An Adaptive E-Advertising User Model: The AEADS Approach
Alaa A. Qaffas and Alexandra I. Cristea
Department of Computer Science, The University of Warwick, Coventry, CV4 7AL, U.K.
Keywords: E-Advertising, E-Commerce, Personalisation, Adaptive Advertising, User Model, User Profile.
Abstract: By customising advertising campaigns based on the attributes of the user, the efficacy and success of the
campaign is likely to be enhanced. The most challenging yet interesting part to model is the user (or customer).
This paper focuses on an automated, simple, lightweight user model, easy to integrate into an existing system
(storage and operation). Accordingly, the arbitrary commercial website can acquire the ability to retrieve
general data of the user and monitor the behaviour of the user during navigation session on the website. It also
presents a study that assesses the effectiveness of a tool based on this model, via a trial run of a model
prototype with users.
1 INTRODUCTION
Technological advancements have led to a significant
increase in web-based promotions and online
marketing, as target audiences can now be accessed
regardless of time or location. The adaptation of
advertising adds significant benefits to customer
satisfaction and business profits
(InternetAdvertisingBureau, 2012). Availability and
the easiest way to manage the adaptation of
advertising with minimal effort on any commercial
site has become a key demand for businesses. Many
models exist, e.g., the Dexter model (Halasz et al.,
1994), AHAM (De Bra et al., 1999), and LAOS
(Cristea and de Mooij, 2003), but they are proposed
mainly for personalising the educational experience.
Lessons learned from them may be applied here, to
some extent. Moreover, these models do not feature
the lightweight integration of adaptive features on any
website as their main purpose. Therefore, a new
model - the Layered Adaptive Advertising Integration
– has been proposed, based on prior ones, in order to
introduce an easier approach to integrating adaptation
features into any commercial website. Some of its
components differ from those in traditional models.
In particular, the user modelling in the proposed
model is separated into storage and delivery parts, the
latter is not covered in this paper, as it has not been
implemented yet. This separation can potentially
enhance the generalisation, portability and efficiency
of the user model and delivery model. The storage
part is encapsulated and manipulated via XML
representation, to allow the system to be integrated
into any website easily and with only minor changes
to the original database of the website. In addition to
the separation, the storage of the user model and its
operation is added to the delivery model, in order to
facilitate the integration process on any website. This
separation also allows the new model to be easily
expanded.
Our research aims to address the following main
research question:
How can we support website owners in the
creation of adaptive advertising?
This main research question can be addressed by
answering the following sub-research questions:
A. What type of tools do website owners need, to
be able to efficiently add adaptive advertising
in a lightweight manner (as an add-on) to their
website?
B. What kind of support do website owners need,
to be able to use these tools?
To answer these questions, we recommend a
collection of tools, Adaptive E-Advertising Delivery
System (AEADS), which facilitate the creation of
adaptive e-advertising. This paper in particular
focuses on one of the vital components in any
adaptive systems, the User Model (UM). In this paper,
we propose a lightweight UM, with a set of features
and attributes that we consider essential to adaptive
advertising, and which can be easily added to any
static commercial website. Furthermore, this model
is implemented and evaluated with real Internet users
and customers.
5
A. Qaffas A. and I. Cristea A..
An Adaptive E-Advertising User Model: The AEADS Approach.
DOI: 10.5220/0005568600050014
In Proceedings of the 12th International Conference on e-Business (ICE-B-2015), pages 5-14
ISBN: 978-989-758-113-7
Copyright
c
2015 SCITEPRESS (Science and Technology Publications, Lda.)
The following sections discuss the related
research, the user model tool and its evaluation, and
finally provide a conclusion.
2 RELATED RESEARCH
Adaptive hypermedia systems allow for
personalisation, thus improving the efficiency and
accuracy of information distribution (Brusilovsky,
1996). This process consists of three major types of
tasks: acquisition, representation and secondary
inference, and production (Kobsa et al., 2001). The
acquisition tasks identify information regarding
users’ characteristics, computer usage and
environment, in order to construct an initial model of
the user. The representation and secondary inference
tasks inference and express the content of the user
model and makes assumptions about them, such as
their behaviours and the environment. The production
tasks generate the adaptation of the contents and
structure of the system to meet the users’ needs. We
use the classification of the data in a user model by
user, usage, environment, hardware, software, and
location. According to (Brusilovsky and Millán,
2007), an adaptive model considers user’s
characteristics in developing a user model and the
data captured can be categorised as knowledge,
interests, goals and tasks, background, individual
traits, and context of work.
