digital coach utilizes, (ii) the theories and
knowledge about how humans form motivation and change behavior as well as manage physi-
cal, sozial, and psychological barriers, Und (iii) the FSI (Daten) about the individual as well as the
individuals’ narrative about their behavior change journey, information that needs to be treated
following ethical guidelines and regulations. Darüber hinaus, the realization of such systems relies
on the integration of effective, efﬁcient, and ethical strategies for adapting behavior in a situ-
ation depending on the individual’s context, personal preferences, and needs (z.B., displaying
motivational messages that are tailored to each individual’s resources and current situation).

A proper representation of this information requires (ich) a strategy able to mitigate the diver-
sity of the information managed and (ii) a conceptual model enabling the exploitation of such
information by preserving, gleichzeitig, the privacy aspects. Personal knowledge graphs
(PKGs) are a valid way for providing an effective representation of FSI and for connecting such
information with users’ personal records (z.B., electronic health records) in order to enable the
design of AI-based systems implementing the coaching paradigm for avoiding FS deterioration
in target users.

In diesem Artikel, we present the design process we adopted to extend the HeLiS ontology [1]
with three new modules, namely Enablers, Barriers, and Arguments, enabling the deﬁnition and
tracking of users’ FSI. 1 Hereafter, we adopt the acronym FuS-KG as reference for the Func-
tional Status Knowledge Graph containing the HeLiS ontology and the three developed exten-
sionen. The adoption of such an ontology as a middle layer for the design of explainable behavior
change systems allow (ich) modeling conceptual information representing individuals’ FSI and the
use of the information to adapt the generation of explanatory and motivational messages to the
individual; (ii) supporting interoperability among different systems which could share, for exam-
Bitte, databases of motivational messages or explainability algorithms; Und, (iii) managing privacy
and ethical issues relating to user data. Through the conceptualization of each enabler or barrier
and of arguments, it is possible (ich) to acquire the personal FSI of users and to properly store them
within the ontology; Und, (ii) to manage which information can be shared with respect to the
target user and, gleichzeitig, design systems that are transparent by design. In der Tat, the use
of ontology enables the linking of information contained in black-box systems with conceptual
information for exposing them.

This contribution is organized as follows. The literature about the acquisition and exploita-
tion of functional status information is brieﬂy surveyed in Section 2. In Section 3 we provide a
brief recap of the HeLiS ontology and present the three ontology modules we designed for ad-
dressing the challenges mentioned above. Dann, in Section 4 we show (ich) how such modules have

1The full ontology and its modules are available at https://w3id.org/helis

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

been integrated into an existing virtual coaching system, namely HORUS.AI, Und (ii) how the
model has been connected to a conversational agent with the aim of collecting, from real users,
arguments concerning daily habits and barriers. Endlich, in Section 5 we conclude the paper by
conveying the future directions we aim to explore.

2. Related Work

Understanding the functional status of a person is important for developing accurate inter-
ventions and providing services for improving their health status as well as maximizing their
functional independence to be able to perform well daily activities and be healthy. Managing
health is a complex challenge and often the health care system’s scarce resources prevent pro-
viding adequate support and care especially to people with chronic and disability conditions [2].
The National Committee on Vital and Health Statistics (NCVHS) [3] states that understanding
the functional status of people is key to achieving optimal health and well-being. Assessing a
patient’s functional status requires a clinician to meet and interview the patient regarding their
habits and lives and also to conduct standardized tests. Jedoch, such assessments represent a
snapshot of a person’s health status, while achieving behavior change for improving health is a
long-term process. Folglich, there is a gap between people’s health goals and the sparsely
conducted health assessments conducted in healthcare, which is a limitation when aiming for
achieving a good quality of care [4]. To meet the need for continuing support, data needs to be
available from frequent measurements.

Physicians and researchers have studied the correlation between the decline in functions and
the insurgence of acute illness or an exacerbation of a chronic illness, and identiﬁed risk factors
with the purpose of detecting the elderly most at risk of experiencing a decline in functions [5,
6, 7]. Darüber hinaus, early detection and treatment of illness is key to a more rapid recovery and
to preventing morbidity and mortality in older adults [8, 9, 10]. Jedoch, the problem is that
functional status information is not yet being fully embraced and thus is not used effectively to
its full potential [4].

The usefulness and the development of interventions based on functional status measure-
ments are still being studied and are under development but many physicians still do not appre-
ciate the importance of this information [11, 12, 13, 14]. In der Tat, even if they were informed of
patients’ perceived health status, only a few changed patient management based on the informa-
tion [15]. The NCVHS deﬁned the problem of collecting patient data, considering not only the
issue of the data collection burden and the quality of the data collected but also the issues relating
to the privacy of the patient that arises when collecting personal and sensitive data [3].

Studies that are based on self-reports of functional performance and early decline in func-
tions report that they successfully predict the actual performance and decline [16, 17]. Jedoch,
researchers veriﬁed that the self-report of functional decline or disability captures only a small
portion of the problems [7]. Daher, new ways to detect the patient’s functional status are needed,
especially methodologies that will evaluate the patient’s functional performance not only in case
of problems or healthcare issues but also in normal function. These new ways should be unob-
trusive but accurate and do not always require face-to-face interaction with a physician or other
health care provider. In [18], sensors are used to detect a decline in daily activities, especially
regarding physical function, and thus deﬁne ad hoc interventions. Using a sensor system to eval-
uate functional status seems critical especially given the growing elderly population. In [18], Die
authors report that having a system able to detect early changes in the functional status of peo-

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Bitte, especially elderly people, and intervene with appropriate interventions could help prevent
functional deterioration and reduce the decline in functional ability.

Our investigation goes in this direction with the aim of designing an AI-enabled system able
to assist the individual in monitoring their functional status and preventing functional decline.
This is achieved through the usage of a coaching mechanism providing motivational feedback
supporting people in their goals to change their lifestyle to improve health.

An example of a recent cooperative effort to create observable and replicable interventions
to inﬂuence behavior and health is given by the taxonomy on behavioral change techniques pre-
sented in [19]. Such a taxonomy supports the aggregation of behavior and behavior change
knowledge as well as sharing and reusing of useful sources of behavior knowledge. We also ob-
served that to our knowledge there currently exists no publicly available conceptual classiﬁcation
that models barriers to behavior change.

An important effort to mention is the human behavior taxonomy from the World Health
Organization2 (WHO) [20]. This taxonomy of human behavior has been developed based on the
knowledge of the WHO and on the International Classiﬁcation of Functioning (ICF), Disability,
and Health. This taxonomy includes a full deﬁnition of its classes, based heavily on the U.S.
National Cancer Institute (NCI) Thesaurus, as well as the Oxford English Dictionary [21].

Another computational effort in capturing human behavior is the Semantic Mining of Activ-
ität, Social and Health Data (SMASH) [22]. This is a project which looks at providing predictions
on human behavior, as well as explanations for the predictions, and is based on an Ontology Re-
stricted Boltzmann Machine [23] where an algorithm learns user representations from health
ontologies, using the user representation to incorporate self-motivation, social inﬂuences, Und
environmental events into the generation of predictions (and explanation of predictions) of hu-
man behavior.

The Neurobehavior Ontology (NBO) [24] is an ontology on the domain of Behavioral pro-
cesses and phenotypes, which are related to behavior and behavior change [25]. The NBO in-
cludes two main components: (1) the behavioral processes ontology, Und (2) the behavioral-
phenotypes ontology. The ﬁrst component of the NBO classiﬁes the behavior process to com-
plement and extend the Gene Ontology (GO) [26]. The second component of the NBO classiﬁes
the normal and abnormal behavior of organisms.

The Health Behavior Change Ontology (HBCO) was built for a project aiming to establish
an automated dialogue between a psychologist and a user to provide behavioral counseling [27].
The HBCO ontology has strengthened the linkage between theoretical and practical parts, but few
practical implementations exist [28], meaning there are currently no speciﬁc strategies providing
a reusable behavior change ontology in practice.

