An Article Conforming To The Formatting Of AISB 2010

an article conforming to the formatting of aisb 2010 name one1, name two1, name three1 and name four2 abstract. this is a word document mad

An article conforming to the formatting of AISB 2010
Name one1, name two1, name three1 and name four2
Abstract. This is a Word document made to conform to the ECAI
specifications. Feel free to recycle it for your purposes.12
1 INTRODUCTION
The notion of responsive environments is broad, encompassing
essentially every space capable of sensing and responding accordingly
to entities that inhabit them (these entities can be people, animals,
or any sort of identifiable objects).
In this work, we focus on a narrower class of responsive environments,
namely those provided with ambient intelligence. Ambient intelligence
was characterised by Gaggioli [1] as referring to physical
environments that are sensitive and responsive to the presence of
people. Their key features are intelligence and embedding.
“Intelligence" here refers to the fact that the digital environment is
able to analyse the context, adapt itself to the people and objects
that reside in it, learn from their behaviour, and eventually
recognise as well as express emotion. “Embedding" means that devices
with computing power will blend into the background of peoples'
activities, and that social interaction and functionality will move to
the foreground. In this paper, we are particularly concerned with
ambient intelligence aimed at adapting to groups of users, with the
group membership continually changing.
To illustrate the class of problems we aim at, let us consider the
case of information delivery to groups of users. Many interesting
applications can be envisaged that fit into this setting:
*
Large displays can be installed in public spaces (airports, train
stations, shopping malls, etc.) for the purposes of advertisement,
entertainment and specific information delivery. The consumers of
these services can form a very heterogeneous group of individuals.
For example, in a train station we can find three individuals
sharing the same physical space: the first one is a tourist with
plenty of available time and interested in shopping local goods,
the second one is a regular passenger who must wait every day for
two hours at the train station to commute, and the third person is
a hurried passenger looking for the right platform to get on a
train that is about to depart. Ideally, a display that is visible
to these three individuals should be sensitive to their interests
and needs and adapt its displayed information accordingly.
*
Digital display windows are becoming ubiquitous in all sorts of
shops. Ideally, these displays should be sensitive to the
customers who approach them, avoiding products that may offend or
annoy customers and presenting content that is capable of raising
the desire to consume, keeping customers in the shop for as long
as possible and making the overall experience of visiting the shop
as pleasant and entertaining as possible.
In this article, for the purposes of illustrating our approach, we
employ the second application above: a bookstore where sensors detect
the presence of customers identified by some portable device (e.g. a
Bluetooth-enabled mobile phone, or a fidelity card equipped with an
active RFID tag). In this scenario there are various sensors
distributed among the shelves and sections of the bookstore which are
able to detect the presence of individual customers (Figure 1
illustrates this scenario). The bookstore can associate the
identification of customers with their profiling information, such as
preferences, buying patterns and so on.

Figure 1. Example of Responsive Environment
With this infrastructure in place, the bookstore can provide customers
with a responsive environment that would adapt to maximise their
well-being with a view to increasing sales. For instance, the device
playing the background music should take into account the preferences
of the group of customers within hearing distance. Similarly, LCD
displays scattered in the store show items based on the customers
nearby, the lights on the shop's display window (showing new titles)
can be rearranged to reflect the preferences and interests of the
group of customers watching it, and so on.
This paper extends and combines our earlier work on managing
responsive environments with software agents [2, 3] and group
adaptation [4, 5]. We describe a scaleable and robust infra-structure
implemented to support a team of software agents to manage devices
shared by a number of people. Our approach naturally addresses a
dynamic environment in which people and devices appear, disappear and
move about in the physical space. Each component is associated with a
software agent that represents the component’s capabilities and needs.
In order to manage the potentially conflicting interests of various
agents sharing resources (e.g., a group of shoppers with different
interests in front of a screen showing articles on offer) we have
experimented with group adaptation techniques. With our
infra-structure, different group adaptation techniques can be easily
adapted and used to control shared devices.
