Personalized Guidance for People Empowerment and Self-efficacy
towards Healthy Lifestyles
The Solution Proposed in SEMEOTICONS
Sara Colantonio, Massimo Martinelli and Ovidio Salvetti
Institute of Information Science and Technologies, Italian National Research Council, ISTI-CNR
Via G. Moruzzi, 1 – 56124 Pisa, Italy
Keywords: Users’ Profiling, Personalized Guidance Systems, Wellbeing Evaluation.
Abstract: This paper discusses the problem of fostering lifestyle changes towards healthier habits by means of
coaching and supportive messages in the frame of a tailored users’ guidance. Starting from the importance
of behavioural changes to foster wellbeing and disease prevention, the main aspects of tailored users’
guidance are reviewed, with a brief overview of the methods presented in the literature. The solution
proposed in the EU FP7 Project SEMEOTICONS is then presented, discussing its advantages with respect
to the state of the art.
1 INTRODUCTION
Primary prevention, in terms of lifestyle
interventions, has demonstrated to be the best
strategy to effectively modify the main patho-
physiological factors responsible of the genesis of
the most common chronic and disabling diseases.
Indeed, if we would exercise regularly, eat healthy,
control the stress, not smoke and moderate the use of
alcohol, about 90% of type II diabetes, 80% of
coronary heart disease, and 70% of stroke could be
prevented (Sassi and Hurst, 2008). These
evaluations have fueled, in the last years, public
initiatives to promote psycho-physical wellbeing,
such as the European Digital Agenda planned for the
next years (EC Digital Agenda, 2013).
In this frame, ICT-enable technologies are seen
as “the most powerful ally” to foster people self-
emporewment and make them active actors in
mantaining healthy lifestyles. Indeed, maintaining a
healthy lifestyle frequently needs the counselling
and supervision of various health professionals such
as dieticians, physical trainers, psychologists and
behaviourists. Such a prevention strategy is
individually tuned and requires an expensive
organization of the health systems. A rationale
alternative to this kind of intensive individual
coaching is the development of ICT systems for self-
learning and self-monitoring. These solutions are
mainly based on the acquisition of daily survey data
about individual’s behaviour and, accordingly, they
provide tailored suggestions about nutrition, weight,
physical activity, tiredness, and stress. Data
collected by such coaching systems could be
analysed and interpreted by health care professionals
so as to support decision making targeted to the
specific individual conditions.
To be highly effective and have favourable
impact on large-scale prevention of chronic diseases,
these systems might incorporate suitable
personalized coaching mechanisms able to cope with
individuals’ variability, personal peculiarities and
preferences.
It is in this frame that the EU FP7 Project
SEMEOTICONS – “SEMEiotic Oriented
Technology for Individual’s CardiOmetabolic self-
assessmeNt and Self-monitoring” poses itself as an
innovative ICT-based solution: the project will
develop a beyond-the-state-of-the-art multisensory
device which will be able, from one side, to acquire
individuals’ physiological data in a contact-less and
unobtrusive fashion and derive from those an
evaluation about individuals’ wellbeing status, and,
from the other, it will provide personalized user
guidance towards the maintenance of healthy
lifestyle. This paper reports an overview of the
overall project approach to this issue and presents
the solutions that are currently under investigation.
583
Colantonio S., Martinelli M. and Salvetti O..
Personalized Guidance for People Empowerment and Self-efficacy towards Healthy Lifestyles - The Solution Proposed in SEMEOTICONS.
DOI: 10.5220/0004938705830590
In Proceedings of the International Conference on Health Informatics (SUPERHEAL-2014), pages 583-590
ISBN: 978-989-758-010-9
Copyright
c
2014 SCITEPRESS (Science and Technology Publications, Lda.)
The paper starts with a discussion about the quest
for personalized user guidance. Then, the
SEMEOTICONS solution is introduced and the
approach to personalized guidance presented.
Discussion and conclusions conclude the paper.