As our conceptualization must refer to the model of the person for whom the behavioral
change techniques need to apply, it is useful to explore the ontologies that explicitly model
“users”, in terms of their proﬁle, characteristics, and sometimes also their behavior. Ein Beispiel
of a user ontology is the General User Model Ontology (GUMO) [29], which we will also import
into our ontology. Besides the GUMO, there exist several other ontologies that encapsulate wider
aspects of user (menschlich) Aktivitäten. One of these, which is in fact a GUMO extension, ist der
User Navigation Ontology (UNO) [30]. Another user proﬁle ontology is OntoPIM (Ontology
Personal Information Management), which describes various users’ dimensions and shares a lot
of concepts with GUMO [31].

2https://www.who.int/classiﬁcations/drafticfpracticalmanual.pdf

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Endlich, in order to address the physical activity behavior domain, we need to mention some
behavior ontologies related to the physical activity or exercise domain, insbesondere, the Ontology
of Physical Exercises3 and the HeLiS ontology [32]. A Physical Activity Ontology (PACO)
was proposed to support structuring and standardizing heterogeneous descriptions of physical
Aktivitäten [33].

3. Building The Personal Health Knowledge Graph

The creation of the FuS-KG presented in this paper started from an existing ontology mod-
eling the healthy lifestyle domain, called HeLiS [1], brieﬂy presented in Section 3.1. The He-
LiS ontology has been created by applying the METHONTOLOGY [34] ontology engineering
methodology. Somit, the modeling of the three modules described below followed the same
process given the possibility of involving a group of knowledge engineers and domain experts
to achieve our goal. Insbesondere, the overall process involved four knowledge engineers and
seven domain experts from the Trentino Healthcare Department. More precisely, three knowl-
edge engineers and four domain experts participated in the ontology modeling stages (Jenseits,
the modeling team). The remaining knowledge engineer and three domain experts were in charge
of evaluating the ontology (Jenseits, the evaluation team).

The choice of METHONTOLOGY was driven by the necessity of adopting a life-cycle split
in well-deﬁned steps. The development of the HeLiS ontology requires the involvement of
the experts in situ. Daher, the adoption of a methodology having a clear deﬁnition of the tasks
to perform was preferred. Other methodologies, like DILIGENT [35] and NeOn [36], war
considered before starting the construction of the HeLiS ontology. Jedoch, the characteristics
of such methodologies, like the emphasis on decentralized engineering, did not ﬁt our scenario
well.

METHONTOLOGY is composed by seven stages, namely Speciﬁcation, Knowledge Ac-
quisition, Konzeptualisierung, Integration, Implementation, Evaluation, and Documentation. Wir
summarize the activities performed in each stage within the following paragraphs. The only
exception is the Evaluation stage that has been provided within the subsection 3.5.

Speciﬁcation. The purpose of the presented FuS-KG is two-fold. Einerseits, we intend
to provide a set of conceptual modules detailing several aspects connected to the representation
of users’ FSI. Andererseits, with the building of FuS-KG we want to foster the design and
development of AI-enabled systems towards the implementation of behavior change strategies
in patients affected by speciﬁc barriers. The three ontology modules have been modeled with a
high granularity level by exploiting, as described in the next paragraph, ﬁne-grained knowledge
acquired from both domain experts and available literature.

Knowledge Acquisition. The knowledge was acquired in two ways: (ich) we organized a set
of focus groups with the domain experts for acquiring the main concepts and for building the
ﬁrst version of the graph; Und, (ii) we analyzed the literature on behavior change strategies and
techniques for detailing our model and for disambiguating possible inconsistencies that came to
light during the focus group.

Concerning enablers and barriers, the modeling team deﬁned which are the main type of
both enablers and barriers presented in the state-of-the-art that are relevant for supporting the
development of third-party behavior change applications. The conceptualization of barriers and

3https://bioportal.bioontology.org/ontologies/OPE/?p=summary

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

of the different states of change has been created by extracting knowledge from domain-speciﬁc
unstructured resources [37, 38]. During this step, the main challenges we faced were related
to the creation of the enablers module where we have (ich) to distinguish between strategies and
techniques and (ii) to detect duplicate knowledge. In der Tat, several notions deﬁned within the
behavior change area present conceptual overlaps that, from the ontological perspective, müssen
be removed.

Concerning argumentation, we deﬁned the main concepts that can drive the creation of moti-
vational dialogues for obtaining FSI from users, or for generating motivational messages tailored
to users for supporting them to overcome speciﬁc barriers in order to achieve their goals of im-
proving their health. With the involvement of domain experts, we deﬁned which is the role of
each argument type within a motivational dialogue and how such arguments are semantically
linked with enablers or barriers.

Konzeptualisierung. The conceptualization of the three ontology modules was split into two
Schritte. The ﬁrst one was covered by the knowledge acquisition stage, where most of the termi-
nology is collected and directly modeled into the ontology as concepts or properties. While the
second step consisted of deciding how to represent, as classes or as individuals, the information
we collected from unstructured resources. Such a differentiation activity has been done, in par-
besonders, on the enablers where the distinction between concepts and individuals is, Manchmal,
very small. Dann, we modeled the properties representing the different relationships between the
deﬁned concepts.

During this stage, we relied on several ontology design patterns (ODP) [39]. Jedoch, In
some cases, we renamed some properties upon the request of domain experts. Insbesondere, Wir
exploit the logical patterns Tree and N-Ary Relation, the alignment pattern Class Equivalence,
and the content patterns Parameter, Time Interval, Action and Classiﬁcation.

Integration. The integration of the ontology has two objectives: (ich) to align them with a
foundational ontology, Und (ii) to link it with the Linked Open Data (LOD) cloud. Der Erste
objective was satisﬁed by aligning the root concepts of both extensions with the ones deﬁned
within the DOLCE [40] top-level ontology. The second objective was satisﬁed by aligning our
ontology with the UMLS Knowledge Base4 since it has been included within the LOD cloud
recently. Hier entlang, it may work as a bridge between the latter and the three ontology modules.

Implementation. The created FuS-KG is represented by means of several ontological mod-
ules by using the RDF/XML language in order to provide a formal representation enabling the
check of inconsistencies, the visualization of ontology structure, and the ease of maintenance.
The editing of the ontology is demanded of the MoKi tool [41], while the exposure of the ontol-
ogy is granted by the services available from the HeLiS ontology website.

Documentation. The documentation of the FuS-KG has been done from two perspectives.
Erste, during the whole modeling process, a document has been prepared by the people involved
in the construction process. This activity was necessary because the development of the FuS-
KG and its sustainability is granted by a public funding program. Daher, all performed steps were
documented and archived within the funding dossier. Zweite, in order to ease the readiness of
the FuS-KG for users, we provided a different documentation ﬁle generated by using the LODE5
system and available on the FuS-KG website.

4https://www.nlm.nih.gov/research/umls/
5http://www.essepuntato.it/lode

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

3.1. The HeLiS Ontology

The personal health knowledge graph described in this paper and used within our virtual
coaching platform has been built by starting from the HeLiS [32]6 ontology, a state-of-the-art
conceptual model for supporting healthy lifestyles. It deﬁnes the dietary and physical activity
domains together with entities that model concepts concerning users’ proﬁles and the monitor-
ing of their activities. [32] provides details about the conceptual model and the methodology for
building the model. Hier, we provide an overview of the HeLiS ontology by introducing the
concepts of modeling users, meals and physical activities, monitoring rules, and detected viola-
tions that are referred to in this paper. Darüber hinaus, we brieﬂy recap the main concepts involved
in the core module of HeLiS in order to better link them with the ones deﬁned in the extensions
presented below.

Figur 1 shows the main concepts deﬁned within the core module of the HeLiS ontology.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Figur 1: The main concepts of the HeLiS core ontology.

The main concepts of the HeLiS ontology are shown in Figure 1 and are organized in four
main branches underlying as many root concepts: (ich) Food, (ii) Activity, (iii) Überwachung, Und
(iv) User.

The Food branch is responsible for modeling the instances macro-grouped under the Ba-
sicFood and Recipe concepts. The former includes also Nutrients’ information (carbohydrates,
lipids, proteins, minerals, and vitamins). The latter describes complex dish composition (wie zum Beispiel
Lasagna) through a list of (cid:104)BasicFood, quantity(cid:105) pairs.

The root concept of the Activity branch is PhysicalActivity, which contains 856 Aktivitäten
sorted into categories. For each activity, we provide the number of calories consumed in one
minute for each kilogram of the user’s weight and the MET (Metabolic Equivalent of Task)
value expressing the energy cost of the activity.