A user model is a basic component in any
personalised system and is a representation of user
data stored for any adaptive changes to the system's
behaviour. All adaptive hypermedia frameworks and
models have a user model as one of their components.
For instance, in AHAM (De Bra et al., 1999), the user
model contains concepts with attributes storing user
preferences, while in LAOS (Cristea and de Mooij,
2003) the user model is even more complex.
There have been many systems proposed to
facilitate adaptation, including AHA! (Bra and Calvi,
1998, Stash et al., 2008), GALE (Smits and De Bra,
2011), ADE (Scotton et al., 2011), and WHURLE
(Brailsford et al., 2001). A generic user model based
on variable-value pairs that facilitate required
adaptations form the basis of ADE, AHA! and GALE
and this is suitable for online advertising purposes as
well. In particular, according to (Mérida et al., 2002)
a model is suggested for the delivery of hypermedia
content that considers the types of users, the devices
used by customers to gain access, the types of access,
the state of the network and the current load on the
server. Nonetheless, these are all standalone systems,
which cannot be integrated into existing ones in a
lightweight manner. XML-based pipelining, as used
by WHURLE for applying lightweight solutions and
standards, is efficient for adding minor modifications
to existing systems, and is, therefore, utilised in our
approach. However, user modelling in WHURLE is
not as extended.
AdSense (GoogleAdSense, Davis, 2006), unlike
our approach, cannot provide advertisements to
clients directly, it just lets advertisers in the Google
Network deliver advertisements to the content site to
be presented to users automatically. It specialises in
banner advertisements and uses location to
personalise content (WebTechnologySurveys,
December 2014). However, this process does not
utilise any form of user-based modelling, or the
assimilation of user information for personalisation
purposes. Among the potential approaches to
selecting the best form of advertisement, adaptive
hypermedia may be used to link the advertisement to
the consumer's taste, via user modelling, and is a
significant element within systems that adapt to the
user (Kobsa, 2007).
Another example, AdROSA (Kazienko and
Adamski, 2007), that makes automatic personalised
web banners, depends mostly on specific browsing
behaviours of a user. It is similar to AdSense, the
portal model of advertising uses AdROSA to deliver
the advertisements.
Social networks are good sources of user
information (Faust, 2007), from which user behaviour
and characteristics for personalising advertisements
can be retrieved. Although the type of content posted
on these websites varies, it is generally indicative of
a user’s preferences, attitudes and behaviours.
Facebook is one of the most popular social
networking sites, with 1.35 billion monthly active
users from around the world (TheStatisticsPortal,
2015). Users can create a personal profile, add
friends, send messages, post status updates and
comments to friends’ “walls”. They can chat together
and upload photos and videos that their friends can
comment on and “like” (Hof, 2011). For these
reasons, Facebook has been used as the first social
medial data-gathering source for the first version of
the system described in this paper, follow-up versions
look into other sources though.
Many existing semantic web-authoring systems
can be used in conjunction with other delivery or
authoring systems (Cristea, 2004, Wu, 2002). In our
case, XML was selected to generate the user model
tool’s internal representation.
The modelling of user profiles involves
acquisition, representation and secondary inference.
Data acquisition can be performed using a variety of
ICE-B2015-InternationalConferenceone-Business
6
different methods depending on class, including user
data acquisition methods, usage data acquisition
methods and environment data acquisition methods.
This includes user-supplied information acquired
through questions asked by the system, acquisition
rules, stereotype reasoning, and plan recognition, a
process which predicts future actions based on
previous patterns (Schmidt, 2003). A simple method
for making a first assessment of others is to classify
them into groups sharing the same interests,
according to a set of criteria – a stereotype (Benaki et
al., 1997b). We use the stereotype technique, as it
makes inferences based on limited observations.
3 AUTHORING ADAPTIVE
E-ADVERTISING
The overall Authoring model of Adaptive E-
Advertising, as informed by prior research and
implementations, especially in the area of
personalised e-learning, includes:
1. The Domain Model - used by businesses to
organise, label and categorise advertisements.
