MLIRUM'03: The Second Workshop on Machine Learning,
       Information Retrieval and User Modeling

at the Ninth International Conference on User Modeling
    June 22-26, Pittsburh, PA, USA



At UM97, a first workshop on "Machine Learning for User Modeling"
(ML4UM) took place, and a special interest group was initiated.  The
second ML4UM workshop was held at the UM99 and the Third at the
UM2001.  The ML4UM SIG now has both a web site and a mailing list.  At
UM2001, the first workshop on "Machine Learning, Information Retrieval
and User Modeling" (ML,IR, and UM) took place.  We have merged these
two workshops and SIGs, as they have such related topics.


User model acquisition is a difficult problem. In Machine Learning,
the information available to a user modeling system is usually
limited, and it is hard to infer assumptions about the user that are
strong enough to justify non-trivial conclusions. Classical
acquisition methods like user interviews, application-specific
heuristics, and stereotypical inferences often are inflexible and
unsatisfying. In Information Retrieval, user models have been limited
to lists of terms relevant to an information need. The list is usually
very short for ad hoc querying and longer for information filtering

Information systems that could benefit from having a user model should
be able to adapt to individual users, to learn about their preferences
and attitudes during the interaction (to construct a user profile),
and memorize them for later use. Moreover, these user profiles could
represent a starting point for the creation of user communities based
on shared interests or goals.  Further, the system should be able to
update its model is a user changes interests.

Machine Learning (ML) is concerned with the formation of models from
observations. Hence, learning algorithms seem to be promising
candidates for user model acquisition systems.

Information Retrieval (IR) is concerned with the study of systems
for representing, organising, retrieving and delivering information
based on content.

User modeling is the glue. As the better we model users, the better
we can satisfy their information needs. We also aim to provide a forum
for researchers who are not necessarily familiar with the diverse
aspects of UM/ML/IR to be able to get acquainted with the
possibilities of collaboration between the communities.  Thus, our
main goal is to build further bridges between three communities: User
Modeling, Machine Learning, and Information Retrieval.

We welcome your contributions to addressing these issues.

Our main goal is to build further bridges between three communities:
User Modeling, Machine Learning, and Information Retrieval.


The two primary questions we would like to address are:
  1. How can we apply Machine Learning and Information Retrieval
     techniques to acquire and continuously adapt user models?
     * What role can and should the user play in reviewing and
       refining their own model?
     * What are issues in modeling the user vs. modeling the
       intermediary for IR?
     * How can intelligent agents be used when in charge of
       managing the interaction with an information system?
     * How can we evaluate user-adaptive IR systems?  Is it based on
       effective retrieval, user experience, reaction and satisfaction?
     * Where/How does the user fit into the picture?  What kind of
       user feedback is helpful/needed, and how can the user query/use the
       learned model?
     * How can ML be used for building user communities based on
       common interests, and background?  How do you apply IR techniques to
     * In the case of the description of a concrete application: Why
       did you choose these particular techniques?  How did they affect the
       success of your application? What general conclusions can you draw
       from your experiences?

  2. SIG issues:
     * What has been done since the last SIG meeting?
     * How can SIG facilities be made more useful?
     * What are possibilities for cooperation between SIG members?
     * What could be activities the SIG should engage in?
     * How can we get more people involved?
     * What are the issues/problems that drive current research?
     * What are the ways we can combine these three fields such that
       changes in any field does not break the integrated system?  Are there
       any standards or good practices for integration that can be
       to address this issue at this stage?


The workshop program will be content-centered.  Papers on related
topics will be grouped together into sessions, each of which will be
presented by a participant.  Each session will have a small discussion
at the end to discuss issues related to that topic.  General research
issues will be separated from SIG issues, which will be discussed at
the end of the workshop.


Authors are required to submit papers not exceeding 10 pages as a PS
or PDF file.  Each submission is required to address at least one of
the main workshop questions.  Fulfillment of this requirement will be
assessed in the course of the review process.

Workshop papers will be published in full length in the workshop
proceedings and presented in talks at the workshop.

Submissions should be made to Ayse Goker <[log in to unmask]>.
Authors are also requested to send and email to Ayse Goker
<[log in to unmask]> containing the title of the paper,
the name of the file that has been submitted, the author name(s),  the
author affiliation(s) and contact information.

Any queries regarding submission should be sent to:  Ayse Goker,
([log in to unmask]) or Sofus A. Macskassy, ([log in to unmask])


March 1: Submission deadline for Workshop papers
March 24: Notification of Workshop authors
April 3: Early Registration Deadline for the conference
April 15: Camera ready copies due


* Sofus A. Macskassy ([log in to unmask])
  Leonard N. Stern School of Business, NYU

* Ross Wilkinson ([log in to unmask])

* Ayse Goker ([log in to unmask])
  Robert Gordon University

* Mathias Bauer ([log in to unmask])