topical media & game development
Rate, Recommend, Regret -- an Expert-based Approach to the Personalization of Guided Tours
Anton Eliëns, Yiwen Wang
resource(s)
abstract
In this paper we propose an approach to generate personalized
guided tours based on a finite collection of tours obtained
by tracking the navigation of expert users.
Our proposal is based on a variant of decision theory,
that uses a regret function to measure the difference between
a proposed decision and a finite collection of expert decisions,
generalized to a finite sequence of discrete choices.
Personalization may then be seen as a minimization
problem over a weighting scheme, expressing the relative importance
of experts of which tours are available.
We illustrate our approach by showing how we may obtain
guided tours in 3D digital dossiers containing information
on contemporary art installations,
and discuss how our approach may be applied in other
cultural heritage applications.
keywords:
decision theory, personalization,
guided tours, digital dossier, cultural heritage
Introduction
Leaving all responsibility for interaction to the user
is usually not a good choice, in particular when an information system contains
complex, highly interrelated information.
In
[Eliens et al. (2006b)], we describe the
3D digital dossier format,
in which we presented the information of respectively the Dutch-Serbian artist
Marina Abramovic and the Australian
artist
Jeffrey Shaw,
contemporary artists with a variety of work, ranging from video to art installations.
The
digital dossier supports navigation using a concept graph and allows
for presenting media-rich material, including 3D models of artwork installations.
The digital dossiers have been implemented using X3D/
VRML
to allow for deployment on the web.
Recently we have explored guided tours in digital dossiers, [van Riel et al. (2006)],
which actually automate user interaction, by mimicking user actions through events generated
by a script.
Although this provides an easy way to create guided tours, this does not solve the problem
of what to select as elements in the guided tour, or how to personalize
these tours in an intelligent manner.
In this short paper, we discuss techniques from decision theory
as a means to aid the construction of guided tours by consulting an advice
function based on tracking the navigation behavior of expert users.
We will also indicate how a similar advice function can be used for
personalizing tours in cooperation with a recommender system for artwork,
by altering the weight given to particular properties.
structure
The structure of this paper is as follows.
In section 2 we will give a brief introduction to decision theory,
and in section 3 we will discuss how techniques from decision theory can be
applied to the construction of guided tours in digital dossiers.
In section 4, we will illustrate how to apply decision theory for the personalization of
tours in a more conventional cultural heritage application and in section 5 we
give our conclusions and indicate directions for future research.
Mathematical preliminaries -- decision theory
In this section we will give a very brief introduction
to decision theory, more in particular a variant of
decsion theory introduced in [Cesa-Bianchi and Lugosi (2006)], that
provides a mathematical foundation for our approach.
In classical prediction theory a prediction is a sequence
of elements that results from a stationary stochastic
process.
The risk of the prediction is taken to be the expected value
of the accumulated loss function, measuring the
discrepancey between predicted values and actual
outcomes.
[Cesa-Bianchi and Lugosi (2006)] introduce a variant of prediction theory in which
no assumption is made with respect to the nature of the
source of predictions.
Instead, the forecaster is considered to
be an entity that gives a prediction for an element
based on advice of one or more experts.
These experts might be actual sequences stored in a database.
The deviation of the forecaster with the actual
outcome is measured using a regret function,
and the prediction task may hence be formulated as
minimimizing the regret function by choosing the
best expert for advice for each element of a prediction sequence.
For example, for the prediction of a bitstring of length n,
the forecaster is a vector of n expert indices,
that give advice for the bitvalue, 0 or 1, in that position.
In the general case, in which we have no information
on the error rate of the experts' advice,
we may use a weighting factor $0 <= %b_{i} <= 1