The Monitoring branch represents concepts concerning the monitoring of users’ behaviors
and it contains two main sub-concepts: MonitoringRule and Violation. MonitoringRule in-
stances describe the parameters deﬁning how users should behave if adhering to health goals

6http://w3id.org/helis

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

(aka “rules”). While Violation instances contain the results of reasoning activities exploited for
generating users’ advice and recommendations. The content of each Violation instance is com-
puted according to the user data that triggered the violation.

Endlich, the User branch contains the conceptualization of user information and it enables
the representation of all users’ events (consumed foods and performed physical activities) Und
the association of each violation to the corresponding user. Users’ events are represented via the
Meal, ConsumedFood, and the PerformedActivity concepts. The last two concepts are reiﬁed re-
lations enriched with attributes for representing the facts that a user consumed a speciﬁc quantity
of food or performed an activity for a speciﬁc amount of time.

3.2. The Enablers Module

The Enablers module contains the main concepts enabling a user to start a behavior change
Verfahren. This module has been built by starting from two of the main references available in
the ﬁeld indicated by the domain experts [37, 38]. We deﬁned four main concepts, nämlich
Intervention, Treatment, Strategy, and Technique.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Figur 2: The main concepts of the FuS-KG enablers module.

Figur 2 shows the main concepts deﬁned within the enablers module of FuS-KG. The Inter-
vention concept follows the deﬁnition provided in [38] and it refers to a single action performed
during a Treatment. Als Beispiel, let us consider a behavior change scenario where a patient
8

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

affected by diabetes has to monitor their glycemic index after each meal and provide the observed
value into a mobile application. The reminder to do this action is an instance of the Intervention
concept.

The Treatment concept is deﬁned as the unfolding of every Intervention performed to allow
users to achieve their aim. Zum Beispiel, the set of Interventions performed by an AI-enabled
system to persuade a patient about following the Mediterranean Diet is a Treatment [42].

The Strategy concept subsumes the ﬁve main strategies that can be implemented during a
behavior change process: Education, GoalAndPlanning, Feedback, Überwachung, and Motiva-
tionalEnhancement. The Education concept models the aim to increase the user’s understanding
of their past and current state and of the steps required to achieve the future state (z.B., to provide
information and/or instruction for behaving in a proper way). The GoalAndPlanning concept
refers to future planning to achieve desired future states (z.B., activity scheduling and/or setting
tasks of progressively greater difﬁculty). The Monitoring concept deﬁnes the action of record-
ing past or current user’s states (z.B., current nutritional behaviors and/or activity events). Der
Feedback concept models the information on current and past states provided to the user about
their condition and/or actions. The meaning of the Feedback concept may also overlap with
other behavior intervention components, such as MotivationEnhancement in a scenario where,
Zum Beispiel, feedback may provide information about progress and may also increase or decrease
motivation. Endlich, the MotivationEnhancement concept refers to interventions that increase the
likelihood that the user will engage in speciﬁc behaviors related to treatment goals or usage of
the application in the future. Each instance of the Strategy concept has to be associated with the
instance of the Treatment concept adopting it. Such an association can be done by instantiating
the adoptsStrategy object property.

The fourth main concept is Technique, meaning an observable, replicable, and irreducible
component of a Strategy used within a Treatment designed to alter or redirect causal processes
that regulate behavior. A Technique is an “active ingredient” (z.B., Rückmeldung, self-monitoring, Re-
inforcement) of a Strategy and it can be used alone or in combination, and in a variety of formats.
Within the proposed FuS-KG, we deﬁned 19 types of techniques subsuming the Technique con-
cept. We refer the reader to check the Enablers module for the details. Darüber hinaus, each instance
of the Technique concept has to be associated with the instance of the Strategy concept adopting
Es. Such an association can be done by instantiating the isUsedBy object property.

3.3. The Barriers Module

The Barriers ontology module is composed of four main branches: (ich) the classiﬁcation of
the barriers, (ii) the representation of the different states of changes, (iii) a new taxonomy for
classifying the list of physical activities deﬁned within barriers, Und (iv) the representation of the
Patienten.

Figur 3 shows the main concepts deﬁned within the barriers module of FuS-KG. The Bar-
rier concept is the root concept of the ﬁrst branch and it subsumes six macro-categories of bar-
riers. The EnvironmentBarrier refers to the hindrances related to performing an action due to
obstacles connected to the circumstances in which the action itself takes place. Zum Beispiel,
they could relate to the weather (like unfavorable climatic conditions), to money (like the cost of
the equipment needed), and to security issues (like the lack of safety). HealthBarrier concerns
the presence of some disease preventing the performance or completion of a speciﬁc action. Das
concept enables the possibility of importing external medical knowledge bases (z.B., the UMLS).
Hier entlang, barriers are connected with medical knowledge that can be exploited at reasoning time
(such as asthma, chest pain, usw.). The PersonalBarrier concept represents barriers associated
9

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

Figur 3: The main concepts of the FuS-KG barriers module.

with real-life situations (z.B., job conditions) that obstruct the performance of speciﬁc actions.
Dann, the PhysicalBarrier and PsychologicalBarrier concepts are related to hindrances given by
physical pains (z.B., knee injury) or emotional status (z.B., fear) that block a person from per-
forming speciﬁc actions. Endlich, the SocialBarrier concept mainly refers to a possible lack of
support from people close to patients (z.B., Eltern, friends, usw.). The Barrier concept is asso-
ciated with the Sign concept specifying a condition that is true in relation to that barrier. Tatsächlich,
the Sign concept deﬁnes speciﬁc circumstances (both environmental and personal) like the fact
that it’s raining, that a person has a headache, or that a person has a full-time job.

The second branch consists of the abstract representation of the Transtheoretical Model of
ändern (TTM) [43]. TTM describes the different stages of change that an individual can be in,
and is used by clinicians for supporting the behavior change process. The main concepts we
deﬁned are StateOfChange, which is the root concept of this branch, and then the six stages in
which a Patient can be: PreContemplation, Contemplation, Preparation, Action, Maintenance,
and Termination. Darüber hinaus, we deﬁned the property hasBehavior that is used as a reiﬁcation of
the status in which a Patient is during a speciﬁc Timespan.

The third branch provides a new taxonomy of physical activities deﬁned in the core of bar-
riers. Usually, the taxonomy deﬁned within the core of barriers classiﬁes physical activities by
type. Stattdessen, this extension provides a different classiﬁcation of physical activities rooted in
the ExerciseType concept. Dann, the activities are classiﬁed following different perspectives: Die
energetic system generally used for performing the action (z.B., aerobic or anaerobic), if the ac-
tivity requires ﬂexibility abilities, if the activity corresponds to an athletic sport, and whether the
activity is performed indoors or outdoors. Zusätzlich, the intensity (or effort) level of each ac-
tivity can be speciﬁed by the property hasIntensity that associates an activity to an IntensityLevel
(d.h., light, moderate, or vigorous). The rationale of this classiﬁcation is given by the necessity of
deﬁning the relationships between barriers and physical activities. Zum Beispiel, if a user suffers
from asthma, such a HealthBarrier may obstruct the performance of some OutdoorActivity.

Endlich, the fourth branch consists of the representation of the user as a Patient. This concept

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

helps to identify the characteristics of each user and specify whether he or she suffers from a
certain disease that could inﬂuence the behavior of the user.

3.4. The Arguments Module

The arguments ontology module aims at supporting efﬁcient and effective dialogues for mo-
tivating behavior change. It has been developed following the model described in [44], and it is
structured in a way that helps the formulation of persuasive dialogues [45] aimed at motivating
a user/patient toward a healthier lifestyle (or a particular lifestyle goal). The module collects
various arguments, which are different types of sentences, that are used to model dialogues pro-
viding beliefs a person may have concerning healthcare issues and the appropriate responses
motivating behavior change. daher, each argument can have various properties that help to
deﬁne its type, Funktion, topic, Kontext, Dienstprogramm, and the healthcare problem or solution it refers to.
Außerdem, the concepts deﬁned in the arguments module are Argument, Concern category,
Context type, Functional type, Ontological type, Topic type and Utility.

