| A Model for Adapting Explanations to the User's Likely Inferences | | BIBAK | Full-Text | 1-55 | |
| Helmut Horacek | |||
| In order to generate natural, high quality textual presentations in
technical domains, good explanations must not only be adapted to the knowledge
attributed to the intended audience, but they must also take into account the
inferential capabilities of the addressees. In this paper, we present a model
for anticipating contextually-motivated inferences addressees are likely to
draw. This model is used to motivate choices in presenting or omitting
individual pieces of information; it takes into account the addressees' domain
expertise and expectations about logical consequences of purposefully presented
information. Several kinds of empirical evidence are incorporated into a text
planning process that aims at exploiting conversational implicature, so that a
most suitable portion of the plan can be selected for being uttered explicitly.
This way, our method adds to discourse planners based on Rhetorical Structure
Theory (RST) the ability to omit easily inferable information. Thus, it
overcomes one of the main shortcomings of RST. In the course of this process,
rules anticipating user inferences are invoked to determine contextually
justified derivability of information. In this manner, text variants can be
composed on the basis of a text plan entailing annotations about the
inferability of pieces of information. Moreover, pragmatically-motivated
preference criteria can be used to choose among several plausible variants. The
model is formulated in a reasonably domain-independent way, so that the rules
expressing aspects of conversational implicature can be incorporated into
typical RST-based text planners. Keywords: explanation; inference; natural language generation; stereotype user model. | |||
| ABIS-96: GI Workshop on Adaptivity and User Modeling in Interactive Software Systems | | BIB | Full-Text | 57-62 | |
| Hans-Günter Lindner | |||
| The Trouble with Computers: Usefulness, Usability, and Productivity, Thomas K. Landauer | | BIB | Full-Text | 63-64 | |
| Michel Desmarais | |||
| A Concurrent, Distributed Architecture for Diagnostic Reasoning | | BIBAK | Full-Text | 69-105 | |
| Stefano A. Cerri; Vincenzo Loia | |||
| This paper demonstrates the feasibility of modeling concurrent diagnostic
reasoning (CDR) by means of the computational model of actors. Actors have a
value added on top of objects, because they include the properties of
abstraction, modularity and reuse of objects but allow really concurrent and
distributed architectures, in the sense that memory (the environment) is
assumed not to be shared among actors. Whether concurrency really implies
efficiency is still debated. We are more concerned here with the actor-based
design of the diagnostic reasoning model. As a testimony of the feasibility of
our proposal, a concrete, actor-based diagnostic program is presented as a
module for an Intelligent Tutoring System in the domain of school algebra. CDR
is obtained from the coordinated behaviour of actors which possess limited
local knowledge and accomplish the global goal of diagnostic reasoning by
interacting with each other. We examine how the 'traditional' approaches to
student modeling, such as overlay and bug models, can be re-visited in a
distributed perspective of computational actors and how the latter view
outperforms the previous ones. Keywords: actors; actor model; diagnostic reasoning; student modeling; concurrent
object-oriented programming; ABCL/1 programming language | |||
| Plan Recognition and Evaluation for On-line Critiquing | | BIBAK | Full-Text | 107-140 | |
| Abigail S. Gertner | |||
| The Traum-AID system is a tool for assisting physicians during the
management of patients with severe injuries. Originally, Traum-AID was
conceived as a rule-based expert system combined with a planner. After this
architecture had been implemented, we began to face the issue of how Traum-AID
could communicate its plans to physicians in order to influence their behavior
and have a positive effect on patient outcome. This paper describes Trauma-TIQ
-- the critiquing interface for Traum-AID -- which examines the actions the
physician intends to carry out and produces a critique in response to those
intentions. Trauma-TIQ's two main components are a plan recognizer that uses
the context of the case to disambiguate plans, and a plan evaluator that
identifies errors and calculates their significance in order to determine an
appropriate response. Unlike previously developed reminder systems, Trauma-TIQ
evaluates the physician's proposed plan and attempts to intervene before
problems occur. And unlike previous critiquing systems, it is able to provide
ongoing decision support during the planning and delivery of care. In the
context of time-critical patient management it is, therefore, a more
appropriate means of interaction. Keywords: critiquing; plan recognition; plan evaluation; decision-support systems;
medical informatics | |||
| The State of the Art in Text Filtering | | BIBAK | Full-Text | 141-178 | |
| Douglas W. Oard | |||
