Influencing Individually: Fusing Personalization and Persuasion

SHLOMO BERKOVSKY, CSIRO and NICTA

JILL FREYNE, CSIRO
HARRI OINAS-KUKKONEN, University of Oulu
9

Personalized technologies aim to enhance user experience by taking into account users’ interests, prefer-
ences, and other relevant information. Persuasive technologies aim to modify user attitudes, intentions, or
behavior through computer-human dialogue and social influence. While both personalized and persuasive
technologies influence user interaction and behavior, we posit that this influence could be significantly
increased if the two technologies were combined to create personalized and persuasive systems. For example,
the persuasive power of a one-size-fits-all persuasive intervention could be enhanced by considering the
users being influenced and their susceptibility to the persuasion being offered. Likewise, personalized
technologies could cash in on increased success, in terms of user satisfaction, revenue, and user experience,
if their services used persuasive techniques. Hence, the coupling of personalization and persuasion has
the potential to enhance the impact of both technologies. This new, developing area clearly offers mutual
benefits to both research areas, as we illustrate in this special issue.
Categories and Subject Descriptors: J.4 [Computer Appications]: Social and Behavioral Sciences—
Psychology; H.5.1 [Information Interfaces and Presentation]: General
General Terms: Design, Human Factors
Additional Key Words and Phrases: Personalization, persuasion
ACM Reference Format:
Berkovsky S., Freyne J., and Oinas-Kukkonen, H. 2012. Influencing individually: Fusing personalization
and persuasion. ACM Trans. Interact. Intell. Syst. 2, 2, Article 9 (June 2012), 8 pages.
DOI = 10.1145/2209310.2209312 http://doi.acm.org/10.1145/2209310.2209312

1. INTRODUCTION
In an effort to alleviate the pressure placed on information seekers in trawling through
the abundant resources available, the advent of personalized information services
has come about. These services aim to enhance user experience and assist users in
achieving their goals by taking into account their interests and preferences, as can be
seen in search engines, social applications, navigation support tools, and many other
applications [Brusilovsky et al. 2007; Mobasher et al. 2000]. Persuasive technolo-
gies attempt to shape, reinforce or change behaviors, feelings, or thoughts about an

The work of S. Berkovsky and J. Freyne was jointly funded by the Australian Government through the
Intelligent Island Program and CSIRO. The Intelligent Island Program is administered by the Tasmanian
Department of Economic Development, Tourism and the Arts. The work of H. Oinas-Kukkonen was sup-
ported by the Academy of Finland and the Finnish Funding Agency for Technology and Innovation.
Authors’ addresses: S. Berkovsky, ICT Center, CSIRO, Australia and NICTA, Australia; email:
[email protected]; J. Freyne, ICT Center, CSIRO, Australia; H. Oinas-Kukkonen, Department of
Information Processing Science, University of Oulu, Finland.
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted
without fee provided that copies are not made or distributed for profit or commercial advantage and that
copies show this notice on the first page or initial screen of a display along with the full citation. Copyrights
for components of this work owned by others than ACM must be honored. Abstracting with credit is permit-
ted. To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of
this work in other works requires prior specific permission and/or a fee. Permissions may be requested from
the Publications Dept., ACM, Inc., 2 Penn Plaza, Suite 701, New York, NY 10121-0701, USA, fax +1 (212)
869-0481, or [email protected].
c 2012 ACM 2160-6455/2012/06-ART9 $10.00
DOI 10.1145/2209310.2209312 http://doi.acm.org/10.1145/2209310.2209312

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
9:2 S. Berkovsky et al.