The paper is organized as follows. First, we summarize our findings on
group adaptation from [4, 5]. Next, we describe the agent architecture
proposed in [2,5] for responsive environments. In Section 4, we
integrate the work on group adaptation (described in Section 2) with
the architectural work (described in Section 3). In Section 5, we
discuss a proof-of-concept implementation. Section 6 contrasts this
paper with related work. Section 7 presents our conclusions and
provides directions for future work.
2 GROUP ADAPTATION
This section summarizes our findings on group adaptation from [4, 5]
and relates them to ambient intelligence. Suppose the environment
(e.g. a shop) contains three people, John, Adam and Mary. Suppose a
device in this environment (e.g. a display) is aware that these three
individuals are present and knows their interest in each of a set of
items (e.g. music clips or advertisements). Table 1 gives example
ratings on a scale of 1 (really hate) to 10 (really like). Which items
should the display show, given time for four items?
A
B
C
D
E
F
G
H
I
J
John
10
4
3
6
10
9
6
8
10
8
Adam
1
9
8
9
7
9
6
9
3
8
Mary
10
5
2
7
9
8
5
6
7
6
Table 1. Example of Individual Ratings for Ten Items (A to J)
Many different strategies exist for aggregating ratings of individuals
into a rating of a group (e.g. used in elections, like when selecting
the leader of a political party). Eleven of these (inspired by Social
Choice Theory) are discussed in [4]. For instance, one could average
the ratings of the individuals to obtain a group rating (making E and
F the most preferred items by the group): the Average Strategy. One
could take the minimum of the ratings, assuming that a group is as
happy as its least happy member (giving a group rating of 1 for item
A): the Least-Misery Strategy. We conducted a series of experiments to
investigate which strategy is best (see [4] for details).
In experiment 1, we investigated how people would solve this problem,
so given ratings for individuals (as in Table 1), which items they
thought the group should watch, if there was time for say six items.
We compared our subjects’ decisions (and rationale) with those of the
aggregation strategies. We found that humans care about fairness, and
about preventing misery and starvation (“this one is for Mary, as she
has had nothing she liked so far”). Subjects’ behaviour reflected that
of several of the strategies (e.g. Average and Least Misery were
used), while other strategies were clearly not used.
In experiment 2, we presented subjects with item sequences chosen by
the aggregation strategies. Subjects rated how satisfied they thought
the group members would be with those sequences, and explained their
ratings. We found that the Multiplicative Strategy (which multiplies
the individual ratings) performed best, in the sense that all subjects
thought its sequence would keep all members of the group satisfied.
Several strategies could be discarded as they clearly were judged to
result in misery for group members. We also compared the subjects’
judgements with predictions by simple satisfaction modelling
functions. Amongst other, we found that more accurate predictions
resulted from using quadratic ratings (which e.g. makes the difference
between a rating of 9 and 10 bigger than that between a rating of 5
and 6) and from normalization.
In responsive environments, group membership changes continuously.
Deciding on the next five items to show based on the current members
does not seem to be sensible strategy, as in the worse case, none of
these members may be present anymore when the fifth item is shown.
Additionally, overall satisfaction with a sequence may depend on the
order of the items: for instance, it may be good for satisfaction to
have mood consistency (not putting a depressing item in the middle of
two happy ones), have a strong ending, and provide a good narrative
flow. In experiment 3, we investigated how a previous item may
influence the impact of the next item. Amongst others, we found that
mood (resulting from the previous item) and topical relatedness can
influence ratings for subsequent items. This means that in a
responsive environment, aggregating individual profiles into a group
profile should be done repeatedly, every time a decision needs to be
made about the next item to display.
When adapting to a group of people, you cannot give everybody what
they like all the time. However, you do not want anybody to get too
dissatisfied. For instance, in a shop it would be bad if a customer
were to leave and never come back, because they really cannot stand
the background music. Many shops currently opt to play music that
nobody really hates, but most people not love either. This may prevent
losing customers, but would not result in increasing sales. An ideal
shop would adapt the music to the customers in hearing range in such a
way that they get songs they really like most of the time (increasing
the likelihood of sales and returns to the shop). To achieve this, it
is unavoidable that customers will occasionally get songs they hate,
but this should happen at a moment when they can cope with it (e.g.
when being in a good mood because they loved the previous songs).