2 TAILORED USER GUIDANCE
The quest for personalized user guidance towards
healthy lifestyles moves towards the concretization
of a paradigmatic scenario as the one proposed in
(Honka et al., 2011): the possibility to have a kind of
health navigator able to guide the users through
their day and assist them in making healthy
decisions. Such a navigator, just like the GPS
navigator, “would locate users on their individual
health map, calculate the possible routes to improve
one’s health, and continuously monitor and
recalculate the route, if users are not on the intended
track”.
Two main ingredients of this “futuristic device”
are (i) the ability to acquire and interpret data about
the current health status of an individual, and (ii) the
capability to provide convincing and motivating
messages that encourage an individual to recover or
move to the desirable track, by changes in lifestyle.
The main challenges for the former issue, from a
user oriented viewpoint, are mainly related to the
ease and comfort of data acquisition and processing.
ICT advances are going in a good direction in this
respect, permitting the development of less and less
invasive sensors and more and more fashionable
devices (Hekler et al., 2013).
The latter issue is, on the contrary, much trickier,
since it depends on the evaluation of a person
wellbeing and health status and on the definition of
effective guidance applications which requires
merging together methods and theories belonging to
different disciplines, such as psychology, motivation
and communication science, social marketing, and
behavioural theories and economics.
Lifestyle and behavioural changes are, in
general, complex processes that require critical
decisions by an individual who should be strongly
motivated and encouraged. Only if aware of her
needs and conscious of her capability to succeed, a
person will be strong enough to go through with the
change process. Social and contextual stimuli to
maintain the correct behaviour are also determinant
factors that should support this process. Personality,
habits and contextual situations (e.g., stressing work
circumstances) can, on the contrary, bias the success
of the change.
In this overall picture, user-centred approaches,
which are able to supply a strongly tailored support,
are the most viable solutions. The idea is to
maximize self-efficacy: the person’s level of
confidence that she can perform a specific task or
move to and maintain a healthy behaviour in the
future. Indeed, tailored information has been proved
to be more effective in giving consumer information
and is generally preferred by patients (Noar et al.,
2011). As is generally understood, tailoring involves
a combination of strategies and information intended
to reach one specific person based on characteristics
that are unique to that person, related to the outcome
of interest, and derived from an individual
assessment. Profiling the individual user becomes
essential in this frame. Dynamic tailoring using
iterative assessment and feedback is an important
intervention strategy. Multiple behaviours can be
targeted simultaneously without hindering
intervention effectiveness.
So far, several ICT applications have been
developed for behavioural change; they have been
labelled personalized guidance/support systems
(PGS), and defined as information systems able to
foster or adjust attitudes, behaviours or compliance
(Oinas-Kukkonen, 2010). Usually, they employ
technologies coming from a blending of
conventional decision support and tele-monitoring
systems.
The solutions proposed thus far can be mainly
grouped in Internet-based, mobile-based or game-
based interventions. For a detailed review please
refer to (Krebs et al., 2010; Honka et al., 2011). In
particular, mobile-based solutions are more and
more emerging, thanks to the feature of modern
smart phones and smart mobile devices of
incorporating several sensors and offering high user
interactivity and multimedia facilities (Krishna et
al., 2009; Riley et al., 2011). Thanks to the
enjoyable and appealing experience they offer,
videogames have the ability to attract and engage the
user and have demonstrated to have the strong
potential to succeed in improving patients’ skills and
empowerment in disease management and
rehabilitation (Kato, 2010). Although only few
studies have been carried out so far to assess the real
effectiveness of videogames for behavioural
changes, they are for sure the best way to reach the
youngest users (Ceranoglu, 2010) and offer the most
appealing way to present tailored suggestions
(Cannon-Bowers et al., 2011).
Several health domains have been tackled by the
proposed PGS solutions: disease management
(Gibbons et al., 2011; Fjeldsoe et al., 2009),
HEALTHINF2014-InternationalConferenceonHealthInformatics
584
psychotherapeutic use (Andrews et al., 2010; Barak
et al., 2008; Mitchell et al., 2010), health behaviour
change (Webb et al., 2010; Cugelman et al., 2011).
In the latter case, smoking cessation, physical
activity, dietary practices are the most targeted
concerns.