Figur 4 shows the main concepts deﬁned within the arguments module of FuS-KG. Der
Argument concept represents the argumentations that are used in the generation of the dialogues.
These sentences are properly characterized by properties that specify the role of each argument
in dialogue and how they relate to each other. Some examples of arguments deﬁned in the
module are: “do physical activity regularly”, “an active lifestyle and a balanced diet are the best
‘medicine’ to live longer and better” or “not having time to exercise”.

Concern category represents healthcare problems (such as “Stress” and “Heart Problems”)
and solutions (like “Healthy diet” and “Physical Activity”). These concepts are useful for in-
dicating which problem and/or solution an argument relates to. Tatsächlich, the property concerns
connects arguments to the associated healthcare category. It is important to notice that some
arguments can concern more than one problem or solution and in some cases, they could re-
fer to both problems and solutions. Zum Beispiel, the “do physical activity regularly” concerns
“Stress”, because doing regular activity helps to reduce stress, while “not having time to exer-
cise” concerns “Physical Activity” because it is an obstacle to be active.

The Context type concept represents speciﬁc contexts that can refer to the location, Alter, oder
status of the user; these are used to contextualize arguments, thus limiting the domain in which an
argument is true and can be used. Zum Beispiel, in healthcare, a solution for a problem for some
people can be damaging for others (z.B., people having a particular health status or age). It’s thus
important to be able to deﬁne the context of an argument and the property only applicable in has
been deﬁned for that purpose.

The Functional type concept speciﬁes the role an argument can have in the dialogue (für
Beispiel, whether the argument is a type of goal a person may have, some kind of evidence
regarding a healthcare problem, an opinion of the user, usw.). Functional type is then subdivided
into Objective, Prospective, and Subjective, where the ﬁrst is used to characterize arguments
based on undeniable information that could be based on well-established medical or scientiﬁc
knowledge or current healthcare guidelines, the second characterizes the goals a person might
have for themselves or for the welfare of others, and ﬁnally, the third is used to characterize
arguments based on controversial or false information, opinions, and beliefs.
In this regard,
the property has functional type connects the arguments to their functional type. Zum Beispiel,
“do physical activity regularly” has the function of a persuasion goal, while “not having time to
exercise” is a subjective argument that expresses an opinion of a possible user.

The Ontological type deﬁnes the kind of belief expressed in an argument. The types deﬁned
in the module are: attitude, background, beneﬁt, Kapazität, cause, commitment, Gemeinschaft, cost,
11

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

Figur 4: The main concepts of the FuS-KG arguments module.

motivation, myth, obstacle, opportunity, risk and side-effect. Where attitude concerns opinions
on the attitude of a person toward a healthcare problem and/or solution. Background speciﬁes
additional facts or opinions on some healthcare problems or solutions. Beneﬁt describes events
having a positive payoff in relation to solving a healthcare problem. Capacity concerns the abil-
ity of a person of addressing a healthcare problem. Cause gives facts or opinions regarding the
cause of a healthcare problem. Commitment describes a pledge a user may take in order to solve
a healthcare problem. Community concerns beliefs on the user’s community. Cost gives facts or
opinions regarding the possible costs for a healthcare solution. Motivation gives an opinion on
the user’s motivation for addressing a healthcare problem. Myth concerns beliefs that are com-
monly thought true regarding a problem or solution but that are in fact false. Obstacle concerns
barriers a user may face trying to achieve a healthcare solution. Opportunity concerns facts or
opinions related to the opportunity of achieving a healthcare solution. Risk describes possible
12

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

negative events that can occur from a healthcare problem. Side-effect concerns facts or opinions
on possible side-effects to a healthcare solution. Dann, the property has ontological type is used
to connect an argument to its type. Zum Beispiel, “an active lifestyle and a balanced diet are
the best ‘medicine’ to live longer and better” is a beneﬁt, while “not having time to exercise” is
deﬁned as an obstacle.

The Topic type concept represents the topic and subject matter used to classify the content of
the arguments. Tatsächlich, knowing the topic of an argument is helpful in choosing arguments that
may interest some users better than others, thus supporting the creation of more effective and
persuasive dialogues.

Endlich, the Utility concept refers to the usefulness of a certain goal; it speciﬁes how beneﬁcial
a goal may be for the user and it can be also used for ranking goals. The ranked by property is
used to connect a goal argument to the measure of its utility.

After deﬁning the concepts used to characterize the arguments and in order to facilitate the
creation of a persuasive dialogue we modeled two properties (d.h., support and attack) that con-
nect two arguments. The support property speciﬁes that an argument helps to support another,
for example “an active lifestyle and a balanced diet are the best ‘medicine’ to live longer and
better” supports “do physical activity regularly” because knowing that having an active lifestyle
helps you to live longer and better could help to motivate the user to do physical activity regu-
larly. Stattdessen, the attack property is used to deﬁne that an argument challenges or attacks another
Streit. Zum Beispiel, “not having time to exercise” attacks “do physical activity regularly”
because a person who believes they have no time to exercise will ﬁnd it a challenge to exercise
regularly.

In order to be able to create effective dialogues, it’s very important to have numerous argu-
gen. Tatsächlich, after having constructed the structure of the argument module, we instantiated
the argumentations in the healthcare domain, collecting material from various sources both from
domain experts and online (concerning the physical activity7 and healthy diet8 domains).

3.5. FuS-KG Evaluation

The evaluation of the quality and correctness of FuS-KG has been conducted from two per-
spectives. Erste, we performed an expert-based evaluation where the team that did not participate
in the modeling process adopted the metrics described in [46, 47, 48, 49, 50] to verify the quality
of FuS-KG: Accuracy, Adaptability, Clarity, Completeness, Computational Efﬁciency, Concise-
ness, Consistency/Coherence, and Organizational ﬁtness. Zweite, we ran the OntOlogy Pitfall
Scanner!
(OOPS!) [51] to identify inconsistencies, pitfalls, and errors and to check whether
FuS-KG met all the needs for which it has been built.

The overall Accuracy of the FuS-KG has been judged as satisfactory. The knowledge of the
domain experts was in-line with the complexity of the use of axioms. In der Tat, within the FuS-KG
there are not very complex axioms. Dann, by considering the representation of the real world,
the evaluators agreed on the correctness of the FuS-KG in describing the domain.

Concerning the Adaptability of the FuS-KG, the evaluators focused on the possible extension
Aspekte. They veriﬁed that the FuS-KG can be extended and specialized monotonically. Hier,
the question has to be addressed from two perspectives. zuerst, concerning the extension of the
FuS-KG from the content perspectives (d.h., adding new enablers, barriers, FSI-related concepts,

7https://www.physio-pedia.com/Barriers to Physical Activity
8https://www.sanihelp.it/

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

usw.), the result was positive because any extension of the FuS-KG did not require the removal of
any axiom. Zweitens, concerning the representation of users’ proﬁles, the update of the FuS-KG
was not monotonic because if a user is associated with a new proﬁle, the old association is re-
moved. Anyway, the FuS-KG does not react negatively to these changes because its consistency
is preserved.

About the Clarity of the FuS-KG, the evaluators agreed with the strategy decided by the
modeling team about using concept labels to communicate the intended meaning of each concept
and the use of deﬁnitions and descriptions of the main concepts of the FuS-KG, especially for
the root concepts of each branch. Darüber hinaus, each deﬁnition has been well documented within
the FuS-KG in order to make the meaning of each concept understandable by those who use the
FuS-KG.

The experts agreed about the Completeness of the FuS-KG. Jedoch, they distinguished
between the TBox and the ABox. In der Tat, concerning the TBox, the evaluators agreed about the
completeness of the FuS-KG and the lexical representations of the concepts. Insbesondere, Sie
veriﬁed that all the represented nutrients appropriately cover the health domain and that all the
information needed for the realization of tools supporting a healthy lifestyle were modeled within
the FuS-KG. Regarding ABox, the evaluators highlighted the necessity of including individuals
concerning commercial products. This observation is interesting, especially, if we consider the
possibility of developing end-user applications. In der Tat, the presence of commercial products
will improve overall user engagement.

In order to verify the Computational efﬁciency of the FuS-KG, we observed how it behaved
within the scenario described in Section 4. In der Tat, the FuS-KG itself does not contain axioms
representing a criticism for reasoners. Andererseits, the ﬁnal aim of the FuS-KG is to be used
for analyzing data provided by users. In Section 4, we show an example of how the FuS-KG is
used and we provide statistics regarding the amount of time needed for completing the reasoning
activity with respect to the dimension of elaborated data.