Therefore, it is important to monitor continuously how satisfied each
group member is. Of course, it would put an unacceptable burden on the
customers if they had to rate their satisfaction (on music,
advertisements etc) all the time. Similarly, measuring this
satisfaction via sensors (like heart rate monitors or facial
expression recognizers) is not yet an option, as they tend to be too
intrusive, inaccurate or expensive. So, we propose to model group
members’ satisfaction, predicting it based on what we know about their
likes and dislikes.
In [5], we investigated four satisfaction functions to perform this
modelling. We compared the predictions of these satisfaction functions
with the predictions of real users. We also performed an experiment to
compare the predictions with the real feelings of users3. The
satisfaction function that performed best defines the satisfaction of
a user with a new item i after having seen a sequence of items items
as:
with the impact on satisfaction of new item i given existing
satisfaction s is defined as

for 0 ≤  ≤1 and 0 ≤  ≤1. Parameter  represents satisfaction
decaying over time (with =0 past items have no influence, with =1
there is no decay). Parameter  represents the influence of the user’s
satisfaction based on previous items on the impact of a new item. The
psychology and economics literature discussed in [5] shows that mood
impacts evaluative judgement. For instance, half the subjects
answering a questionnaire about their TVs received a small present
first to put them in a good mood. These subjects were found to have
televisions that performed better. Parameters  and  are user
dependent (as confirmed in the experiment in [5]). We do not define
Impact(i) in this paper, but refer readers to [5] for details: it
involves quadratic ratings and normalization as found in the
experiment discussed above.
The satisfaction function given does not take the satisfaction of
other users into account, which may well influence a user’s
satisfaction. As argued in [5] (based on social psychology), two main
processes can take place. Firstly, the satisfaction of other users
nearby can lead to so-called emotional contagion: other users being
satisfied may increase a user’s satisfaction (e.g. if somebody smiles
at you, you may automatically smile back and feel better as a result).
An experiment in [5] shows that this emotional contagion depends on
the relationship you have: you are more likely to be contaged by
somebody you love or respect (like your child or boss) then by
somebody you do not know.
Secondly, the opinion of other users nearby may influence your own
expressed opinion, based on the so-called process of conformity. Two
types of conformity exist: (1) normative influence, in which you want
to be part of the group and express an opinion like the rest of the
group even though you still believe differently, and (2) informational
influence, in which your own opinion changes because you believe the
group must be right.
More complicated satisfaction functions are presented in [5] to model
emotional contagion and both types of conformity. However, the work
presented in this paper uses the function given above (and its
variants), postponing the incorporation of group influence to future
work.
3 AGENT-BASED AMBIENT INTELLIGENCE
Software agents [6] have been used in responsive environments
solutions (e.g., [2, 3, 7, 8, 9] and [10]). The association of
distributed threads of execution with physical components allows for
arbitrary functionalities to be used in the management of resources
and coordination of activities. These functionalities are combined
with the desirable features of software agents such as proactiveness
and social abilities (communication) [6]. For instance, a digital
camera able to take pictures can be associated with a software agent
that will manage any requests from other components for pictures, but
the agent will also store the last n pictures taken. Even though the
camera itself may not have provisions for storing more than one
picture, by associating an independent thread of execution with it, we
are able to extend its functionalities.
The same physical components can be associated with different software
agents at different times, thus allowing for hassle-free versioning.
In such case, engineers and programmers devise new versions of
software agents to replace previous ones, fixing any bugs, improving
on existing features or adding new functionalities to take advantage
of new components. The new software agents can take over from their
previous counterparts without the need to redesign the whole solution
from scratch
We propose to assign a software agent to every device and person in
the environment, following [3], to endow it with ambient intelligence.