However, regardless of tailoring method, the
effects of ICT-based intervention have been found
overall to decline after intervention completion,
suggesting the need for innovative techniques to
help participants maintaining changes.
In this frame, there is the need of proactive
methods able to aggregate data from advanced
sensing framework, to recognize trends, and to
support constantly the users with effective tailored
guidance and information.
3 SEMEOTICONS PROPOSAL
The solution proposed in SEMEOTICONS goes just
in this direction, since it comprises a self-monitoring
device able to ensure a comprehensive approach to
individuals’ lifestyle changes and to keep the usage
rate also after the first period of interest.
More precisely, SEMEOTICONS core idea is to
develop an interactive smart mirror able to move the
semeiotic analysis of face signs from the office of
medical doctors closer to individual’s normal-life
settings. This way, normal people are enabled to
self-assess their personal wellbeing status, with
particular concern to their cardio-metabolic risk.
Indeed, the face is an efficient discloser of important
clues about a person healthy or unhealthy status. In
particular, the face semiotics is a potential source of
information for surrogate markers of obesity,
metabolomics, cardiovascular homeostasis and
psychophysical status, which are related to cardio-
metabolic risk factors. The main goal of
SEMEOTICONS is just to exploit the valuable
pieces of information conveyed by human face
systematically in a smart system able to help people
in their daily life. To this end, a multisensory smart
mirror, a kind of “wise wizard” mirror, called Wize
Mirror, is being developed to be easily integrated, as
a piece of house-ware, at home, or at different levels
of the health care delivery chain, including fitness
centres, nutritional centres, pharmacies, and so on.
The Wize Mirror is being designed to supply a
contactless evaluation of face signs by acquiring and
processing heterogeneous, multimodal data about
the exterior aspect and shape of the face as well as
more in-depth characteristics mainly related to the
composition of face skin levels. More precisely, the
mirror seamlessly integrates contactless sensors,
such as three-dimensional optical sensors, a
multispectral camera, gas detection sensors, and
microphones. A touch-screen interface is also
included for user’s interactions and output
visualization. Data are mainly collected in the form
of videos, images and gas concentration signals, and
processed to extract a number of biometric,
morphometric, colorimetric, and compositional
descriptors which assess individual’s facial signs.
These signs correspond to the main cardio-metabolic
risk factors, such as overweight,
hypercholesterolemia, hyperglycaemia, impaired
vascular homeostasis, psychological status (i.e.,
stress, anxiety and tiredness) and noxious habits (see
Figure 1).
All these descriptors are planned to be suitably
integrated to form a Virtual Individual’s Model used
to compute and trace the daily evolution of an
individual’s wellness index. A health diary about
Figure 1: A sketch of the data acquisition and processing chain of the Wize Mirror.
PersonalizedGuidanceforPeopleEmpowermentandSelf-efficacytowardsHealthyLifestyles-TheSolutionProposedin
SEMEOTICONS
585
this index is planned to be created so as to enable the
individual to evaluate and personally relate her
lifestyle to her wellbeing. Suggestions and coaching
messages are to be also provided, in relation to the
evolution of the wellness index and each descriptor.
Three main features characterize the resulting
semeiotics-based well-being evaluation: it (i) is non-
invasive, (ii) requires just a natural interaction
between the subject and the system, (iii) supports
and guides personal choices towards improvements
and maintenance of a healthy life style.
Indeed, the development of the Wize Mirror
takes into account the most important factor for a
successful implementation: the final user who is
going to benefit from this technology.
Just think about this scenario: Dave wakes up
and goes to his bathroom to prepare to the day to
start. As usual, he stands for few minutes in front of
his mirror, thinking about all the things that he has
to accomplish during the day and he hear:
“Good morning Dave, lots of things to do today!
You look a bit tired; I see some signs of stress and
fatigue on your face and your eyes. I guess you are
having a very stressful period. Why don’t you try to
take some time just for yourself? In your agenda,
there is room from 5 to 6 p.m. to go to gym. May I
plan this for you? To have a full energy, you can
have a lunch organized in this way...”