As it has been described elsewhere (Qaffas
and Cristea, 2014b), it is not further detailed
here.
2. The Adaptation Model (Qaffas and Cristea,
2014a) - enabling businesses to adapt the
advertisements they have organised, using the
domain model tool for their customers’ needs.
3. The User Model - representing the personal
data of an individual user, stored for any
adaptive changes to system's behaviours. For
example, it can be used to predict the most
relevant items for the user, when they search
for information, as described below. This is
the focus of our paper.
Here, the social input data component has been
added to the user model, and then some functions of
this model were separated, (e.g., the inference
function) to be used in the delivery engine to support
the integration process.
The user (customer) modelling tool has been
designed to be simple (to have few user model
features), in order to be lightweight, and to integrate
with any potential website user model. With this tool,
we implement the first steps of the user modelling,
including its acquisition data, and retrieve explicit
and implicit data. We use the explicit data supplied
by users, and retrieve data from social networks, by
using the social networks authorisation, and
authentication APIs. We also conduct implicit data
acquisition, by using several techniques, including
stereotype reasoning (Benaki et al., 1997a), and plan
recognition (Schmidt, 2003) to be used in the delivery
Engine.
All of the data about users in the user model is
stored in XML files. Storing all of the data in a
lightweight fashion (XML) facilitates the integration
into any commercial webpage, as XML allows for
pipeline processing and independence to any other
processing on the website. Users can login into the
system via two methods: register (Figure 1), and
Facebook login (Figure 2). By logging in via the
latter, the user model can be automatically populated
with the necessary information for the adaptation of
advertisements. The user information is arranged in
an XML file with attributes such as id, name,
password, email, age, gender,
location, number of logins to site, total
number of clicks on each advertisement,
device used, and software used. All users can
update their information on their profile page. This
data will be stored in the users.xml file (Figure 3).
The social data from the social login allows us to
retrieve sufficient information about users and to infer
from specific to general cases.
Figure 1: User Registration.
Figure 2: User Login.
AnAdaptiveE-AdvertisingUserModel:TheAEADSApproach
7
Figure 3: User Model XML file sample.
The implementation of the user modelling is made by
creating servlets to be used in JSP pages, adding data
to the user_item.xml file, such as the number of
clicks on advertisement for each user, and the number
of times each advertisement is shown, for each user
attribute (Figures 4 a, b and c). The number of clicks
and shows will be utilised to apply plan recognition.
Plan recognition refers to the task of inferring the plan
of an intelligent agent (here, the human customer)
from observing the agent's actions or their effects
(Schmidt, 2003). In addition, this process will depend
on the plan library that businesses create in the
authoring part. The delivery engine checks the
clicked items and the plan library to acquire a
sequence of advertisements to be presented to the
user. The latter process belongs to the delivery engine
part and no further details are given here. Moreover,
a new XML file named
users_items_sequence.xml tracks each
user’s selection sequence of advertisements, albeit
only the final ten selections will be stored in this file.
The threshold of 10 selections was decided based on
trial and error on the testing phase of the system. This
file will be used to predict user actions for current and
similar users.
Furthermore, for advertising adaptations, we
used, as said, the stereotype technique, as it makes
inferences based on limited observations. Each user
is assigned to a group (stereotype), according to the
types of advertisements on websites (a website owner
arranges his advertisements into groups and
subgroups). The system then determines the
activation conditions for applying the stereotype to a
user. For example, if the user model shows that the
user is interested in computers and televisions, then
the system activates the stereotype “technology”.
From the usage data, if, for instance, the user has
bought at least two electronic items or computers,
then the stereotype “technology” can be activated.
a: Show Item
b: Item Details
c: User Item.XML file
Figure 4: Plan Recognition.
Figure 5: Stereotype.
ICE-B2015-InternationalConferenceone-Business
8
The administrator can create and control (add- update
- delete) stereotypes.xml from the stereotype page
(Figure 5). Based on hypotheses H1 (described
below), an initial minimal set of necessary
dimensions for an advertising user model are defined,
and include age, gender, bandwidth, device type,
number of clicks on advertisements, education level,
education type, and hobbies. Each dimension has its
own attributes. In addition, action sequencing is used
in this research to predict the future actions of the
user, to recommend actions based on the action
sequences of other users, or to perform some of these
actions on behalf of the user.