issue, object, or action. This can be achieved through software support for carrying
out tasks, computer-human dialogue, credible advice, or social influence [Fogg 2003;
Oinas-Kukkonen and Harjumaa 2009]. Persuasive technologies provide new abilities
that make a desired behavior easier to achieve, and simulate compelling experiences
that can effectively persuade users, or create relationships through a variety of cues to
establish trust and to support a desired change. These technologies are often exploited
to persuade users to maintain a healthy lifestyle, to be environmentally friendly, or
to purchase certain products. Although both personalized and persuasive technologies
aim to influence user interactions or the users themselves, little work has been done in
either area on incorporating techniques proven to work in the other. Most persuasive
applications employ a one-size-fits-all approach to the delivery of persuasive interven-
tions, failing to deliver personalized persuasion that leverages user characteristics and
preferences, or to provide personalized tools that assist users in achieving the intended
goals. Personalized technologies use sophisticated modeling and understanding of user
preferences to provide personalized services, but fail to cash in on increased success
that could potentially be achieved, if their services were supported by state-of-the-art
persuasive communication.
The implementation of personalized and persuasive technologies would enhance the
impact of either personalized or persuasive technology applied in isolation. Personal-
ized systems would benefit from incorporating persuasive techniques to gather valu-
able user information, increase uptake of recommendations, and improve the quality
of service and the overall user experience. Persuasive systems could adapt the type
and intensity of the persuasive interventions to the preferences and characteristics of
each individual user, thus upgrading their persuasive capabilities. We propose that
the impact of the combination of these technologies would exceed the impact currently
seen by them applied independently, and predict an increased interest in investigating
their fusion from both research communities.
In this preface, we take the opportunity to introduce a conceptual framework for
personalized and persuasive technologies. We discuss several categories, scenarios,
and existing work, where the fusions of personalized and persuasive technologies is
already underway, and highlight opportunities for future research that could advance
this area.

2. WAYS IN WHICH PERSONALIZATION CAN ENHANCE PERSUASION

According to Oinas-Kukkonen [2012], behavior change support systems are the pri-
mary focus of research in the area of persuasive technologies. Persuasive technolo-
gies convey persuasive interventions through carefully chosen language, interface, and
modality to influence users’ behavior and perceptions, and different goals and strate-
gies may be applied by persuasive systems to support different outcomes and behavior
change strategies. A key challenge, in particular for mass persuasion, is that often the
target audiences are large and heterogeneous, and include users with wide-ranging
goals, needs, and preferences. Thus, influencing the entire audience effectively with a
one-size-fits-all persuasive intervention is difficult.
The persuasive research community is aware of the potential of adaptation and tai-
loring, as illustrated through the use of names in communication, adaptation to user
input, and delivery of tailored feedback. In addition to existing strategies, we pro-
pose that information relating to the target user could be exploited to personalize the
persuasive intervention itself, such that the message conveyed, the interface used, or
the timing of the intervention could be personalized to the user being targeted. The
proposed fusion of persuasion and personalization encourages the use of deeper user
modeling and personalization techniques throughout the persuasion process. Table I

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
Influencing Individually: Fusing Personalization and Persuasion 9:3

Table I. Fusion of Personalization in Persuasive Technologies

Tool – increases capability to Medium – provides compelling Actor – creates social relationship
achieve goals by experience by with users by
- monitoring progress of - showing personalized cause-and- - providing personalized
parameters important to user effect scenarios language cues
- providing contextualized - facilitating realistic simulations - tailoring interaction to user’s
and personalized suggestions for each user cultural diversity
- adapting textual feedback: - predicting future activities of - adapting relationships to user’s
content, mode, language, the user social circle
method, delivery, interface - providing personalized - facilitating service tailored to
simulated objects user’s behavioral norms

shows different roles that can be taken by persuasive technologies and ways to person-
alize these.