This is just a very easy example, which discloses
the usefulness of having a device able to assess the
wellbeing status of an individual in a completely not
intrusive fashion. This peculiar aspect of the Wize
Mirror, which increases the usability factor of the
device, represents a significant step forward with
respect to existing solutions, which often require the
user to wear obtrusive electronic systems to gather
data. Moreover, the Wize Mirror application sees the
user at the centre of each design and development
stage. The non-invasiveness of the system and the
natural interaction pattern (looking into a mirror)
strongly encourages the profitable adoption of this
device. The Mirror is meant to display the results of
the semeiotic computational analysis according to an
intuitive and easy-to-read representation of a set of
comprehensive indicators and a wellness index. The
Graphical User Interface displays the results of the
well-being evaluation as well as the suggestions of a
Personalized Guidance System.
The system is being designed to be a multi-user
device, e.g., shared among the members of a family,
or used in pharmacies and fitness centres. Methods
to automatically recognize the user are being
evaluated in this respect.
3.1 Personalized Guidance Module
SEMEOTICONS PGS is being designed to be a kind
of personal health navigator towards wellbeing, and
thus complements the evaluation of individuals’
wellbeing status with the provision of pertinent
information and suggestions that support and
supervise individual’s self-monitoring.
The personalized guidance, based on user
profiling in terms of preferences and attitudes, is
being implemented to supply advices and
counselling messages towards behavioural changes.
Educational materials are planned to be conveyed as
well to help relating individual’s signs with correct
behaviours and lifestyle. Tracking user’s progresses
in the improvement of her wellbeing descriptors and
highlighting the successes that a user has achieved is
meant to motivate the individual to use the device
and to keep her wellness index high, thus leading to
a better style and quality of life.
Figure 2 sketches the main components of
SEMEOTICONS PGS. Such components mainly
correspond to the main processing steps of the system, i.e.
accurate profiling of users, estimation of the wellness
index, provision of personalized guidance.
In particular, the user profiling along with the
descriptors extracted from the acquired data
composes a Virtual Individual’s Model (VIM) used
to estimate the wellness index. Indeed, the VIM
complements the user profile, to be considered also
as the starting baseline evaluation, with a global
picture of individual’s wellbeing status obtained
from these descriptors with respect to the cardio-
metabolic risk.
Users’ Profiling. As stated in the previous section,
in order to be effective and sustainable, user
guidance needs to be tailored to the individual’s
needs and characteristics. Profiling the user is
determinant in this respect. In particular, in
SEMEOTICONS PGS, the user profile has a
twofold value, since it is meant to be used to:
i. assess the health status of the user at the starting
point, when she will start using the Wize Mirror.
In this respect, it includes all the information
pertaining to the individual’s health behaviours
and clinical risk factors, including the genetic
susceptibility and family history of cardio-
metabolic diseases;
ii. identify users’ characteristics, attitudes, habits
and preferences so as to select the best strategy
to provide suggestions and coaching messages,
and find solutions that motivate to engage with
the behaviour change process and identify the
barriers that should be worked out.
In the most advanced settings under investigation
HEALTHINF2014-InternationalConferenceonHealthInformatics
586
Figure 2: A sketch of SEMEOTICONS Personalized Guidance System – a kind of Personalized Health Navigator towards
healthy lifestyles.
the personal profile is dynamic, taking into account
contextual changes. In particular, since the Mirror
will be a static device, contextual awareness is here
to be meant as the possibility to take into account the
evolving circumstances and situations that the user
can go through, e.g., stressing working or emotional
periods. For the same reason, direct means are
mainly considered to collect data about the users,
i.e., questionnaires. In this respect, several already
available and well-assessed questionnaires are being
evaluated to measure different aspects of physical,
social and mental health, quality of life, behavioural
risk factors, other determinants of behaviour, and
personal characteristics, such as personal motivators.
To understand contextual circumstances,
personalized questionnaires can be envisaged in
correspondence with the detection of specific signs
from the acquired data, e.g., stress or tiredness,
increased weight.
For the definition of the users’ profiles, several
approaches are being investigated, including overlay
models (Brusilovsky and Millán, 2007),
computational methods (Castellano et al., 2007) and
ontologies (Tahir et al., 2013), with a preference for
the hybridization of the latter two approaches.