We illustrate this approach through figure 2: the rectangular box
represents the physical environment and the “cloud” above it stands
for the digital (logical) environment. For instance, customer 1 is
represented by user agent c1 and device d1 by agent d1. Each device
has an action radius which may be determined, e.g,. by the range of
its sensors or the visibility of its display. For instance, device d2
is only reacting to two people in its action range (customers 4 and
5). Hence, c4 and c5 are the only user agents currently communicating
with d2.
F igure 2. Agent-Based Responsive Environments
The environment is dynamic: both devices and humans may enter, move
around, and leave at any moment. So, their corresponding agents need
to be created, updated and terminated automatically. Additionally, the
connections between the agents cannot be static, since with whom the
agents need to communicate can change continuously.
To allow for ad-hoc communication among various parties, we follow [2,
3] and use a blackboard architecture, implemented using JavaSpaces4
[11]. So, agents do not communicate directly, but constantly monitor
and post messages on the tuple space. Similarly, physical entities
communicate with the tuple space rather than directly with their
corresponding agents. Administrator agents manage the ‘digital cloud’,
continuously monitoring the tuple space and creating, updating and
terminating agents to reflect what happens in the physical world.
4 INTEGRATING GROUP ADAPTATION
To integrate group adaptation into the architecture, we made the
device agents into aggregator agents: they decide what the device
should do (e.g. which music to play) depending on the opinions of the
user agents within their action radius.
The goal of a user agent (c1 etc in Figure 2) is to increase the
satisfaction of its physical counterpart by influencing the items that
are played on the shared device5. It does so by viewing what is being
displayed at a given time, updating its satisfaction and notifying the
display’s aggregator agent. To update satisfaction, the formula
described in Section 2 is used (and its variants), with predetermined
values for its parameters6.
The goal of an aggregator agent (d1 etc in Figure 2) is to control the
shared device and keep the users within its action radius as satisfied
as possible. It does so by continually asking each user agent within
its action radius for its satisfaction in relation to the items
displayed so far, and its profile (which provides ratings for the
possible items to display next).
The strategies described in [4] (like the Average Strategy and the
Least Misery strategy) did not use information about the group
members’ satisfaction so far. Receiving this information from the user
agents allows our aggregator agents to use more sophisticated
strategies. It seems sensible for the aggregator agents to try to
increase the satisfaction of the least satisfied user within their
action radius, whilst trying still to take into account the opinions
of all other group members.
Aitken [8] proposed that the aggregator agents determine (1) an
aggregated profile (for the possible items to display next), using one
of the standard algorithms described in [5], and (2) the least
satisfied member so far. The aggregator agents then select the item
with the highest (individual) rating for the least satisfied member.
If multiple items with such highest rating exist -let us call these
candidates- the aggregated profile is used, selecting the candidate
that has the highest rating in the aggregated profile. For instance,
in the example in Table 1, suppose John is the least satisfied member
so far. Based on this, items A, E, and I are candidates to display
next, as they have the highest rating for John. If the Average
Strategy were used to determine the aggregated profile, item E would
be displayed, as E has the highest average rating of the candidates
for the group as a whole.
This approach has some limitations. For instance, in the example of
Table 1, suppose that Mary was the least satisfied member so far.
Aitken’s approach would result in item A being displayed next. Whilst
this clearly would make Mary more satisfied, it would have a bad
effect on Adam’s satisfaction. Displaying item E may well be a better
option, as it has almost the same rating for Mary whilst being
significantly better for Adam. This could be incorporated into the
approach by making higher level groupings of ratings, e.g. treating 9
and 10 as “highly satisfying”. Another modification needed is to base
the aggregated profile used on the group without its least miserable
member.
An alternative to Aitken’s approach would be to attach weights to
users, in a manner similar to that described in [12]. Weights would
depend on the user’s satisfaction, with satisfied users having a lower
weight than dissatisfied ones. Using weights works well with some
aggregation strategies (like the Average Strategy and Multiplicative
Strategy), but is impossible to do with others (like the Least Misery
Strategy). The advantage of the improved Aitken’s approach is that it
works for all aggregation strategies, allowing the designer of a
responsive environment to experiment with different options. Such
experimentation is important, as whilst results from [4, 5] show an
advantage of using the Multiplicative Strategy, the best strategy to
use may well be domain dependent.
