Call for Papers UM2001 8th International Conference on User Modeling Workshop on User Modeling, Machine Learning and Information Retrieval (http://www.scms.rgu.ac.uk/um2001-ws) UM2001 Dates: July 13- 17, 2001 - Sonthofen, Germany (http://www.dfki.de/um2001) Overview -------- The rapid evolution of Internet services has led to a constantly increasing number of Web sites, and to an increase in the available information. Thus, the main challenge is to support Web users in order to facilitate navigation through Web sites and to improve searching among the extremely large Web repository. Usually, users have to decide themselves which sequence of actions must be performed to solve a given task. Complex search queries, for example, must be constructed step by step. The complexity of today's services could be lowered by means of a "pro-active" support or advice from the system. To meet these conditions the interaction must convey precise and relevant information, and address the personal background of the individual user. Web search engines use the typical information retrieval paradigm of a few words to represent the user need, and then match against very large numbers of documents, in particular, web pages. The results are often very mixed. This is partially because of the very poor user model. Two people may have very different needs but use the same two word query. The system 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. Thus we have two important questions: how can we acquire a good user model, and how can we exploit that model? Machine Learning techniques, that extract permanent features of a given user from the dialogue, represent a very promising solution: i) they have been successful in cases where large data sets were available by providing tools for retrieval and filtering of useful information; ii) they have been applied to the definition of models of users interacting with an information system. Information retrieval techniques then need to be augmented to exploit the more sophisticated model. This can be done by constructing an answer out of a set of targeted information retrieval (IR) queries, or by more sophisticated use of IR and database approaches. Topics ------ 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. 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 using ML for user modeling; * possibilities of user modeling approaches in IR; * possible applications of ML for IR using user modeling. Papers tackling theoretical issues but grounded with reference to practical applications of machine learning in user modeling for information retrieval are encouraged. Novel relevant applications as well as state-of-the-art critical reviews, which will stimulate interdisciplinary discussion, are also welcome. There are several themes and topics that we would like to explore: * moving user models beyond queries in IR; * modeling the user vs. modeling the intermediary for IR; * matching algorithms when user models are more sophisticated; * exploring information delivery models when user models are more sophisticated (using both better matching and adaptive delivery); * acquisition of user models appropriate to an information environment; * ML solutions to support to the navigation of Web sites; * ML solutions for intelligent information retrieval, especially in large repositories, e.g. Digital Libraries; * ML for extraction and management of user profiles; * ML for building user communities based on common interests, and background; * intelligent agents in charge of managing the interaction; * user interaction in intelligent IR; * evaluation of user-adaptive IR systems; * intelligent user interfaces in IR; * personalization of Web sites; * personalization for Web users; Submission ---------- Authors are required to submit papers not exceeding 10 A4 pages preferably as a PDF file (if not then a PS file). Submissions should be made by ftp to the following site and directory: ftp ftp.scms.rgu.ac.uk username: anonymous password: cd pub/incoming/um2001-ws put Please use short filenames which reflect the title of the paper. Authors are also requested to send an email to Ayse Goker (asga@scms.rgu.ac.uk) 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, (asga@scms.rgu.ac.uk) or Fabio Abbattista, (fabio@di.uniba.it) Important Dates --------------- March 8, 2001 - Submission deadline for Workshop papers April 1, 2001 - Notification of Workshop authors April 10, 2001 - Early Registration Deadline for the conference July 13 - 17, 2001 - Main conference dates Organizers ---------- Ayse Goker, Robert Gordon University, Scotland, UK (asga@scms.rgu.ac.uk) Fabio Abbattista, Universitý di Bari, Italy (fabio@di.uniba.it) Ross Wilkinson, CSIRO, Australia (Ross.Wilkinson@CMIS.CSIRO.AU) Giovanni Semeraro, Universitý di Bari, Italy (semeraro@di.uniba.it)