2.1. Personalization to Strengthen the Impact of Persuasive Technologies

We propose three natural opportunities for personalization in persuasive systems: per-
sonalized assistive features focus on monitoring and presenting information about as-
pects of importance to a user; personalized messages tailor the content as well as the
look and feel of the information in order to meet users’ communication preferences;
and personalized strategies focus on responding to a user’s susceptibility to various
persuasive techniques and methods.
Personalized assistive features of persuasive systems may act as facilitators that as-
sist users in achieving their goals in an easy and simple manner. Persuasive systems
are often unresponsive to the preferences of the users and fail to monitor progress with
respect to parameters that are important for them. By incorporating personalization,
which understands the desired change and adaptively supports the user in achiev-
ing this change, the persuasive power of the system could be leveraged. They could
monitor on users’ behalf, provide guidance and support, or even provide encouraging
personalized feedback. An example of such tools would be a personalized exercise
planner in a persuasive fitness application. The planner would recommend a fitness
routine, which considers the fitness level, injuries, exercise preferences, location, and
weather, with the aim of generating a plan that is appealing to and achievable for
that user.
Personalized messages offer a powerful form of communication. They can enrich
persuasive systems through adaptive delivery of the interventions, which reflect the
preferences of the individual using the system. The language, modality, font, layout,
and many other characteristics of the messages can be personalized, allowing users
to relate more to the information, service, and persuasive technique being used. In
addition, the content displayed to an individual can be adapted to a user’s prefer-
ences, tailored to the observed contextual conditions, and certain information can be
highlighted or removed. The information can be delivered at appropriate times (morn-
ing, evening), through the most appropriate medium (email, SMS), and according to
the preferred frequency (daily, weekly). The above exercise planner could deliver its
recommendations through contextualized just-in-time messages, supported by appro-
priate language, visual style, and multimedia content.
A core area, which has been thus far under-investigated, is that of personalized
persuasive strategies, where the type of intervention itself is adapted to a user’s per-
sonality, behavior, and susceptibility to various forms of persuasion. We posit that this
personalization has a huge untapped potential to maximize the impact of persuasive
applications. There are multiple dimensions that the exercise planner could poten-
tially personalize in this scenario, such as the credibility of the information sources,

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
9:4 S. Berkovsky et al.

tone and style of the intervention, inclusion of animated avatars, or application of au-
thoritative language to name a few.

2.2. Practical Examples

There are relatively few studies that successfully incorporate personalized techniques
or features into persuasive systems. Dijkstra [2006] studied the impact of personal-
ized smoking cessation messages, which gave smokers personalized feedback on their
smoking. The system provided to users generic information on the dangers of smok-
ing and personalized information pertaining to their smoking habits. After completing
a computerized questionnaire, one cohort of smokers was presented with the generic
information, while another with personalized information. The results showed that af-
ter four months, the personalized feedback led to significantly higher levels of smoking
cessation than standard non-personalized feedback. In this case, the persuasive power
of the information presented to users was increased by adapting the information to the
reported smoking level of each individual.
The physical activity motivating game design is a persuasive gaming concept which
leverages enjoyment of computer games to encourage players to perform mild physical
activity while playing [Berkovsky et al. 2010]. The design persuades users to perform
physical activity by making the game more difficult and offering virtual in-game re-
wards in return for activity. Initial evaluations showed that the persuasiveness of the
design (in terms of encouraging activity) was related to a player’s gaming skills, such
that better players performed less activity. Thus, a personalized application of the
design was developed, which adapts the difficulty of the game to a player’s skills, in
order to stabilize the persuasive power of the games. This successfully balanced the
amount of activity performed by different players without affecting their willingness to
be persuaded. The use of personalization in this example shows how responding to the
characteristics of individual users can leverage the impact of a persuasive application.
Nguyen et al. [2007] investigated the connection between a persuasive argument
and the characteristics of the users being persuaded. They developed models for the
discrepancy between a user’s and an argument’s positions, the strength of the argu-
ment for the user, and the user’s involvement with the topic of the argument. Users
were modeled through a set of sample arguments, which they were asked to rate. The
evaluation showed that modeling was an important step towards accurately predict-
ing the users’ response to an argument and that it should be applied when selecting
the most appropriate argument to be presented by a persuasive system. The personal-
ized selection of arguments can streamline the persuasion task and make the desired
behavior or attitude change easier to achieve.