Another alternative would be to use the aggregation strategies
discussed in [4], but apply them only to all members of the group that
are currently unsatisfied. More research will be needed to decide on
the best way to use the users’ satisfaction so-far, and to compare it
with the use of the strategies discussed in [4].
5 IMPLEMENTATION
The ideas presented in this paper have been successfully implemented
as a proof-of-concept prototype: a PC with an of-the-shelf BluetoothTM
USB adaptor (our sensor) detected BluetoothTM-enabled mobile phones
within its range and delivered music and/or video clips via the PC.
The owners of mobile phones had to previously register their profile
with preferred genres and artists/groups, and any dislikes, this
information being stored in a database to which software agents
representing the humans had access. This implementation has been
reported in [8]: we used JADE7 to start up and manage our agents as
lightweight threads, communicating via JavaSpaces [11], defining a
computational environment [13] using freely available technologies.
We chose to use BluetoothTM to detect users entering or leaving the
environment, as it is a widely accepted open standard that is already
integrated into many devices (like mobile phones). Infrared is only
useful in line-of-sight, so was judged impractical for our purposes,
as users would have to scan when entering or leaving the environment.
We did not use RFID tags as these were not readily available, but we
do not anticipate any significant problems if we were to use them
instead of Bluetooth-enabled devices.
F or evaluation purposes, we wanted to see graphs of the users’
predicted moods. We implemented a graph writing component using Java2D8.
We show in figure 3 a screenshot with a mood graph for one user in the
environment. Hovering over the mood graph shows the details of the
item being played at that time (the screen shot shows that a Star
War’s MPEG file has been played as the first item). In this example,
the Average Strategy has been used, and satisfaction has been modelled
with a delta value of 0.5 and an epsilon of 0.5. A history of graphs
is kept, allowing the designer to compare algorithms easily.
Figure 3. Screenshot of Mood Graph
For the shared device, we implemented a media player using the Java
Media Framework9. This allowed us to control the device directly
through the JavaSpaces (which would be impossible if using an existing
media player such as Windows Media Player10).
To ensure a degree of robustness, each agent has a backup. The main
agents keep a dialogue with their backups, notifying them that they
are still alive. If the main agent does not respond, then the backup
spawns a new main agent, thus allowing the application to stay active.
The software has been extensively tested to ensure it can deal with a
reasonable number of users (10-50 seems appropriate for the kind of
scenarios we are interested in) and keeps working when individual
processes fail (so, the backup system works). While the implementation
provides a proof-of-concept, its goal is, in fact, far more ambitious.
It provides an important tool for further research into this area. The
software has been kept as generic as possible and facilities have been
provided to tailor it: it is easy to modify the group modelling (e.g.
add other aggregation algorithms, modify the satisfaction function,
change parameters), and model other responsive environments.
6 RELATED WORK
The Intelligent Inhabited Environments research group [10] at the
University of Essex explicitly proposes, as we do, the construction of
intelligent responsive environments through the coupling of the
physical world and virtual worlds inhabited by software agents.
However, their test bed, the iDorm experiment, which is a student
dormitory facility to serve a single student, equipped with a host of
sensors and effectors that can monitor the activities in it and
respond accordingly, only allows for single-occupant scenarios.
In [2, 3] a negotiation protocol is proposed to allow user ag-ents
suggest settings for a shared device. The protocol is one-off in that
it does not keep track of previous results. User agents communicate
their best choices to the agent managing the shared device; these
preferences define a space of possible config-urations from which one
final configuration must be drawn. Each of the preferences is also
associated with the “power” of influence of that user agent: depending
on how high this power is, the final configuration will be closer to
that agent’s choice. This is a primitive kind of group adaptation, in
which the power of influence remains static.