The evaluators judged the FuS-KG “Concise” because all the axioms included are relevant
with regard to the targeted domain and there are no redundancies. Auch, the FuS-KG has been
judged “Consistent” and “Coherent”. It has been judged consistent because no contradictions
were found by the evaluators and coherent because the evaluators observed little bias between
the documentation containing the informal description of the concepts and their formalization.

Dann, concerning the Organizational ﬁtness, the FuS-KG has been deployed within the or-
ganization as a web service in order to make it easily accessible by the community and potential
stakeholders. Darüber hinaus, as described in Section 4, the ontology has been also deployed within
external architectures. A focus group has been organized with both the modeling team and the
evaluation team for discussions about the adopted methodology, which was judged appropriate
by considering the necessity of working in situ altogether and synchronizing the commitments
of all the people involved.

Endlich, the entire FuS-KG has been analyzed by the OOPS! tool in order to ﬁnd potential pit-
falls and trigger mitigation actions. Since some ontologies have been reused in the core module
of FuS-KG (d.h., the HeLiS ontology), some pitfalls appeared, but all of them pointed to reused
ontology entities. The pitfall record includes P04 (Creating unconnected ontology elements),
P08 (Missing annotations), P11 (Missing domain or range in properties), P13 (Inverse relation-
ships not explicitly declared), and P22 (Using different naming conventions in the ontology).
Jedoch, all pitfalls that appeared in the modules for newly implemented entities during the im-
plementation have been solved. Inconsistencies were checked with the reasoners Pellet [52] Und
HermiT [53] and no errors were found when running them. To ensure that each module met the
14

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

quality needs, the scanning has also been performed separately on each module.

Evaluations on the whole FuS-KG and for all modules were run successfully, im Guten
results. This ensures that the FuS-KG is consistent, meets the requirements, and to the best of
our knowledge, has no errors.

4. Scenarios Integrating The Personal Health Knowledge Graph

In diesem Abschnitt, we describe two real-world scenarios that adopted FuS-KG. In the former,
FuS-KG has been used for performing real-time reasoning to support behavior monitoring. In
the latter, FuS-KG is integrated into a chatbot aiming to populate the argument module with
knowledge harvested from real users through interviews.

4.1. The Integration Within The HORUS.AI Platform

The ontology modules described in Section 3 are exploited for monitoring the functional sta-
tus of a user through their integration into a SPARQL-based reasoner. Such a reasoner is used
for detecting undesired situations within users’ behaviors. When inconsistencies with respect to
the encoded guidelines are detected, the knowledge base is populated with individuals of type
UndesiredEvent that, im Gegenzug, can be used by another component for providing feedback to users.
Reasoning can be triggered in two ways. zuerst, each time a new data package is acquired or
an existing one is modiﬁed in the knowledge base, the reasoner is invoked for processing the
neu, or updated, Information. Data packages can be manually added by the user or automatically
acquired from IoT devices. Zweitens, at the end of a speciﬁc timespan, such as the end of a
day or of a week, the reasoner is invoked with the aim of checking the overall user’s behavior
in such a timespan. In the latter case, the reasoner works on a collection of data labeled with a
timestamp valid within the considered timespan. The integrated reasoner relies on the architec-
ture implemented in RDFPro [54]. RDFPro has been chosen for two main reasons. zuerst, Die
architecture of RDFPro allows the integration of custom methods into reasoning operations (ich)
for performing mathematical calculations on users’ data and (ii) for exploiting real-time informa-
tion acquired from external sources without materializing them within the knowledge repository.
Zweitens, as reported in [54], efﬁcient analysis performed on RDFPro demonstrated the suitabil-
ity of this reasoner with respect to other state-of-the-art reasoners in a real-time scenario. In diesem
arbeiten, RDFPro has been adapted and extended in order to better ﬁt the needs of the proposed
solution. The extension consisted of the integration of new methods supporting the real-time
stream reasoning of sensor data. Hier entlang, we were able to support the real-time processing of
users’ data in a more efﬁcient manner.

We organize the reasoning in two phases: ofﬂine and online. The ofﬂine phase consists of
a one-time processing of the static part of the ontology (d.h., monitoring guidelines, barriers,
arguments, Aktivitäten) when the system starts. This is performed to materialize the ontology
deductive closure, based on OWL 2 RL and some additional pre-processing rules that identify
the most speciﬁc types of each individual deﬁned in the static part of the HeLiS ontology ABox.
Außerdem, this kind of information greatly helps in performing the aggregation operations
during the online reasoning phase.

During the online phase, each time the reasoning is triggered by a user event (z.B., ein neuer
data package is entered by a user) or by a timed event (z.B., a speciﬁc timespan ended), Die
user data is merged with the closed ontology and the deductive closure of the rules is computed.
The resulting UndesiredEvent individuals and their RDF descriptions are then stored back in the

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

knowledge base. The generation of each UndesiredEvent individual is performed in two steps.
Erste, information inferred by aggregating the domain, Überwachung, and user knowledge is used
for generating the UndesiredEvent individuals. Zweite, accessory information is integrated into
the UndesiredEvent individuals for supporting the creation of feedback when the explanation
concerning the detected undesired event is generated. Accessory information includes, zum Beispiel-
reichlich, references to other individuals of the ontology enabling access to the positive and negative
aspects associated with the detected behavior, or the number of times that the speciﬁc guideline
has been violated. This kind of information can be used for deciding the enforcement level of
the persuasion contained within the generated feedback.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Figur 5: The overall picture of the online reasoning process.

Figur 5 summarizes the online phase of the reasoning process whose main components
and steps are detailed in the following sections. The green path, drawn with a continuous line,
executed as the ﬁrst step, is in charge of collecting the rules to validate depending on the trigger
received by the reasoner. The red path, drawn with a dotted line, executed as the second step,
is invoked for collecting rules that can be validated as semantically associated with the ones
collected during the green path. The blue path, drawn with a dashed line, executed as the third
step, generates and populates violations before storing them in the knowledge repository.

As an example of how the reasoning process works in practice, let us consider a patient,
Michelle, who is affected by hyperglycemia; such a condition compromises her physical func-

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

tional capacity since she is often very tired. After a colloquium with her physicians, the high-
lighted problem is that Michelle has a very stressful job and she is used to unloading her stress
on food. Darüber hinaus, given her job schedule, she is not able to plan meal consumption properly
during the day. Michelle started to be monitored by an AI-enabled application including a guide-
line concerning the total amount of calories contained in each meal has to be lower than 1000.
All this information (d.h., user proﬁle, barriers, and rules) are represented within the AI system in
order to make them exploited for reasoning purposes by combining them with the data provided
by Michelle.9

1. :Hyperglycemia a :Profile.
2. :Michelle a :User; :hasUserId “493853”ˆˆxsd:integer;

:belongsProfile :Hyperglycemia.

3. :MR1 a :MonitoringRule; :appliesTo :Hyperglycemia; :zeitliche Koordinierung :Meal;

:monitoredEntity :Food; :command “hasCalories”; :hasOperator “lower”;
:hasMonitoredValue “1000”ˆˆxsd:integer; :hasRuleId “1”ˆˆxsd:integer;
:hasPriority “1”ˆˆxsd:integer.

4. :BBPMichelle a :BehaviorBarrierPerformance.
5. :JobCondition a :Barrier.
6. :BBPMichelle :hasUser :Michelle; :refersTo :MR1;

:isPreventedBy :JobCondition.

Rows 1 Und 2 deﬁne the proﬁle and assign it to Michelle. Row 3 describes the guideline that
Michelle has to follow. Rows from 4 Zu 6 deﬁne the behavior that the mentioned barrier avoids
performing. For the ﬁrst two days, Michelle provided the data about her food intake correctly as
shown below (for brevity, we reported only the meals, or snacks, that trigger the detection of an
undesired event):

:Michelle :consumed :Breakfast-493853-1, :Snack-493853-3, :Dinner-493853-8.
:Breakfast-493853-1 a :Breakfast; :hasTimestamp “2020-12-14T07:19:00Z”;

:hasConsumedFood [ :hasFood :AlmondMilk; :amountFood “250”ˆˆxsd:integer ],
[ :hasFood :RiceFlakes; :amountFood “100”ˆˆxsd:integer ].