3. WAYS IN WHICH PERSUASION CAN ENHANCE PERSONALIZATION

The aim of personalized applications is to provide relevant information or services to
users based on their preferences and needs. Personalization often takes place in rec-
ommender systems, information filtering and information retrieval systems, directed
Web navigation, e-learning platforms, shopping assistants, and many other online ser-
vices [Brusilovsky et al. 2007]. Personalized systems build and sustain user trust and
loyalty through the provision of intelligent support adapted to user requirements.
The personalization cycle can be broadly divided into two components: user model-
ing and personalized service delivery. The former focuses on the mining and extrac-
tion of the required user information from observed interactions with the system. The
latter focuses on the development of accurate personalization algorithms and provi-
sion of the actual service to users. Figure 1 illustrates the personalization cycle, the

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
Influencing Individually: Fusing Personalization and Persuasion 9:5

Fig. 1. Fusion of persuasion in personalized technologies.

information exchanged between the two components, and the ways in which we sug-
gest its enhancement through persuasive technologies.

3.1. Persuasion to Increase Uptake of Personalized Technologies

The key fusion points for persuasion in personalized systems lie in the user-related
functional areas, which we denote by persuasive user experience and persuasive data
acquisition.
The most general way in which persuasion could be included in personalized sys-
tem is through the information, language, media, and communication modes used by
the system. Persuasive use of attractive avatars, praise, and humorous language will
improve user experience and the users will be more likely to use the system again. To
establish and successfully sustain user enjoyment, designers of personalized systems
have to consider the power of the social role, which has been successfully investigated
in the persuasive research. In addition, personalization systems may benefit from ex-
plaining to users the reasoning behind a recommended or filtered item(s), or suggested
information. Explaining to users the system’s behavior builds up trust, which, in turn,
increases both user loyalty and the uptake of the services. For example, consider a
personalized recommender system deployed by an e-commerce Web site. The recom-
mender would exploit persuasive technologies to explain the recommendations and
make them look attractive to users, thus, increasing their uptake.
Personalized search engines, navigation aids, learning tools, and recommender sys-
tems require accurate information pertaining to their users in order to provide person-
alized services. This information can take the form of explicitly provided user data or
implicit data learned from the observed user interactions. Acquiring rich and reliable
user information has been a major challenge for personalized technologies. We pro-
pose that persuasion could be used to encourage users to provide more information,
alleviating the data acquisition challenge. The use of persuasive language, praise, and
rewards can encourage users to provide more information. Persuasive tools, such as
monitoring, reminders, and suggestions, can play an important role in increasing the
amount of content contributed by users, especially in social media applications. In ad-
dition, the persuasive power of simulated scenarios can be leveraged to demonstrate
quality enhancements that could potentially be achieved if more user information was
available to the system. The above-mentioned e-commerce recommender would ask
users to rate the purchased items or to offer users the opportunity to answer rele-
vant questions posted by other users in order to learn their preferences and encourage
contribution of user-generated content.

3.2. Practical Examples

Work on the persuasive nature of personalized systems has become popular as re-
search into the interaction, presentation, and user interfaces of personalized systems
has attracted increased attention. Often, however, work that focuses on encouraging
users to provide information and follow recommendations—which are clearly persua-
sive users tasks—is not labeled to indicate this.

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
9:6 S. Berkovsky et al.

