∞ Lifelong User Modelling
Workshop held in conjunction with UMAP
User Modeling, Adaptation and Personalisation.
June 22-26, 2009, Trento, Italy.
Online Proceedings
∞ Programme
9.00 - 10.00 — Session 1 presentations
9.00-09.15 — Using Written and Behavioural Data to Detect Evidence of Continuous Learning ,
Chad Lane, Mark Core, Dave Gomboc, Mike Birch, John Hart, and Milton Rosenberg, University of Southern California and US Army Research, Development, and Engineering Command Simulation and Training Technology Center
9.15-09.30 — Applications first, modeling later: Achieving widespread adoption of longitudinal user modeling today using life-tracking sites on the Web ,
Max Van Kleek and David R. Karger, MIT CSAIL, m.c. schraefel, University of Southampton.
9.30-09.45 — A (multi'domain'sional) Scrutable User Modelling Infrastructure for Enriching Lifelong User Modelling ,
Demetris Kyriacou, Hugh C Davis, and Thanassis Tiropanis, University of Southampton.
9.45-10.00 — Lifelong User Modelling Goals, Issues and Challenges ,
Judy Kay and Bob Kummerfeld, University of Sydney.
10.00 - 10.30 — Session 1 discussion
10.30 - 11.00 — Coffee break
11.00 -- 12.15 — Session 2 presentations
11.00 - 11.15 — Building, Exploiting, and Sharing Personal Digital Memories in SPECTER and SharedLife , Alexander Kroner, German Research Center for Artificial Intelligence.
11.15 - 11.30 — An Architecture for Life-long User Modelling , Desmond Elliot, Frank Hopfgartner, Teerapong Leelanupab, Yashar Moshfeghi and Joemon M Jose, University of Glasgow.
11.30 - 11.45 — Using Psychometric Approaches in the Modeling of Abstract Cognitive Skills for Personalisation , Victoria Macarthur & Owen Conlan, Trinity College Dublin.
11.45 - 12.00 — Personal Lifelong User Model Clouds , Peter Dolog, Aahlborg University, Judy Kay and Bob Kummerfeld, University of Sydney.
12.00 - 11.15 — A Preference Evolution Perspective on Lifelong User Modeling , Anthony Jameson and Silvia Gabrielli, Fondazione Bruno Kessler, Trento.
12.15 - 1.00 — Session 2 discussions:
1.00 - 2.30 — Lunch
We will continue the discussion at a local restaurant.
2.30 - 4.30 — Discussion - Identifying Research Directions for Lifelong User Modelling
We are clearly at the start of serious explorations of the research that will need to be done to identify the nature of lifelong user modelling and the mechanisms for supporting it. This session will involve small group discussions, based around key themes listed in the questions to the right as objectives of the workshop, with the list being refined on the basis of themes that have emerged from the morning presentations and associated discussion. Each group will tackle one of these. Each group will aim to identify the key research directions needed to address their question. Then all groups will share their conclusions.
4.30 - 5.00 — Coffee break
5.00 - 6.00 — Summary and future planning User Modelling
This session will be in a discussion format. Together, the participants will formulate a summary of the current state of support for lifelong user modelling and identifying most important questions to address. We will also discuss the future pragmatic plans for this group.
Call for papers
It is now timely to explore the challenges and opportunities of building life-long user models. These will capture salient aspects about the user over very long periods of time, from early childhood into old age. Life-long models will be critical if we are to realise the potential of personalisation that operates over the long term, as well as short-term personalisation that can be improved by long term data about the user. One of these benefits is a new form of augmented cognition. Another important class of personalisation will be in the context of improved life-long teaching and learning. This should take account of many elements that might be valuable as parts of a long term learner model. Notable among these is the learner's previous knowledge and its evolution, context-sensitive modelling of the user's response to learning activities and the learner's long term goals. To take just one other example, there is huge potential for radical improvements in the support for personal information management, with a long term user model enabling software tools to be far more effective than is currently possible with existing models in serving the different needs of each individual.

While there is a considerable body of research into techniques for many aspects of user modelling, we now need to tackle the new challenges that need to be addressed for life-long user modelling. At a technical level, these include representational aspects which can take account of the effects of time, such as forgetting. Ontological issues will be fundamental since the life-long user model needs to be able to operate in relation to many different applications. On a very different level, there are critical challenges associated with privacy and user control which involve a combination of technical, social, user interface and other issues.

All submissions will be reviewed by at least 3 members of the workshop committee. Authors of accepted submissions will be asked to present both a presentation and a poster. Proceedings will be available in print and on-line.
Classes of submission:
• New research: This is work that has not been previously published. It should present new ideas and work to contribute to the workshop. These contributions will be reviewed and will be included in full in the workshop proceedings. Key criteria for acceptance will be the importance and novelty of the ideas for addressing the challenges of lifelong user modelling.
• Previous work: This is previously published work that is relevant to the workshop. It should be accompanied by an abstract which overviews the work and its relevance to this workshop. Only the abstract will appear in the proceedings.
Submission instructions
Full papers should be 4-8 pages. The submissions must use Springer LNCS style. Papers should be submitted via email to llum@it.usyd.edu.au
Judy Kay and Bob Kummerfeld, University of Sydney, Australia (chairs)
Susan Bull, University of Birmingham, UK.
Peter Dolog, Aalborg University, Denmark.
Eric Horvitz, Microsoft Research, USA.
Anthony Jameson, DFKI, Germany.
H Chad Lane, USC/Institute for Creative Technologies, USA.
Gord McCalla, University of Saskatchewan, Canada.
Valerie Shute, Florida State University, USA.
The workshop will focus on the following key questions:
• What are the particular representational requirements for life-long user modelling?
• What are the requirements for enabling a life-long user model to be useful for a range of applications?
• How will research in ontologies and the semantic web support life-long user modelling?
• Which aspects need to be part of the foundation design of technical solutions that will ensure the user's privacy over their life-long user model?
• How will we ensure users can control and share their life-long user model effectively?
• Do we need interfaces to user models? And to the personalisation processes? And if so, what are the particular new requirements on these?
• What are the relevant existing standards that should be part of life-long user modelling and where is there a need for additional standards?