:Snack-493853-3 a :Snack; :hasTimestamp “2020-12-14T11:34:00Z”;

:hasConsumedFood [ :hasFood :CannedOrangeSoda; :amountFood “300”ˆˆxsd:integer ],

:Dinner-493853-8 a :Dinner; :hasTimestamp “2020-12-15T19:45:00Z”;

:hasConsumedFood [ :hasFood :CocaCola; :amountFood “330”ˆˆxsd:integer ],

[ :hasFood :Apple; :amountFood “150”ˆˆxsd:integer ].

[ :hasFood :Pizza; :amountFood “450”ˆˆxsd:integer ].

Based on the provided data, combined with the knowledge contained within the HeLiS on-
tology, the reasoner determines that the amount of kilo-calories consumed during each meal,
except for Dinner-493853-8, satisﬁes the rule MR1. This event triggers into the knowledge base
the assertion of the following UndesiredEvent individual:

:undesiredevent-493853-8-20161215 a :UndesiredEvent;

:hasUndesiredEventRule :MR1; :hasUndesiredEventUser :Michelle;
:hasUndesiredEventMeal :Dinner-493853-8; :hasUndesiredEventQuantity 1356;
:hasUndesiredEventExpectedQuantity 1000;
:hasUndesiredEventLevel 2; :hasTimestamp “2016-12-15T19:45:00Z”;
:hasPriority 1; …

The generated individual completes the amount of knowledge that can be exploited by the
system for starting an interaction with the user. In der Tat, the knowledge linked with the Unde-
siredEvent individual can be used for generating the feedback sent to Michelle. In this particular

9For brevity, we avoid discussing the different ways in which the information expressed in natural language can be

formalized as shown in this section. This aspect is out of the scope of this paper.

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Fall, Michelle is advised that she consumed too many calories during a speciﬁc dinner together
with further information describing how this kind of behavior can affect her health. Gleichzeitig
Zeit, the results of the monitoring activity can be also sent to the physician that can use such
information for a better understanding of the reasons which led Michelle to perform undesired
behaviors.

4.2. The Integration within an Argument Collection Chat-bot

The argument module can be easily populated with instances of arguments harvested with
the use of a chatbot. Chatbots are effective tools in argument mining as they explicitly ask users
für (counter) arguments about a topic. Zusätzlich, in manchen Fällen, they are a necessary choice,
as open textual discussions about a very speciﬁc topic are not always available. Zum Beispiel,
in the healthy lifestyle domain, Die (counter) arguments regard users’ barriers, capacities, Und
suggestions from experts (such as nutritionists, psychologists, and coaches) that can be found in
private forums, social networks, or specialized journals. daher, argument mining is difﬁcult
to perform and a chatbot is a more effective solution [55, 56, 57]. Hier, we show how we used
a chatbot for populating the argument module with arguments regarding the Mediterranean Diet
and physical activity.

The Healthy Lifestyles Domain. We harvested arguments regarding barriers and enablers of
speciﬁc prescriptions of the Mediterranean Diet [58] and of a regular physical activity.10 These
prescriptions regard (ich) the number of daily portions of fruit, vegetable, ﬁsh, and milk; (ii) Die
number of weekly portions of red meat, cured meat, sweets, and sugary drinks; Und, (iii) die Zeit
(minutes) of daily and weekly physical activity.

The Involved Users. The users were Computer Science students of the local university
who voluntarily participated in the collection of the arguments. This sample of the population
presents some biases (similar age, Sex, and school degree) that do not affect our goal as we are
not interested in covering all the representative arguments about healthy lifestyles but in an initial
population of the argument module with the use of a bot. Dann, different population samples can
provide a bigger coverage. Zusätzlich, the chatbot can be used by domain experts able to provide
well-known arguments in the literature.

The Chatbot. The chatbot is inspired by [55] and starts by asking some proﬁling questions
(Alter, Geschlecht, and school title). Dann, the users were asked whether they respect each of the above
prescriptions about healthy lifestyles with a simple yes/no click button. Positive cases are then
asked about textual suggestions (d.h., arguments) they would give to friends that would like to
respect such prescriptions but fail. Negative cases are deepened by asking (open-text format): (ich)
why they do not follow that particular prescription; (ii) suggestions for friends that want to follow
such prescriptions; (iii) whether such suggestions would hold for them; Und, (iv) if the previous
point is false, what would they consider a valid suggestion. Users answering with a sentence too
short (with less than 4 Wörter) are encouraged to expand the argument with a chatbot request;
exceptions are the short “I don’t know” answers that are not asked to be expanded. With this
dialogue procedure, we collected arguments from both positive and negative cases.

Processing the Arguments. A manual checking of the arguments has been performed to
discard duplicate arguments (d.h., arguments with the same meaning). This operation can be per-
formed by checking the semantic similarity of arguments with a universal sentence encoder [59].
The arguments were then manually tagged with their functional and ontological types. Even this

10https://sites.google.com/site/compendiumofphysicalactivities/home and http://www.hhs.gov/

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

operation can be automatically performed with the use of Natural Language Processing tech-
niques for information extraction [60].

The Gathered Arguments. The chatbot provided 270 (counter) argument instances for the
argument module. Each argument has its own functional and ontological types. Examples of
arguments are the barriers to following a particular prescription, such as lack of time, forgetting
about the prescription, too much effort, or dislike of the food in the prescription. Other examples
regard suggestions to better follow such prescriptions, z.B., the use of apps for monitoring the
Lebensstil, change of your habits gradually, and alternative healthy food.

5. Conclusion and Future Directions

In this work, we presented three modules extending the HeLiS ontology to provide a con-
ceptualization of “Enablers”, “Barriers” and “Arguments”. These modules aim to enhance the
AI capabilities of coaching systems designed for supporting the monitoring of users’ functional
Status. Besides the description of the three modules, we have shown how such modules have
been integrated into a working AI coaching system, nämlich, HORUS.AI, and we provide a brief
but useful running example showing how the main concepts of these modules can be instantiated.
As mentioned in Section 1, this work represents a ﬁrst step toward the long-term achieve-
ment of having a full-ﬂedged AI coaching system. Future efforts will be focused on three main
directions. Erste, we plan to expand the knowledge base since ontologies are inevitably sub-
ject to constant changes. This will involve domain experts and the exploration of techniques
that leverage some form of data mining able to detect hidden information from large textual
Daten. Zweitens, we plan to integrate ontology with natural language understanding (NLU) Und
natural language generation (NLG) components. Hier entlang, we will be able to investigate strate-
gies about how to automatically transform natural language texts into their equivalent semantic
argument-based representation, sowie, exploit the output of the reasoning process for gen-
erating effective contextual feedback. Thirdly, we plan to evaluate the system in a real-world
coaching scenario. In this work, we did not provide a living lab evaluation since the ontology
itself cannot be evaluated without addressing the point above (d.h., integration with both NLU
and NLG). We will focus on doing such integration in order to deploy the end-to-end system into
real-world scenarios and to observe the effectiveness of the ontology modules presented.

Insbesondere, we will investigate three main directions: expanding the Knowledge Base, Re-

ﬁning the Barrier ontology and sourcing collaboration, and publishing the ontology.

Expanding the Knowledge Base Ontologies are inevitably subject to constant changes, mit
many researchers in the ontology engineering space claiming that ontologies are confronted by
evolution. In order to address this, one should plan the addition of concepts and relations impera-
tive to the domain that are currently absent. This will involve domain experts and the exploration
of techniques that leverage some form of data mining, such as Natural Language Processing and
Machine Learning, because of their ability to detect hidden information from large textual data.
Reﬁnement of the Barrier ontology Ontology reﬁnement is a vitally important maintenance
strategy that can improve the readability and usability of the ontology and support its evolution to
cover new unseen concepts and constraints. Having imported existing ontologies into the Barrier
Ontology, there’s a need to reﬁne the ontological entities in order to retain relevant elements
imperative to the application domain.