4 SCENARIO
To better understand the usage of the user modelling
tool and the application of the data it stores, we
describe a usage scenario as follows:
When the login page is loaded, Ahmed, a 25-year-
old man, and a customer of a given company, enters
his username and password. He could click the login
button or he can login using his Facebook account.
In both cases, bandwidth, location, device type, and
software used for Ahmed are automatically obtained
by the system. Login with a Facebook account will
simplify access to the website and allows systems to
automatically obtain important data.
Ahmed is using a smart phone with bandwidth
lower than 1M (as extracted by the system). If Ahmed
logs into the website for the first time, then only the
general rules will be applied. All of the
advertisements that are not appropriate for Ahmed
(based on general rules: e.g., advertisements targeted
to women, to higher or lower ages, higher bandwidth,
or another device type) will be excluded. All of the
advertisements that are appropriate for Ahmed, and
all of the advertisements that are not assigned any
rules, will be placed in the queue, to be shown to
Ahmed.
However, if Ahmed logs into the website more
than once, the behaviour rules and some inference
processes will be applied. In order to apply behaviour
rules and inference processes, the system needs to
store all of Ahmed's behaviour, the advertisements
that are shown to him and not clicked, the numbers of
his actions, as well as advertisements that were
shown and clicked, and the number of times they were
clicked. When Ahmed clicks on any advertisement
link, or the advertisement is shown to him, the system
stores all of this data in two fields (number of shows,
and number of clicks for each advertisement). In
addition, the system stores the last ten clicks for
Ahmed to be used to infer his actions.
Based on this data, the system applies the
behaviour rules and places the advertisements that
results from it into another queue; in addition, there
is another queue for the inference process, based on
Ahmed’s history of actions. Finally, the system
decides on an advertisement (or collection thereof)
from these three queues to be shown on the page that
Ahmed loaded.
5 CASE STUDY
5.1 Hypotheses
The following hypotheses have been defined to
evaluate the user model tool:
H0a: The user model (UM) concept for
advertising (as illustrated by the UM tool) is useful
for constructing a user model for recommendation of
advertisements.
H0b: The UM concept for advertising (as
illustrated by the UM tool) is easy to use for
constructing a user model for recommendation of
advertisements.
H0x are the basic hypotheses, and the rest are
derived from them:
H1: The attributes of the proposed UM are
useful for recommending advertisements
(username, password, email, age, gender,
education level, education type, hobbies,
bandwidth, location, device type and
software used).
H2: The data in the user model is adequate for
the advertisements delivery engine
decision.
H3: Automatically generating user model data
(location, device type, and software used)
is useful.
H4: Social networks used as a source for user
data are an appropriate data source for
recommending advertisements.
H5: A user’s advertisement preferences can be
predicted, by tracking the user’s behaviour
sequence when they use the system.
H6a: The input and output mechanisms of the
user model tool are useful.
H6b: The input and output mechanisms of the
user model tool are easy to use.
H7: The stereotypes for users with respect to
advertisements recommendation are useful
and appropriate.
AnAdaptiveE-AdvertisingUserModel:TheAEADSApproach
9
H8: The stereotypes for users with respect to
advertisements recommendation are easy
to use.
H9: It is useful to integrate the user model
creation tool in any JSP website.
H10: It is easy to integrate the user model
creation tool in any JSP website.
H11: Any website administrator can
understand, use, and update the
stereotypes.
These hypotheses were evaluated by surveying a
sample group of Internet users and analysing their
answers, as further described below.
5.2 Case Study Setup
The user model tool was evaluated from a
functionality and ease of use perspective by students
studying different subjects and modules (Introduction
to Business, Principles of Marketing, Management
Information System and E-Marketing) at King
Abdul-Aziz University in Jeddah, Saudi Arabia.
Students were deemed appropriate as a testing
population because, first, all of them are Internet
users, and regular online shoppers, who are familiar
with the current online providers. The other reason
was to get a large number of users. Note that, whilst
our users were familiar with the Internet, their study
of a variety of subjects ensured that they were not
only Computer Science specialists, and that the tool
was tested with a wide variety of backgrounds,
knowledge and interests.
