Information Technology Reference
In-Depth Information
consideration of interaction modes and platforms used means, for us, that the
personalization system must integrate them into its reasoning in relation to the
preferences of the user. The personalization system must be able to know or deduce,
for example, that for a given piece of information the user would prefer to listen to it
from his cell phone, rather than read it on his PDA.
This notion of personalization is inscribed in the continuity of current research,
which has been very active in man-machine interactions since the beginning of the
1980s, and targets new, increasingly adaptive and intelligent interactions [HOO 00],
[KOL 98], [MOU 09], [KOL 92] (see also the
User Modeling and User-Adapted
Interaction
journal). Initially, through its approach centered around adaptation to the
user, personalization in human-computer interaction (HCI) can also be seen as very
complementary to current research on plasticity, which currently most often puts
emphasis on adaptation to the platform and the interaction environment [CAL 03],
[CAL 07], [KOL 04,] (see also Chapter 11 in this topic).
This chapter is based on different documents, including [ANL 05a], [ANL 05b],
[ANL 05c], [ANL 06b], [ANL 07], [GRI 07,], and especially [ANL 06a] (a PhD
thesis co-financed by Archimed in Lille and the Nord-Pas-de-Calais region of
France). It begins with a non-exhaustive review of personalization systems at the
origin of the proposal, which is the focus of this chapter. Then, an approach called
PERsonalization METhodology
(PerMet) for the development of personalized ISs,
as well as a personalization system called
PERsonalization SYSTem
(PerSyst),
which differs from the others in its distributed and evolving aspect, will be
presented. Giving the main points, we then describe an application developed for the
validation of our approach in the domain of transport; it is meant for itinerary
planning based on the personal calendar of the user. A discussion and a conclusion
will end this chapter.
3.2. Personalization in HCI: examples of existing approaches, at the origin of
the approach proposed
Several systems are contributing to progress in the domain of personalization in
human-machine interactions. These systems are, for the most part, destined to aid
navigation on the Web (for example, Web browsers). They ensure the observation
of user behavior, and the research, filtering and presentation of this information.
Arising from the works of Lieberman [LIE 01], Letizia saves the URLs chosen
by the user, reads the pages and draws up a profile of the user as he visits pages;
based on this, it searches for other pages that are likely to interest the user and
presents its results in an independent window.