Wellness Index Estimation. The VIM integrates all
the descriptors extracted from the sensed data,
starting from and according to the user’s profile.
The descriptors correspond to an evaluation of
face signs produced by the main cardio-metabolic
risk factors (see Coppini et al., 2014). In particular,
the following traits of an individual’s face will be
evaluated computationally (see Figure 1):
- face morphology and colorimetry to identify
signs of obesity and psychological status;
- face skin composition to identify signs
corresponding to hyper-glycaemia and hyper-
hypercholesterolemia;
- face skin functionality to evaluate endothelial
function;
- face expressions to identify signs of stress,
anxiety and fatigue;
- other general face traits allowing for the
computation of heart rate and heart rate
variability;
- exhaled composition to identify noxious
substances.
All the descriptors are condensed into a wellness
index, easily displayable to the user, so as to
correlate the evolution of semeiotic signs to
individual’s cardio-metabolic status.
The wellness index represents a non-diagnostic
estimation of a user’s health status, meaningful for
self-assessment and self-monitoring purposes. To
this aim, its temporal evolution is tracked to define a
wellbeing diary.
A proper multidimensional space, the cardio-
metabolic wellbeing space, is being defined to track
the relevant measurements and to extract meaningful
values representing the wellness status. This point is
quite innovative, and, even if the wellness index
extracted is not intended to be used for diagnostic
purposes, it is going to be released as a reliable
indicator of the cardio-metabolic risk.
Suitable machine learning methods are under
PersonalizedGuidanceforPeopleEmpowermentandSelf-efficacytowardsHealthyLifestyles-TheSolutionProposedin
SEMEOTICONS
587
investigation for analyzing, understanding and
transforming the multidimensional vector formed by
the computational descriptors, e.g. non linear
mappings. This way, the most significant
information are extracted and conveyed into the
index. It is worth noting that the wellness index is
being defined to encompass the temporal evolution
of the computational descriptors of facial signs.
To validate the results of the wellness index
estimation, well-established cardio-metabolic risk
charts (e.g., HEART SCORE, Fatty-Liver index,
HOMA index, FINRISK index) are being taken as
validated ground-truth.
The visual representation of the virtual
individual’s model, i.e., an expressive way to
represent the wellness status, is being designed and
developed, tailored on the subject’s
preferences/attitudes. It could vary from a very
simple and friendly visualization – like a comic; to a
more ‘scientific’ one – a sort of augmented subject’s
photorealistic visualization.
Personalized Guidance Provision. SEMEOTICONS
PSG is meant to provide personalized suggestions
and messages, in accordance to (i) the estimated
wellness index and its variation over time, (ii) the
user’s profile in terms of attitudes, habits and
preferences and (iii) possible contextual information
related to user’s life circumstances, the system.
For example, the system might (i) either suggest
to contact the general practitioner, due to a serious
worsening trend of the index or (ii) reward and
encourage the individual subject that is maintaining
a good wellness index or (iii) display dietary
suggestions and/or workout plans, or (iv) supply
specific suggestions according to specific signs
detected, and so on.
This personalized user’s guidance, strictly
coupled with the correlation of the wellness index to
established cardio-metabolic risk charts, is planned
to be specifically tuned to foster the prevention of
cardio-metabolic diseases.
The coaching messages and the information
provided with them are meant to foster
- awareness and comprehension
- abilities and empowerment.
More precisely, the suggestions aim to make the
user aware of the benefits and risks associated with
various options. This is planned to be done with
simple, concrete, correct and high-quality messages,
tailored to users’ characteristics so as to influence
information intake and user engagement. Moreover,
the proposed interventions are meant to be posed so
as to let the users gain greater control over the
decisions and actions affecting their health.
The presentation, visualization and linguistic
style of suggestions are studied to be in accordance
to users’ peculiarities, since they are important
moderators in communication modalities. For
instance, they take into account users’ attitudes to be
anxious, hypochondriac, tending to depression or
cheerful and social.
Inspiration for personalizing the suggestions
styles are being drawn from game design strategies
with the twofold aim of being appealing and
attractive and of reinforcing engagement and
maintaining the interest high.