Consequently, a sample of 285 Internet users were
asked to evaluate the user model tool. In assessing the
tool, they were asked to do the following.
First, the respondents were introduced to the user
model tool and given a general overview of adaptive
advertising. Next, the participants were instructed to
use the tool and assess its effectiveness. The three-
part questionnaire was provided at this point, to guide
the evaluation process. The first section collects data
on the personal details of each user. The second part
presents a series of Likert scale (McIver and
Carmines, 1981) questions, to encourage the users to
rate the effectiveness of the system in terms of
functionality and application. The Likert scale offered
each respondent a series of five options when
evaluating the user model tool, with the first scale
option being ‘not at all useful’ or ‘very difficult’ and
the last scale option being ‘very useful’ or ‘very easy
to use’, respectively. A series of qualitative questions
were posed in the final section, for respondents to
speak freely about their experiences using the user
model tool.
Table 1: Authoring Tool Features.
A Whole User
model Tool
G Saving Information in
XML as Export Format
B User Registration
Process
H Facebook User Profile
Import
C Login Process I Match User Characteristic
with Stereotype
D Facebook Login
Process
J Adding own Stereotype
E Submitting
Information
K Modifying existing
Stereotype
F Updating User
Profile
L Deleting Stereotype
Table 2: User Model Attributes.
1 Location 10 Education Type
2 Device Type 11 Hobbies
3 Software
Used on
Device
12 Bandwidth
4 Username 13 Get Location Automatically
5 Passwords 14 Get Device Type
Automatically
6 Email 15 Get Software Used
Automatically
7 Age 16 Getting Number of Shows
for Each User
8 Gender 17 Getting Number of Clicks
for Each User
9 Education
Level
18 Getting Last 10 Sequence of
Clicks for Each User
5.3 Results
Out of the 285 questionnaires distributed, 114 were
completed (as students were clearly told that
providing the answers was optional and had no
impact on any of their other university activities or
outcomes). Half of the respondents were aged 18-24,
while 43.9% of them were 25-34, as can be seen in
Figure 6. The results show that two thirds of the
respondents were male and 34.2% were female, as
shown in Figure 7. In addition, the education level
(Figure 8) for the most of the participants was
bachelor’s degree, while 5.3% were at postgraduate
level. This may have skewed our data slightly in the
sense of a preference for the younger and well-
educated population. However, they represent the
generation whose needs must be considered by web
providers, as they are shaping the demand of the
present and future.
The Likert scale (Figure 9) facilitated respondents
assessment of the features and functions of the tool
and the results indicate that all of key features (A-L,
ICE-B2015-InternationalConferenceone-Business
10
Figure 6: Age.
Figure 7: Gender.
Figure 8: Education Level.
defined in Table 1) were well-received. The tool’s
primary features were highly rated by users as each
allocated a minimum score of four indicating that
users found the tool’s features are useful, and the
standard deviation values of 0.47-0.50 were obtained.
Therefore, as each score exceeded three, the user
model tool can be deemed ‘useful’. The most popular
features of the tool were ‘Saving Information in XML
as Export Format’, and ‘User Registration Process’
while the least popular features were (but still above
four) were ‘Match User Characteristic with
Stereotype’ and ‘Modifying Existing Stereotype’
while the slightly lower enthusiasm for these features
may be caused by misunderstanding the purpose of
the stereotype. Therefore, some respondents may
have felt that these features were less vital, when
compared to others. Nonetheless, as each of these
rules obtained a minimum score of four, they can still
be regarded as useful. These results support
hypotheses H6a and H7 indicating that the input and
output mechanisms of the user model tool are useful,
and the stereotypes for users with respect to
advertisements recommendation are useful and
appropriate.
Figure 9: Usefulness (Ox axis detailed in Table 1).