Group rating naturally connects with the area of Collaborative
Filtering [14], in which systems are built to predict a person’s
affinity for items or information by connecting that person’s recorded
profile with the profiles of a group of people and sharing ratings
between similar persons. Location aware collaborative filtering and
the filtering of interests of a group instead of a single person –
which are specific proposals and contributions of our work – are two
recent research topics not yet explored.
In [15], a system called MusicFX is described which is used in a
company’s fitness centre to select background music to suit a group of
people working out at any given time. MusicFX selects radio stations,
rather than individual songs (so, is less concerned with a sequence of
items). It uses a version of the Average without Misery strategy (see
[3]). It does not try to model user satisfaction.
A relevant project, with similar goals and methodology to ours, is
found in [16]. In this work, the authors propose the application of
rating techniques based on Social Choice Theory to determine the
contents of public displays. It is even argued, in agreement with our
approach, that a distributed architecture is appropriate to leverage
system performance. Our contribution with respect to that work lies in
the explicit use of multi-agent technologies, which enables a more
descriptive and yet concise presentation of our architecture.
7 CONCLUSIONS & FUTURE WORK
This paper shows how existing work on agent architectures for ambient
intelligence can be combined with work on group adaptation to obtain
responsive environments that take the affective state (satisfaction)
of their users into account. A proof-of-concept implementation was
presented, which has been functionally tested and which will provide a
test bed for further research into this area. We intend to perform a
range of experiments to see how well the aggregator agents function
and to explore the advantages and disadvantages of several approaches
for incorporating user satisfaction into the decision making.
In the architecture and implementation presented so far, the
satisfaction of a user only depends on the items displayed, not
directly on the other users in the environment. So, it does not yet
allow for contagion and conformity. We would like to extend this work
to incorporate this. This would mean that user agents should be
communicating with the agents of users nearby to express their
satisfaction. The importance of modelling contagion and conformity
will depend on the application domain. For example, when adapting
music, contagion and conformity are likely to be higher in certain
environments (like a pub) than in other environments (like a
bookshop), as users are more aware of each other (looking at each
other rather than at the books) and are more likely to know each other
(as mentioned the relationship type influences contagion). To reduce
communication, it may well be sufficient for agents to communicate
their satisfaction only to agents representing users that their users
have a good relationship with. So, for instance, the agents
representing a mother and her child would exchange information, but
the agents of two strangers not.
We have considered in our studies and experiments rather sophisticated
rating strategies, derived from Social Choice Theory. The items
considered to be rated, however, have been a little simplistic in our
experiments so far. Considering for example the train station scenario
devised in the beginning of this article, we can have a group of
heterogeneous agents with diverse interests competing for the display.
These different interests may not be comparable (e.g. the interest in
learning about available products in nearby shops and the need to
obtain information about train departures), and in this case more
sophisticated decision procedures must be implemented in the
aggregator agent, probably resorting to multi-attribute decision
procedures. We have thus far also employed simplifying assumptions
about the behaviour of the users, as well as of our designed
aggregating agents. One of our major simplifying assumptions is that
the goals of the users are unique and stable, and we extend this
assumption to the aggregating agent. More refined implementations
shall be considered in the future, in which we take into account that
users can change their minds and interests dynamically and yet
predictably, and in which we refine the behaviour of the aggregating
agents so that they can change their goals and strategies depending on
the group of agents that is sensed to be in the vicinity of a display.
REFERENCES
[1] A. Gaggioli. Optimal Experience in Ambient Intelligence. In:
Ambient Intelligence. G. Riva, F. Vatalaro, F. Davide, M. Alcañiz
(Eds.). IOS Press (2005).
[2] F. S. Correa da Silva and W. W. Vasconcelos. Managing Responsive
Environments with Software Agents. Journal of Appl. AI (in press).
[3] F. S. Correa da Silva and W. W. Vasconcelos. Agent-Based
Manage-ment of Responsive Environments. Procs. 9th AI*IA, Milan,
Italy. LNAI Vol. 3673, Springer-Verlag, Berlin, Germany (2005).
[4] J. Masthoff. Group Modeling: Selecting a Sequence of Television
Items to Suit a Group of Viewers. UMUAI, 14:37-85 (2004).
