useful when we do not want to burden the cognitive
workload of the users in the process of formulating
their information needs. Thus the “one-size fits all”
information delivery approach available on medical
portals should be changed.
The user model should evolve dynamically in
order to avoid what we have defined as the “lock-
out” problem. Since users seem sceptical towards
letting computer systems infer their profile, it is
preferable to let users create their own profile
explicitly.
- Implement different search interfaces: our
research has shown that menu-based and NL-based
interfaces fit different types of information needs
and allow different levels of specificity. Users
should be able to choose between both types of
interface.
- Adapt the description of retrieved documents:
as stated in section 5.1, users may sort out relevant
documents only because the headings do not
explicitly name the topics they ask information
about. Thus it is important to generate descriptions
in real time that explicitly link the content of the
documents to users’ information needs.
- Allow users to submit questions in their own
language: formulating information needs in NL is
not an easy task, especially when it comes to foreign
languages. In order to reduce misunderstandings and
fully exploit the nuances of NL, it is preferable to
implement search interfaces that support
multilingual input, so that users can submit
questions in their own language.
- Implement the “ask human experts”
functionality and allow anonymous information
access: our interview has revealed some differences
concerning what the two user groups prioritize on a
medical portal. Two of the biggest differences
concerned the possibility to submit questions to
human experts and to access portal information
anonymously. If the portal is aimed at helping
people with medical problems, then these
functionalities should be available.
REFERENCES
Bader, J.L., & Theofanos, M.F., 2003. Searching for
Cancer Information on the Internet: Analyzing Natural
Language Queries. Journal of Medical Internet
Research, 5, Article e31. Retrieved September 2005
from http://www.jmir.org/2003/4/e31.
Bental, D., et al., 2000. Adapting Web-based information
to the needs of patients with cancer. In AH’00, 1st
International Conference on Adaptive Hypermedia.
Springer-Verlag.
Boyle, C., & Encarnacion, A., 1994. Metadoc: an adaptive
hypertext reading system. User Modeling and User-
Adapted Interaction, 4, 1-19.
Brajnik, G., Mizzarro, S., & Tasso, C., 1996. Evaluating
user interfaces to IR systems. In SIGIR’96, 19
th
Conference on Research and Development in
Information Retrieval. ACM press.
Chin, N., 2001. Empirical evaluation of User Models and
User-Adapted Systems. User Modeling and User-
Adapted Interaction, 11, 181-194.
Eysenbach, G., Sa, E.R., & Diepgen, T.L., 1999. Shopping
around the Internet today and tomorrow towards the
millenium of cybermedicine [Electronic Version].
BMJ, 319, 1-5.
Eysenbach, G., & Köhler, C., 2002. How do consumers
search for an appraise health information on WWW?
Qualitative study using focus groups, usability tests
and in-depth interviews [Electronic Version]. BMJ,
324, 573-577.
Grasso, F., Cawsey, A., & Jones, R., 2000. Dialectical
argumentation to solve conflicts in advice giving: a
case study in the promotion of healthy nutrition
[Electronic Version]. Int. J. of Human Computer
Studies, 53, 1077-1115.
Kass, R., & Finin, T., 1998. Modeling the user in natural
language. Computational Linguistics, 14, 5-22.
Kobsa, A., Koenemann, J., & Pohl, W., 2001.
Personalized hypermedia presentations techniques for
improving online customer relationships [Electronic
Version]. The Knowledge Engineering Review, 16,
111-155.
Lennox A., et al., 2001. Cost effectiveness of computer
tailored and non-tailored smoking cessation letters in
general practice: randomised trial [Electronic
Version]. BMJ, 322, 1-7.
Long, D., & Bourg, T., 1996. Thinking aloud: telling a
story about a story. Discourse Processes, 21, 329-339.
Lyons, C., Krasnowski, J., Greenstein, A., Maloney, D., &
Tatarczuk, J., 1982. Interactive Computerized Patient
Education. Heart and Lung, 11, 340-341.
Micarelli, A., & Sciarrone, F., 2004. Anatomy and
Empirical evaluation of an adaptive Web-based IF
system. User Modeling and User-Adapted Interaction,
14, 159-200.
Moon, J., & Burstein, F., 2005. Intelligent Portals for
supporting Medical Information needs. In Web
portals: the New Gateways to Internet Information
and Services, pp. 270-289. Idea Publishers.
Nielsen, J., 1993. Usability Engineering. Academic Press.
Norman, D.A., 1999. Affordances, Conventions and
Design. Issue of Interactions, 6, 38-43.
Salton, G., & McGill, M., 1983. Introduction to modern
Information Retrieval. McGraw-Hill.
Santos, E., Nguyen, H., Zhao, Q., & Pukinskis, E., 2003.
Empirical evaluation of adaptive UM in a medical IR
application. In UM’03, 9
th
Int. Conference on User
Modeling. Springer-Verlag.
Sneiders, E., 2002. Automated Question Answering:
Template-Based Approach. PhD thesis, Royal Institute
of Technology, Sweden.
ICEIS 2006 - HUMAN-COMPUTER INTERACTION
102