The participants agreed that it is useful to collect all
of the user model attributes to allow the selection of
the appropriate advertisements, based on their profile
and preferences. Figure 10 shows that user model
attributes are useful or very useful, as the average
score of 4.47-4.65, whereas the standard deviation
values range between 0.48-0.50. Scoring highest in
terms of usefulness for the user model attributes were
“Education Level” and “Location”. These results
support hypotheses H1 and H3 to some extent, which
said that the attributes of the proposed UM are useful
for recommending advertisements, and automatically
generating user model data is useful. The lowest
scoring attributes were ‘Get Software Used
Automatically’ and “Getting Last 10 Sequence of
Clicks for Each User”, although both elements scored
above four. This may be due to a fear of their
behaviour being tracked. Therefore, users felt that
these attributes were useful, but not as vital. These
outcomes support hypothesis H2 and H5 to some
extent, as a user’s advertisement preferences can be
predicted, by tracking the user’s behaviour sequence
when they use the system and the data in the user
model is adequate for the advertisements delivery
engine decision.
All features were deemed to be easy or very easy
to use, with average values of 4.46-4.61 and standard
deviation values of 0.49-0.55. Consequent data
analysis showed that users were particularly
impressed with the ‘Updating User Profile’ and
‘Facebook User Profile Import’ features but not quite
AnAdaptiveE-AdvertisingUserModel:TheAEADSApproach
11
Figure 10: Usefulness (Ox axis detailed in Table 2).
as impressed with ‘Saving Information in XML as
Export Format’ and ‘Match User Characteristic with
Stereotype’ that support hypotheses H7 and H8,
which indicate that the stereotypes for users with
respect to advertisements recommendation are
appropriate and easy to use. However, these
components still received a minimum score of four,
which implies that these components are easy to use.
Generally, these investigation results indicate that the
user model tool is easy to use (Figure 11).
Figure 11: Ease of Use (Ox axis detailed in Table 1).
5.4 Qualitative Answers and Discussion
The last part of the questionnaire asked respondents
to extend their feedback about the user model tool in
order to highlight aspects that could be improved.
This stage of research is fundamental, as it contributes
towards enhancing modelling performance, by
facilitating the efficient dealing with system issues, as
they arose. Several respondents claimed that the tool
should offer a more diverse range of hobbies as
features, so that the scope of targeted campaigns
could be extended, while others praised the Facebook
login feature, which is now commonly offered by the
majority of web-authoring applications. This feature
is particularly useful, as the students were only
required to remember one set of credentials to run
different applications, it increases the integration of
the user model with other web-based systems and
increases overall functionality and ease of use. These
results support to some extent hypothesis H4 which
indicates that Social networks used as a source for
user data are an appropriate data source for
recommending advertisements. One respondent also
stated that the tool should refer to age in numbers
rather than letters. Several respondents did not offer
any specific suggestions on improving the tool, but
acknowledged that it was an interesting topic of
research, as online marketing systems and strategies
become more and more advanced. Thus, the system
should perhaps be promoted as a user-friendly tool, as
opposed to a more advanced mechanism that requires
specialist knowledge to run. Some also expressed
confusion with regards to calculating bandwidth, so it
may be necessary to take bandwidth limitations into
consideration automatically, a modification that will
increase usability in tracking these details on behalf
of the user. Moreover, one respondent questioned
why data was stored in XML as opposed to a
database, so it may be necessary to explain how XML
data can be transferred easily between different
programmes. This support hypothesis H6a and b to
some degree, in that the input and output mechanisms
of the user model tool are useful and easy to use. In
addition, regular users do not require such advanced
knowledge of the system in order to use it effectively.
Another respondent suggested that additional
demographical data should be collected, in order to
create more in-depth user profiles and identify more
specific target audiences. Similarly, another
suggested the insertion of additional fields to
diversify the tool, as more specific rules could be
made in order to create more advanced marketing
strategies. These are all useful suggestions, but need
treated with care, as the main purpose was to obtain a
light, flexible, easily transferable and applicable user
model. Prior experience with adaptive hypermedia
shows that adding a large number of features may
only result in confusing the user. A way to deal with
these various needs is to allow users some higher
degree of customisation of the variables used -
dependent however not only on their needs, but also
on their knowledge of adaptive processes and
systems, as was proposed in the context of adaptive
education (De Bra et al., 2010). Moreover, the focus
here is on developing a user model, and not the
strategies that would be implied by it. Finally, in
terms of interface and usability, one user stated that
the system requires a more attractive UI, though this
may not be a pertinent concern at this stage of the
research process, the provision of a more attractive UI
would undoubtedly improve usability and attract
more users.