Sourcing collaboration and publishing the ontology We aim to publish a stable version of
the ontology. This will help to entice interested people (especially medics or health-modeling

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Experten) to collaboratively contribute to our work, hence improving its usability.
It will also
help to gather feedback from research fellows who contribute to public ontology libraries or
publishing platforms. Publishing the ontology to be reviewed by other researchers is a step that
will be undertaken immediately. BioPortal 11 and OBO Foundry 12 is the open-source repositories
we are currently considering for this. Jedoch, we aim to publish the Barrier Ontology in many
Repositories, requesting the respective communities to comment on all entities and presentation
of the ontology.

Danksagungen

This work has been supported by the HORIZON 2020 HumanE-AI project (Grant 952026).

Verweise

[1] Mauro Dragoni, Tania Bailoni, Rosa Maimone, and Claudio Eccher. Helis: An ontology for supporting healthy
lifestyles. In International Semantic Web Conference (2), Volumen 11137 of Lecture Notes in Computer Science,
pages 53–69. Springer, 2018.

[2] Alastair Baker. Crossing the quality chasm: a new health system for the 21st century, Volumen 323. British Medical

Journal Publishing Group, 2001.

[3] National Committee on Vital and Health Statistics. Classifying and reporting functional status, 2001.
[4] Iezzoni LI and Greenberg MS. Capturing and classifying functional status information in administrative databases.

Health Care Financ Rev, 3(24):61–76, 2003.

[5] Linda P Fried, Karen Bandeen-Roche, PH Chaves, Brent A Johnson, et al. Preclinical mobility disability predicts
incident mobility disability in older women. Journals of Gerontology-Biological Sciences and Medical Sciences,
55(1):M43, 2000.

[6] Graziano Onder, Brenda WJH Penninx, Luigi Ferrucci, Linda P Fried, Jack M Guralnik, and Marco Pahor. Mea-
sures of physical performance and risk for progressive and catastrophic disability: results from the women’s health
and aging study. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, 60(1):74–79,
2005.

[7] Fredric D Wolinsky, Douglas K Miller, Elena M Andresen, Theodore K Malmstrom, and J Philip Miller. Weiter
evidence for the importance of subclinical functional limitation and subclinical disability assessment in gerontology
and geriatrics. The Journals of Gerontology Series B: Psychological Sciences and Social Sciences, 60(3):S146–
S151, 2005.

[8] Kenneth S Boockvar and Mark S Lachs. Predictive value of nonspeciﬁc symptoms for acute illness in nursing

home residents. Journal of the American Geriatrics Society, 51(8):1111–1115, 2003.

[9] Jacqueline Hogan. Why don’t nurses monitor the respiratory rates of patients?

British Journal of nursing,

15(9):489–492, 2006.

[10] Saxon Ridley. The recognition and early management of critical illness. Annals of the Royal College of Surgeons

von England, 87(5):315, 2005.

[11] Eugene Nelson, Beach Conger, Richard Douglass, Dale Gephart, John Kirk, Robert Page, Austen Clark, Ken-
neth Johnson, Kevin Stone, John Wasson, et al. Functional health status levels of primary care patients. Jama,
249(24):3331–3338, 1983.

[12] David R Calkins, Lisa V Rubenstein, Paul D Cleary, Allyson R Davies, Alan M Jette, Arlene Fink, Jacqueline
Kosecoff, Roy T Young, Robert H Brook, and Thomas L Delbanco. Failure of physicians to recognize functional
disability in ambulatory patients. Annals of internal medicine, 114(6):451–454, 1991.

[13] David R Calkins, Lisa V Rubenstein, Paul D Cleary, Allyson R Davies, Alan M Jette, Arlene Fink, Jacqueline
Kosecoff, Roy T Young, Robert H Brook, and Thomas L Delbanco. Functional disability screening of ambulatory
Patienten. Journal of General Internal Medicine, 9(10):590–592, 1994.

[14] Eric J Cassell. Doctoring: The nature of primary care medicine. Oxford University Press, USA, 2002.
[15] Mireia Espallargues, Jose Mar´ıa Valderas, and Jordi Alonso. Provision of feedback on perceived health status to

health care professionals: a systematic review of its impact. Medical care, pages 175–186, 2000.

11https://www.bioontology.org/
12http://www.obofoundry.org/

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

[16] Linda P Fried, Yuchi Young, Gary Rubin, Karen Bandeen-Roche, WHAS II Collaborative Research Group, et al.
Self-reported preclinical disability identiﬁes older women with early declines in performance and early disease.
Journal of clinical epidemiology, 54(9):889–901, 2001.

[17] Bonnie J Wakeﬁeld and John E Holman. Functional trajectories associated with hospitalization in older adults.

Western Journal of Nursing Research, 29(2):161–177, 2007.

[18] Gregory L. Alexander, Marilyn Rantz, Marjorie Skubic, Myra A. Aud, Bonnie Wakeﬁeld, Elena Florea, and Anin-
dita Paul. Sensor systems for monitoring functional status in assisted living facility residents. Research in Geron-
tological Nursing, 1(4):238–244, 2008.

[19] Susan Michie, Rachel N Carey, Marie Johnston, Alexander J Rothman, Marijn de Bruin, Michael P Kelly, Und
Lauren E Connell. From Theory-Inspired to Theory-Based Interventions: A Protocol for Developing and Test-
ing a Methodology for Linking Behaviour Change Techniques to Theoretical Mechanisms of Action. Annals of
Behavioral Medicine, 52(6):501–512, 12 2017.

[20] Kai R. T. Larsen, S. Michie, E. Hekler, B. Gibson, D. Spruijt-Metz, D. Ahern, H. Cole-Lewis, R. Ellis, B. Hesse,
R. Moser, and Jean C Yi. Behavior change interventions: the potential of ontologies for advancing science and
üben. Journal of Behavioral Medicine, 40:6–22, 2016.

[21] J. Weisz, Mei Yi Ng, and S. Bearman. Odd couple? reenvisioning the relation between science and practice in the

dissemination-implementation era. Clinical Psychological Science, 2:58 – 74, 2014.

[22] Nhathai Phan, Dejing Dou, Hao Wang, David Kil, and Brigitte Piniewski. Ontology-based deep learning for human
behavior prediction with explanations in health social networks. Information Sciences, 384:298–313, 2017.
[23] Hao Wang, D. Dou, and Daniel Lowd. Ontology-based deep restricted boltzmann machine. In DEXA, 2016.
[24] Georgios V. Gkoutos, Paul N. Schofield, and Robert Hoehndorf. Chapter four – the neurobehavior ontology: Ein
ontology for annotation and integration of behavior and behavioral phenotypes. In Elissa J. Chesler and Melissa A.
Haendel, editors, Bioinformatics of Behavior: Teil 1, Volumen 103 of International Review of Neurobiology, Seiten
69–87. Academic Press, 2012.

[25] Bart Rutten, C Hammels, Nicole Geschwind, Claudia Menne-Lothmann, Ehsan Pishva, Koen Schruers, Daniel
Van den Hove, Gunter Kenis, Jim van Os, and Marieke Wichers. Resilience in mental health: Linking psychological
and neurobiological perspectives. Acta psychiatrica Scandinavica, 128, 03 2013.

[26] The Consortium and Nicola Mulder. The gene ontology project in 2008. Nucleic Acids Res., 36, 11 2007.
[27] Timothy W. Bickmore, Daniel Schulman, and Candace L. Sidner. A reusable framework for health counseling
dialogue systems based on a behavioral medicine ontology. Journal of Biomedical Informatics, 44(2):183–197,
2011.

[28] Donna Spruijt-Metz, Eric Hekler, Niilo Saranummi, Stephen Intille, Ilkka Korhonen, Wendy Nilsen, Daniel Rivera,
Bonnie Spring, Susan Michie, David Asch, Alberto Sanna, Vicente Traver, Rita Kukakfa, and Misha Pavel. Build-
ing new computational models to support health behavior change and maintenance: new opportunities in behavioral
Forschung. Translational Behavioral Medicine, 5, 09 2015.

[29] Dominik Heckmann, Tim Schwartz, Boris Brandherm, Michael Schmitz, and Margeritta Wilamowitz-

Moellendorff. Gumo – the general user model ontology. pages 428–432, 07 2005.

[30] Panayotis Kikiras, Vassileios Tsetsos, and Stathes Hadjiefthymiades. Ontology-based user modeling for pedestrian
navigation systems. In ECAI 2006 Workshop on Ubiquitous User Modeling (UbiqUM), Riva del Garda, 2006.
[31] A. Katifori, Maria Golemati, C. Vassilakis, G. Lepouras, and C. Halatsis. Creating an ontology for the user proﬁle:

Method and applications. In RCIS, 2007.