Herlocker et al. [2000] examined the compelling nature of textual explanations that
supports recommendations in movie recommender systems. They evaluated in a live
user study 21 variants of explanations, ranging from algorithm-specific to domain-
specific information. The most influential or persuasive explanations were discovered
to contain visual representations of information about the ratings of like-minded users,
information on the past accuracy of the recommendations provided by the system, sim-
ilarity of the recommended movie to other movies already seen by the user, and infor-
mation on the presence of the user’s favorite actors in the movie. These are all visual
cues that convey persuasive messages, which explain the nature of the recommenda-
tions and increase user trust.
Farzan and Brusilovsky [2009] investigated the use of persuasive cues in a per-
sonalized navigation support system. This work evaluated the role of visual social
cues (icons representing the amount of reading and annotation by other users in the
community) in persuading users to take up recommendations for relevant documents
and, thus, simplify their navigation. It was discovered that showing cues relating to
the actions of other users in the community successfully affected user behavior and
that users followed these cues when seeking relevant information. The results were
discovered to depend on user factors (degree of trust) and on contextual factors (time
availability), which affected the perceived usefulness or persuasiveness of the cues. In
this example, the inclusion of visual persuasive cues affected the uptake of services
provided by a personalized navigation support system.
Felfernig et al. [2007] proposed that the presentation of recommended items and the
presence of other items influence user choices within the recommendation set. They
analyzed the position and decoy effects in recommendation lists and their impact on
the persuasiveness of the recommended items. The evaluation showed that the per-
ceived utility of a recommended item changes in the light of the surrounding items and
that position effects are important in the design of item comparison pages. Specifically,
the appeal of items changed when similar, but better-value or higher-specification,
items were shown close to the recommended item. They investigated methods to de-
termine the ordering and decoy strategies that can effectively persuade users to con-
sume a recommended item. Thus, including decoy items in recommendation lists can
be considered a persuasive strategy aimed at boosting the attractiveness of target rec-
ommended items.

4. ARTICLES IN THE SPECIAL ISSUE

Three works exemplifying the application of personalization in persuasive technolo-
gies and of persuasion in persuasive technologies were accepted for publication in this
special issue.
“Adaptive Persuasive Systems: A Study of Tailored Persuasive Text Messages to Re-
duce Snacking” by Kaptein, De Ruyter, Markopoulos, and Aarts presents a persuasive
system aimed at changing the eating habits of users by encouraging reduced snacking.
Persuasive interventions of the system were delivered through mobile text messages,
which were personalized according to users’ susceptibility to various influence strate-
gies. A two-week study involving more than 200 users compared the impact of three
types of messages and discovered that personalized messages were more effective than
non-personalized ones. This article is among the first to practically demonstrate the
potential of personalized persuasive strategies (see Section 2.1), and pave the way for
further research in this direction.
In “Investigating the Persuasion Potential of Recommender Systems from a Qual-
ity Perspective: An Empirical Study,” Cremonesi, Garzotto, and Turrin experimen-
tally assess the persuasiveness of several TV program recommender systems. A

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
Influencing Individually: Fusing Personalization and Persuasion 9:7

six-month-long large-scale user study, which measured the capability of recommenders

to increase sales and diversify of video content consumed by users, was conducted. It
was found that user acceptance of personalized recommendations is higher than of
non-personalized ones, that the level of acceptance increases over time, and that the
recommendations increase consumption of long-tail, that is, not popular, items. Thus,
this article exemplifies the power of persuasive personalized user experience (see Sec-
tion 3.1) in modifying the behavior of users and their interaction with a recommender
system.
Finally, “System Personality and Persuasion in Human-Computer Dialogue” writ-
ten by Andrews investigates the integration of user characteristics in the generation
of persuasive human-computer dialogue. Specifically, the work evaluates the impact of
considering a user’s degree of extraversion on the perceived persuasiveness and trust-
worthiness of a system. Two studies, involving more than 140 participants, ascertain
the dependencies between a user’s personality, the perceived personality of the sys-
tem’s arguments, and the impact of the persuasive dialogue. The number of support
statements in the generated arguments was found to determine the perceived qual-
ity of the interaction. Hence, this article demonstrates the practical natural language
generation application of personalized persuasive messages (see Section 2.1).

5. DISCUSSION
The potential impact of fusing personalized and persuasive technologies is tremen-
dous. However, their fusion also raises a number of technological and ethical issues,
which can influence and motivate future research in this area.