We believe that the system could increase the
sales potential of businesses, by facilitating the
accurate targeting of advertisements, based on a
series of predefined demographic attributes and rules.
This modified user model could offer more portability
ICE-B2015-InternationalConferenceone-Business
12
to adaptive advertising systems and be integrated into
any website, which support hypotheses H9 and H10
“It is useful and easy to integrate the user model
creation tool in any JSP website”. In addition, this
model would facilitate the extension and expansion of
existing systems and would offer a flexibility that we
believe will help any business to personalise their
advertisements, without the need to overhaul their
existing business model. The website can call a
method that resides on the same site in a specified
location, using a code to manage all advertisements
on that page, to alter them according to adaptation
rules (Stash et al., 2007) and to keep records of those
that have been displayed and clicked in the user
model for current and future adaptation. These
outcomes support hypothesis H11 to some extent, as
any website administrator can understand, use, and
update the stereotypes.
6 CONCLUSIONS AND FUTURE
WORK
In this paper, a lightweight user modelling approach
has been proposed. It could help Internet users to
register to any web-based e-commerce system, and
thus help companies’ access their target audience
more directly, by tailoring their marketing campaigns
towards specific consumer demographics and
focusing their advertisements on users who satisfy a
predetermined range of criteria. Based on the
outcome of theoretical and practical testing, a
minimum set of user model dimensions have been
validated. The evaluation results indicate that the
initial functionality and usability of the small
prototype system is promising. Further modifications
are planned, based on the suggestions offered by
survey respondents. The user modelling tool can be
refined further, by taking into account user feedback
and creating a lightweight adaptive system that is
more customisable, and based on the needs and
preferences of Internet users. As an immediate next
step, in our follow-up studies, the delivery engine will
be implemented, which is resident on the same
website server, to deliver the advertisements to
Internet users. This part parses the contents in the
XML file and uses adaptation strategies to send the
appropriate advertisements to the appropriate user,
based on their user model.
REFERENCES
Benaki, E., Karkaletsis, A. & Spyropoulos, D. 1997a. User
Modeling In Www: The Umie Prototype. Proc. Of The
Workshop” Adaptive Systems and User Modeling On
the World Wide Web, 6th International Conference On
User Modelling UM.
Benaki, E., Karkaletsis, V. A. & Spyropoulos, C. D. 1997b.
Integrating User Modeling Into Information Extraction:
The Umie Prototype. User Modeling. Springer.
Bra, P. D. & Calvi, L. 1998. Aha! An Open Adaptive
Hypermedia Architecture. New Review of Hypermedia
and Multimedia, 4, 115-139.
Brailsford, T. J., Choo, B. S., Davies, P. M. C., Moore, A.,
Stewart, C. D. & Zakaria, M. R. 2001. Web-Based
Hierarchical Universal Reactive Learning Environment
(Whurle): An Overview (White Paper for the Whurle Project).
Brusilovsky, P. 1996. Adaptive Hypermedia: An Attempt
to Analyze and Generalize. In: Brusilovsky, P.,
Kommers, P. & Streitz, N. (Eds.) Multimedia,
Hypermedia, and Virtual Reality Models, Systems, and
Applications. Springer Berlin Heidelberg.
Brusilovsky, P. & Millán, E. User Models for Adaptive
Hypermedia and Adaptive Educational Systems. The
Adaptive Web, 2007. Springer-Verlag, 3-53.
Cristea, A. I. 2004. What Can The Semantic Web Do For
Adaptive Educational Hypermedia? Educational
Technology and Society, 7, 40-58.
Cristea, A. I. & De Mooij, A. 2003. Laos: Layered Www
AHS Authoring Model And Their Corresponding
Algebraic Operators. Www03 (The Twelfth
International World Wide Web Conference), Alternate
Track on Education, Budapest, Hungary.
Davis, H. 2006. Google Advertising Tools: Cashing In With
Adsense, Adwords, And The Google Apis, " O'reilly
Media, Inc.".
De Bra, P., Houben, G.-J. & Wu, H. 1999. Aham: A Dexter-
Based Reference Model for Adaptive Hypermedia.
Proceedings of the Tenth ACM Conference On
Hypertext And Hypermedia: Returning To Our Diverse
Roots: Returning To Our Diverse Roots. Acm.