[5] J. Masthoff and A. Gatt. In Pursuit of Satisfaction and the
Prevention of Embarrassment: Affective State in Group Recommender
Systems. UMUAI, 16:281-319 (2006).
[6] M. Wooldridge, An Introduction to Multi-Agent Systems, John Wiley
& Sons Ltd., England, U.K., (2002).
[7] Jan M.V. Misker, Cor J. Veenman, and Leon J.M. Rothkrantz, Groups
of Collaborating Users and Agents in Ambient Intelligent Environments.
In: Procs. 3rd Int’l Joint Conf. on Autonomous Agents & Multi-Agent
Systems (AAMAS’04), NY, USA. ACM Press. (2004)
[8] C. Aitken. Designing Software Agents to Manage Responsive
Envir-onments. B.Sc. Hons. Report. Dept. of Computing Science,
University of Aberdeen, UK, http://www.csd.abdn.ac.uk/
~wvasconc/aitken_chris.pdf. (2006).
[9] G. Vizzari, Dynamic Interaction Spaces and Situated Multi-Agent
Systems: from a Multi-Layered Model to a Distributed Architecture,
Ph.D. Dissertation, Universita degli Studi di Milano-Bicocca, Milan,
Italy. (2004)
[10] H. Hagras, V. Callaghan, M. Colley, G. Clarke, A. Pounds-Cornish,
and H. Duman. Creating an Ambient Intelligence Environment Using
Embedded Agents. IEEE Intelligent Systems, 19:12-20, (2004).
[11] E. Freeman, S. Hupfer, and K. Arnold. JavaSpaces: Principles,
Patterns and Practice. Addison-Wesley, USA. (1999)
[12] J. Masthoff. Selecting News to Suit a Group of Criteria: An
Exploration. In: Procs. 4th Workshop on Personalization in Future TV -
Methods, Technologies, Applications for Personalized TV, Eindhoven,
Netherlands. Springer (2005).
[13] D. Weyns, M. Schumacher, A. Ricci, M. Viroli, and T. Holvoet.
Environments in Multi-Agent Systems. The Knowledge Engineering Review,
20:127-141 (2005).
[14] J. L. Herlocker, J. A. Konstan and J.Riedl, Explaining
Collaborative Filtering Recommendations. Procs. ACM Conf. on CSCW.
Pennsylvania, USA (2000).
[15] J. McCarthy and T. Anagnost. MusicFX: An Arbiter of Group
Preferences for Computer Supported Collaborative Workouts. In: Procs.
ACM Conf. on CSCW, Seattle, USA, pp. 363-372 (1998).
[16] S. Pizzutilo, B. De Carolis, G. Cozzolongo, F. Ambruoso. Group
Modeling in a Public Space: Methods, Techniques and Experiences. In:
Procs. of WSEAS AIC 05, Malta, Sept. 2005. pp. 175-180 (2005).
1 Dept. of Computing Science, Univ. of Aberdeen, AB24 3UE, UK. Email:
{name1, name2}@csd.abdn.ac.uk.
2 Dept. of Computer Science, Univ. of Another, AB24 3UE, UK. Email: {name1,
name2}@cs.ac.uk.
3This was done in another (educational) domain. See [5] for a
discussion on why this was necessary.
4JavaSpaces is part of Sun’s JINI Network Technology, available at
http://www.sun.com/software/jini/
5In our case, no cheating takes place. User agents honestly report
their mood, rather than e.g. always claiming to be very miserable in
order to get a better next item.
6Both the variant to use and the parameter values are specified in
configuration files.
7 Java Agent DEvelopment Framework, available at http://jade.
tilab.com. Although JADE has its own communication facilities, we did
not make use of them. Instead, we used JADE to facilitate the
management and debugging of our agents. By using JavaSpaces, we confer
openness on our solution, as any Java-enabled device can communicate
with other components by posting and retrieving entries from the
space.
8 http://java.sun.com/products/java-media/2D
9 http://java.sun.com/products/java-media/jmf
10 http://www.microsoft.com/windows/windowsmedia