Techniques used in recommender systems are
under investigation and a proactive decision support
system is being studied, exploiting both procedural
knowledge (formalized through ontologies and open
standards provided by the semantic web
communities) and computational models.
A lightweight inference engine is being designed
to reason on the procedural knowledge and produce
relevant suggestions, while computational models to
be used to address less formalized and unstructured
decisional tasks. Such core decision support system
natively provides personalized guidance; indeed the
procedural knowledge is being designed to be
adaptive and to best adhere to user’s psycho-
physiological status, attitude and inclination.
4 DISCUSSION
AND CONCLUSIONS
ICT applications to foster behavioural changes have
shown to be effective tools to implement primary
prevention, meant as the promotion of healthy
lifestyles. This type of prevention, actually, appears
nowadays as the most viable strategy to reduce the
socio-economic burden of chronic and widespread
diseases, such as cardiovascular and metabolic
diseases.
However, developing successful applications is a
non trivial task, which requires merging methods
and theories from several disciplines, including
computer science, psychology and marketing.
In this paper, we have discussed the main issues
that arise when dealing with this problem and
presented the SEMEOTICONS solution.
In particular, thanks to the main features of
SEMEOTICONS’ expected results, such solution
appears promising. Indeed, it is based on a
completely non invasive evaluation of the health
status of the user, by means of a multisensory device
having the exterior aspect of a mirror. This can be
easily integrated as a piece of houseware and is
HEALTHINF2014-InternationalConferenceonHealthInformatics
588
characterized by three main features (i) non-
intrusiveness, (ii) natural interaction with the user,
(iii) provision of tailored support to personal choices
towards improvements and maintenance of healthy
lifestyles.
In particular, the tailored support is being studied
to overcome the usual shortcomings of behavioural
change applications. Indeed, the suitable selection of
the presentation, visualization and linguistic style of
suggestions are being studied to be in accordance to
users’ peculiarities, since they are important
moderators of effect in communication modalities.
Moreover, personalized guidance services are meant
to be provided continuously and on a daily basis,
helping people to maintain achieved changes and,
thus, overcoming the limits in endurance of other
attempts presented in the literature.
ACKNOWLEDGEMENTS
This work is being partially supported by the EU
FP7-ICT-2013.5.1-611516 Project SEMEOTICONS
started last November 2013.
The authors would like to take all the partners of
the Project Consortium and in particular Dr.
Giuseppe Coppini and M.D. Paolo Marraccini from
the Institute of Clinical Physiology of the Italian
National Research Council and Franco Chiarugi
from the Foundation for Research and Technology -
Hellas.
REFERENCES
Andrews G., Cuijpers P., Craske M.G., McEvoy P., Titov
N., 2010. Computer therapy for the anxiety and
depressive disorders is effective, acceptable and
practical health care: A meta-analysis. PLoS ONE, vol. 5.
Barak A., Hen L., Boniel-Nissim M., Shapira N., 2008. A
comprehensive review and a meta-analysis of the
effectiveness of internet-based psychotherapeutic
interventions. J. Technol. Human Services, vol. 26,
pp. 109–160.
Brusilovsky P., Millán E., 2007. User models for adaptive
hypermedia and adaptive educational systems, in
Lecture Notes in Computer Science New York:
Springer, vol. 4321 LNCS, pp. 3–53.
Cannon-Bowers J.A., Bowers C., Procci K., 2011. Using
video games as educational tools in healthcare,” in
Computer Games and Instruction, S. Tobias and J. D.
Fletcher, Eds. Charlotte, NC: Information Age, pp.
47–72.
Castellano G., Fanelli A.M., Mencar C., Torsello M.A..
2007. Similarity-Based Fuzzy Clustering for User
Profiling. In Proc. of the 2007 IEEE/WIC/ACM Int.
Conf. on Web Intelligence and Intelligent Agent
Technology (WI-IATW '07). IEEE Computer Society,
Washington, DC, USA, 75-78.
Ceranoglu T.A., 2010. Video games in psychotherapy.