Emerging opportunities. Most existing online persuasive strategies are digital re-
flections of well-established offline strategies studied in behavioral research. However,
Web-based and mobile environments offer a cardinally new paradigm and opportuni-
ties for new persuasive research. For example, social networking systems offer oppor-
tunity for persuasion through strong and weak ties. How can these online contexts
provide opportunities to produce novel online persuasive strategies for personalized
persuasion?

User modeling. The user modeling process, which is required to realize personalized
persuasive strategies, is a challenging task. The construction of persuasion-related
user models requires explicit information about user susceptibility to various forms of
persuasion. This information is not readily available and is unlikely to be successfully
learned from the implicitly observed system interactions. So how do we progress in
effectively gathering user modeling data that can facilitate the provision of accurate
personalized persuasion?

Ethical issues. The introduction of personalized persuasion can lead to an ethical

dilemma, as user requirements may conflict with a system designer’s intentions, in
particular in commercial applications. For example, the primary goal of e-commerce
sites is to increase sales and revenues, whereas the users are interested in purchasing
products reflecting their needs and abilities. How should we balance what is best
for the user and the commercial realities facing the service provider when delivering
personalized persuasive interventions?
In summary, the fusion of persuasion and personalization is a highly promising and
appealing area for both scientific research and practical design. We would like to invite
academics and practitioners to elaborate these ideas and help advance the field with
influential and targeted solutions.

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.
9:8 S. Berkovsky et al.

REFERENCES
B ERKOVSKY, S., F REYNE , J., C OOMBE , M., AND B HANDARI , D. 2010. Recommender algorithms in activity
motivating games. In Proceedings of the ACM Conference on Recommender Systems. ACM, New York,
175–182.
B RUSILOVSKY, P., K OBSA , A., AND N EJDL , W. 2007. The Adaptive Web: Methods and Strategies of Web
Personalization. Springer, Berlin.
D IJKSTRA , A. 2006. Technology adds new principles to persuasive psychology: Evidence from health educa-
tion. In Proceedings of the Persuasive Technology Conference. 16–26.
FARZAN, R., AND B RUSILOVSKY, P. 2009. Social navigation support for information seeking: If you build
it, will they come? In Proceedings of the International Conference on User Modeling, Adaptivity and
Personalization. 66–77.
F ELFERNIG, A., F RIEDRICH , G., G ULA , B., H ITZ , M., K RUGGEL , T., L EITNER , G., M ELCHER , R., R IEPAN,
D., S TRAUSS, S., T EPPAN, E., AND V ITOUCH , O. 2007. Persuasive recommendation: Serial position
effects in knowledge-based recommender systems. In Proceedings of the Persuasive Technology Confer-
ence. 283–294.
F OGG, B. J. 2003. Persuasive Technology: Using Computers to Change What We Think and Do. Morgan
Kaufmann.
H ERLOCKER , J. L., K ONSTAN, J. A., AND R IEDL , J. 2000. Explaining collaborative filtering recommen-
dations. In Proceedings of the ACM Conference on Computer Supported Collaborative Work. ACM,
New York, 241–250.
M OBASHER , B., C OOLEY, R., AND S RIVASTAVA , J. 2000. Automatic personalization based on web usage
mining. Comm. ACM, 43, 8, 142–151.
N GUYEN, H., M ASTHOFF , J., AND E DWARDS, P. 2007. Modeling a receiver’s position to persuasive
arguments. In Proceedings of the Persuasive Technology Conference. 271–282.
O INAS -K UKKONEN, H. 2012. A foundation for the study of behavior change support systems. Person.
Ubiquit. Comput. To appear.
O INAS -K UKKONEN, H. AND H ARJUMAA , M. 2009. Persuasive systems design: Key issues, process model,
and system features. Comm. Assoc. Inf. Syst. 24, 485–500.

ACM Transactions on Interactive Intelligent Systems, Vol. 2, No. 2, Article 9, Publication date: June 2012.