De Bra, P., Smits, D., Van Der Sluijs, K., Cristea, A. &
Hendrix, M. Grapple: Personalization and Adaptation
In Learning Management Systems. World Conference
on Educational Multimedia, Hypermedia And
Telecommunications, 2010. 3029-3038.
Faust, K. 2007. Very Local Structure in Social Networks.
Sociological Methodology, 37, 209-256.
Googleadsense. Maximize Revenue From Your Online
Content [Online]. Available: www.Google.Com/
Adsense/ [Accessed 25 March 2014.
Halasz, F., Schwartz, M., Grønbæk, K. & Trigg, R. H. 1994.
The Dexter Hypertext Reference Model.
Communications of the ACM, 37, 30-39.
Hof, R. D. 2011. Facebook's New Ad Model: You. Forbes,
188, 106-+.
Internetadvertisingbureau 2012. Internet Advertising
Revenues Report 2012 Full Year Results.
Kazienko, P. & Adamski, M. 2007. Adrosa—Adaptive
Personalization of Web Advertising.
Information
Sciences, 177, 2269-2295.
Kobsa, A. 2007. Generic User Modeling Systems. The
Adaptive Web. Springer.
AnAdaptiveE-AdvertisingUserModel:TheAEADSApproach
13
Kobsa, A., Koenemann, J. & Pohl, W. 2001. Personalised
Hypermedia Presentation Techniques For Improving
Online Customer Relationships. The Knowledge
Engineering Review, 16, 111-155.
Mciver, J. & Carmines, E. G. 1981. Unidimensional
Scaling, Sage.
Mérida, D., Fabregat, R. & Marzo, J.-L. 2002. Shaad:
Adaptable, Adaptive and Dynamic Hypermedia System
for Content Delivery. Workshop on Adaptive Systems
for Web Based Education. Waswe2002. Málaga
España, 2002. Citeseer.
Qaffas, A. & Cristea, A. 2014a. How to Create an E-
Advertising Adaptation Strategy: The Aeads Approach.
In: Hepp, M. & Hoffner, Y. (Eds.) E-Commerce and
Web Technologies. Springer International Publishing.
Qaffas, A. & Cristea, A. 2014b. How to Create an E-
Advertising Domain Model: The Aeads Approach. The
2014 International Conference On E-Learning, E-
Business, Enterprise Information Systems, And E-
Government(Eee'14). Las Vegas, United State.
Schmidt, C. F. 2003. Introduction to Plan Recognition
[Online]. Available: Http://Www.Rci.Rutgers.Edu
/~Cfs/472_Html/Planning/Planrecog.Html [Accessed
30 November 2014.
Scotton, J., Stewart, C. & Cristea, A. I. 2011. Ade: The
Adaptive Display Environment for Adaptive
Hypermedia. Proceedings of the ACM Hypertext 2011
International Conference, Eindhoven, the Netherlands.
Smits, D. & De Bra, P. 2011. Gale: A Highly Extensible
Adaptive Hypermedia Engine. Proceedings of ACM-
Chh, 63-72.
Stash, N., Cristea, A. I. & De Bra, P. 2007. Adaptation
Languages as Vehicles of Explicit Intelligence In
Adaptive Hypermedia. International Journal Of
Continuing Engineering Education And Life Long
Learning, 17, 319-336.
Stash, N., De Bra, P. & Cristea, A. 2008. Adaptation To
Learning Styles In A General-Purpose System
AHA!(Adaptive Hypermedia Architecture).
Educational Technology & Society, 11.
Thestatisticsportal. 2015. Number of Monthly Active
Facebook Users Worldwide 2008-2014. Available:
Http://Www.Statista.Com/Statistics/264810/Number-
Of-Monthly-Active-Facebook-Users-Worldwide/
[Accessed 10 February 2015].
Webtechnologysurveys. December 2014. Usage of
Advertising Networks for Websites [Online]. Available:
Http://W3techs.Com/Technologies/Overview/Advertis
ing/All 25 December 2014].
Wu, H. 2002. A Reference Architecture for Adaptive
Hypermedia Applications. Technische Universiteit
Eindhoven.
ICE-B2015-InternationalConferenceone-Business
14