[32] Mauro Dragoni, Tania Bailoni, Rosa Maimone, and Claudio Eccher. Helis: An ontology for supporting healthy
lifestyles. In International Semantic Web Conference (2), Volumen 11137 of Lecture Notes in Computer Science,
pages 53–69. Springer, 2018.

[33] Hyeoneui Kim, Jessica Mentzer, and Ricky Taira. Developing a physical activity ontology to support the interop-

erability of physical activity data. Journal of Medical Internet Research, 21(4), 2019.

[34] M. Fern´andez-L´opez, A. G´omez-P´erez, and N. Juristo. Methontology: from ontological art towards ontological

engineering. In Proc. Symposium on Ontological Engineering of AAAI, 1997.

[35] Helena Soﬁa Pinto, Steffen Staab, and Christoph Tempich. DILIGENT: towards a ﬁne-grained methodology for
distributed, loosely-controlled and evolving engineering of ontologies. In Ramon L´opez de M´antaras and Lorenza
Saitta, editors, Proceedings of the 16th Eureopean Conference on Artiﬁcial Intelligence, ECAI’2004, einschließlich
Prestigious Applicants of Intelligent Systems, PAIS 2004, Valencia, Spanien, August 22-27, 2004, pages 393–397.
IOS Press, 2004.

[36] Mari Carmen Su´arez-Figueroa. NeOn methodology for building ontology networks: speciﬁcation, scheduling and

reuse. PhD thesis, Technical University of Madrid, 2012.

[37] Susan Michie, Robert West, Rona Campbell, Jamie Brown, and Heather Gainforth. ABC of Behaviour Change

Theories. 06 2014.

[38] David C Mohr, Stephen M Schueller, Enid Montague, Michelle Nicole Burns, and Parisa Rashidi. The behavioral
intervention technology model: an integrated conceptual and technological framework for ehealth and mhealth

D
Ö
w
N
Ö
A
D
e
D

F
R
Ö
M
H

T
T

:
/
/

D
ich
R
e
C
T
.

ich
T
.

e
D
u
D
N

ich

T
/

A
R
T
ich
C
e
–
P
D

F
/

D
Ö

ich
/

ich

1
0
1
1
6
2
D
N
_
A
_
0
0
2
0
3
2
0
7
2
3
7
9
D
N
_
A
_
0
0
2
0
3
P
D

ich

B
j
G
u
e
S
T

Ö
N
0
7
S
e
P
e
M
B
e
R
2
0
2
3

Data Intelligence Just Accepted MS.
https://doi.org/10.1162/dint_a_00203

Interventionen. Journal of medical Internet research, 16(6):e3077, 2014.

[39] Pascal Hitzler, Aldo Gangemi, Krzysztof Janowicz, Adila Krisnadhi, and Valentina Presutti, editors. Ontology
Engineering with Ontology Design Patterns – Foundations and Applications, Volumen 25 of Studies on the Semantic
Netz. IOS Press, 2016.

[40] Aldo Gangemi, Nicola Guarino, Claudio Masolo, Alessandro Oltramari, and Luc Schneider. Sweetening ontolo-
gies with dolce. In Proceedings of the 13th International Conference on Knowledge Engineering and Knowledge
Management. Ontologies and the Semantic Web, pages 166–181. Springer-Verlag, 2002.

[41] Mauro Dragoni, Alessio Bosca, Matteo Casu, and Andi Rexha. Modeling, managing, exposing, and linking on-

tologies with a wiki-based tool. In LREC, pages 1668–1675, 2014.

[42] Ivan Donadello, Mauro Dragoni, and Claudio Eccher. Explaining reasoning algorithms with persuasiveness: a case

study for a behavioural change system. In SAC, pages 646–653. ACM, 2020.

[43] J.O. Prochaska, C.A. Redding, and K.E. Evers. The transtheoretical model and stages of change, page 97. 2015.
[44] Lisa Chalaguine, Emmanuel Hadoux, Fiona Hamilton, Andrew Hayward, Anthony Hunter, Sylwia Polberg, Und
Henry W. W. Potts. Domain modelling in computational persuasion for behaviour change in healthcare, 2018.
[45] Ivan Donadello, Anthony Hunter, Stefano Teso, and Mauro Dragoni. Machine learning for utility prediction in

argument-based computational persuasion. In AAAI, pages 5592–5599. AAAI Press, 2022.

[46] Leo Obrst, Werner Ceusters, Inderjeet Mani, Steve Ray, and Barry Smith. The Evaluation of Ontologies, Seiten

139–158. Springer US, Boston, MA, 2007.

[47] Aldo Gangemi, Carola Catenacci, Massimiliano Ciaramita, and Jos Lehmann. Modelling ontology evaluation
and validation. In York Sure and John Domingue, editors, The Semantic Web: Research and Applications, 3rd
European Semantic Web Conference, ESWC 2006, Budva, Montenegro, Juni 11-14, 2006, Verfahren, Volumen
4011 of Lecture Notes in Computer Science, pages 140–154. Springer, 2006.

[48] Asunci´on G´omez-P´erez. Ontology evaluation. In Steffen Staab and Rudi Studer, editors, Handbook on Ontologies,

International Handbooks on Information Systems, pages 251–274. Springer, 2004.

[49] Thomas R. Gruber. Toward principles for the design of ontologies used for knowledge sharing?

Int. J. Hum.-

Comput. Stud., 43(5-6):907–928, 1995.

[50] M. Gr¨uninger and M. Fuchs. Methodology for the Design and Evaluation of Ontologies. In IJCAI’95, Workshop on

Basic Ontological Issues in Knowledge Sharing, April 13, 1995, 1995.

[51] Mar´ıa Poveda-Villal´on, Asunci´on G´omez-P´erez, and Mari Carmen Su´arez-Figueroa. Oops! (ontology pitfall scan-

ner!): An on-line tool for ontology evaluation. Int. J. Semantic Web Inf. Syst., 10(2):7–34, 2014.

[52] Evren Sirin, Bijan Parsia, Bernardo Cuenca Grau, Aditya Kalyanpur, and Yarden Katz. Pellet: A practical OWL-DL

reasoner. J. Web Semant., 5(2):51–53, 2007.

[53] Birte Glimm, Ian Horrocks, Boris Motik, Giorgos Stoilos, and Zhe Wang. Hermit: An OWL 2 reasoner. J. Autom.

Reason., 53(3):245–269, 2014.

[54] Francesco Corcoglioniti, Marco Rospocher, Michele Mostarda, and Marco Amadori. Processing billions of RDF

triples on a single machine using streaming and sorting. In ACM SAC, pages 368–375, 2015.

[55] Lisa A. Chalaguine, Fiona L. Hamilton, Anthony Hunter, and Henry W. W. Potts. Argument harvesting using
chatbots. In COMMA, Volumen 305 of Frontiers in Artiﬁcial Intelligence and Applications, pages 149–160. IOS
Drücken Sie, 2018.

[56] Lisa Andreevna Chalaguine and Anthony Hunter. Knowledge acquisition and corpus for argumentation-based
chatbots. In AI3@AI*IA, Volumen 2528 of CEUR Workshop Proceedings, pages 1–14. CEUR-WS.org, 2019.
[57] Lisa Andreevna Chalaguine, Anthony Hunter, Henry W. W. Potts, and Fiona Hamilton. Impact of argument type

and concerns in argumentation with a chatbot. In ICTAI, pages 1557–1562. IEEE, 2019.

[58] Anna Bach-Faig, Elliot M Berry, Denis Lairon, Joan Reguant, Antonia Trichopoulou, Sandro Dernini, F Xavier
Medina, Maurizio Battino, Rekia Belahsen, Gemma Miranda, and et al. Mediterranean diet pyramid today. Wissenschaft
and cultural updates. Public Health Nutrition, 14(12A):2274–2284, 2011.

[59] Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario
Guajardo-Cespedes, Steve Yuan, Chris Tar, Brian Strope, and Ray Kurzweil. Universal sentence encoder for
english. In EMNLP (Demonstration), pages 169–174. Verein für Computerlinguistik, 2018.