Rev. Gen. Psychol., vol. 14, pp. 141–146.
Coppini G., Favilla R., Gastaldelli M., Colantonio S.,
Marraccini P., 2014. Moving Medical Semeiotics to
the DigitalRealm. SEMEOTICONS approach to Face
Signs of Cardiometabolic Risk. In Proc. of
SUPERHEAL 2014 – HEALTHINF 2014. INSTICC.
Cugelman B., Thelwall M., Dawes P., 2011. Online
interventions for social marketing health behavior
change campaigns: A meta-analysis of psychological
architectures and adherence factors. J. Med. Internet
Res., vol. 13.
EC Digital Agenda – http://ec.europa.eu/digital-
agenda/en/life-and-work/living-healthy-ageing-well
(accessed on December 2013).
Fjeldsoe B.S., Marshall A.L., Miller Y.D., 2009. Behavior
change interventions delivered by mobile telephone
short-message service. Amer. J. Prev. Med., vol. 36,
pp. 165–173.
Gibbons M., Wilson R., Samal L., Lehmann C., Dickersin
K., Lehmann H., Aboumatar H., Finkelstein J.,
Shelton E., Sharma R., Bass E., 2011. Consumer
health informatics: Results of a systematic evidence
review and evidence based recommendations.
Translational Behavioral Medicine, vol. 1, pp. 72–82.
Honka A., Kaipainen K., Hietala H., Saranummi N., 2011.
Rethinking Health: ICT-Enabled Services to Empower
People to Manage Their Health. IEEE Reviews in
Biomed. Engineer., vol. 4, pp. 119-139.
Hekler E.B., Klasnja P., Traver V., Hendriks M., 2013.
Realizing Effective Behavioral Management of
Health: The Metamorphosis of Behavioral Science
Methods, Pulse, IEEE , vol.4, no.5, pp.29-34.
Kato P.M., 2010. Video games in health care: Closing the
gap. Rev. Gen. Psychol., vol. 14, pp. 113–121.
Krebs P., Prochaska J.O., Rossi J.S., 2010. Defining what
works in tailoring: A meta-analysis of computer-
tailored interventions for health behavior change. Prev
Med. 2010 Sep–Oct; 51(3-4): 214–221.
Krishna S., Boren S.A., Balas E.A., 2009. Healthcare via
cell phones: A systematic review. Telemedicine e-
Health, vol. 15, pp. 231–240.
Mitchell J., Vella-Brodrick D., Klein B., 2010. Positive
psychology and the internet: A mental health
opportunity,” E-Journal Appl. Psychol., vol. 6, pp. 30–
41.
Noar S.M., Harrington N.G., Van Stee S.K.V., Aldrich R.
S., 2011. Tailored health communication to change
lifestyle behaviors. Amer. J. Lifestyle Medicine, vol.
5, pp. 112–122.
Oinas-Kukkonen H., 2010, Behavior change support
systems: A research model and agenda, in Lecture
Notes in Computer Science. New York: Springer,
2010, vol. 6137 LNCS, pp.4–14.
Riley W.T., Rivera D.E., A.A. Atienza, Nilsen W., Allison
S.M., Mermelstein R., 2011. Health behavior models
in the age of mobile interventions: are our theories up
PersonalizedGuidanceforPeopleEmpowermentandSelf-efficacytowardsHealthyLifestyles-TheSolutionProposedin
SEMEOTICONS
589
to the task? Transl Behav Med. 2011 March; 1(1): 53–
71.
Sassi F., Hurst J., 2008. The prevention of lifestyle-related
chronic diseases. OECD Health Working Papers.
Tahir A., Fattah S., Alfred R., Appolonius H., 2013.
Ontology-based user model and irt for personalised
learning environment, ICERI2013 Proceedings, pp.
4406-4411.
Webb T.L., Joseph J., Yardley L., Michie S., 2010. Using
the internet to promote health behavior change: A
systematic review and meta-analysis of the impact of
theoretical basis, use of behavior change techniques,
and mode of delivery on efficacy. J. Med. Internet
Res., vol. 12.
HEALTHINF2014-InternationalConferenceonHealthInformatics
590