| This paper develops a conceptual framework for text filtering practice and
research, and reviews present practice in the field. Text filtering is an
information seeking process in which documents are selected from a dynamic text
stream to satisfy a relatively stable and specific information need. A model of
the information seeking process is introduced and specialized to define text
filtering. The historical development of text filtering is then reviewed and
case studies of recent work are used to highlight important design
characteristics of modern text filtering systems. User modeling techniques
drawn from information retrieval, recommender systems, machine learning and
other fields are described. The paper concludes with observations on the
present state of the art and implications for future research on text
filtering. Keywords: information filtering; text retrieval; social filtering; collaborative;
content-based; Selective Dissemination of Information; current awareness;
recommender systems | |||
| A Feature-based Approach to Recommending Selections based on Past Preferences | | BIBAK | Full-Text | 179-218 | |
| Bhavani Raskutti; Anthony Beitz; Belinda Ward | |||
| The increasing availability of a large number of interactive multi-media
information services means that users have a large and diverse collection of
choices open to them. This diversity and choice may present navigation
difficulties to users which can dissuade them from using such services. One
method of assisting users to navigate through large collections is to use
information filtering to extract only the information relevant to an end-user
according to his/her long-term preferences. In this paper, we describe a
mechanism to acquire a user's long-term preferences (user profile), and then
show how the acquired profile may be used to recommend selections that may be
of interest to the user. The profile is acquired on the basis of a user's
habits using a Heuristic-Statistical approach, and is used to create selection
indices which are then used during on-line interactions to recommend
selections. Our mechanism has been incorporated into an experimental Video On
Demand (VOD) service that is implemented using a client-server architecture.
The profile acquisition component is incorporated into a VOD server on a
multi-tasking machine, while the VOD user interface resides on a personal
computer. Our mechanism for acquiring profiles and making recommendations has
been quantitatively evaluated on the basis of data collected about movie
preferences. Keywords: information filtering; personalised recommendations; acquisition of
individual user models; interactive services | |||
| Wiederverwendung von Plä en in deduktiven Planungssystemen (Reuse of Plans in Deductive Planning Systems), Jana Köhler | | BIB | Full-Text | 219-222 | |
| Douglas E. Appelt | |||
| User Models and Filtering Agents for Improved Internet Information Retrieval | | BIBAK | Full-Text | 223-237 | |
| Sima C. Newell | |||
| Over the past few years, the amount of electronic information available
through the Internet has increased dramatically. Unfortunately, the search
tools currently available for retrieving and filtering information in this
space are not effective in balancing relevance and comprehensiveness. This
paper analyzes the results of experiments in which HTML documents are searched
with user models and software agents used as intermediaries to the search.
Simple user models are first combined with search specifications (or 'User
Needs'), to define an Enhanced User Need. Then Uniform Resource Agents are
constructed to filter information based on the EUN parameters. The results of
searches using different agents are then compared to those obtained through a
comparable simple keyword search, and it is shown that a user searching a pool
of existing agents can obtain better search results than by conducting a
traditional keyword search. This work thus demonstrates that the use of user
models and information filtering agents do improve search results and may be
used to improve Internet information retrieval. Keywords: Agent; Internet; information; user; model; retrieval; filter; Uniform
Resource Agents | |||
| Information Filtering Using User's Context on Browsing in Hypertext | | BIBAK | Full-Text | 239-256 | |
| T. Hirashima; K. Hachiya; A. Kashihara | |||
| Browsing is one of the most popular ways to gather information in database
with hypertext structure. In order to support a user to browse, modeling of the
user's interests is one of the most important issues. Although there are
several promising methods to infer the interests from the user's browsing
behavior, they assume that the interests are consistent during the browsing.
However, the user's interests are often strongly dependent on the local context
of the browsing. This paper describes a method to model the user's shifting
interests from the browsing history. An information filtering method using the
model of the interests has been implemented. We call it 'context-sensitive
filtering'. The results of an experimental evaluation, by real users' browsing
for an encyclopedia in CD-ROM format, are also reported. Keywords: Information filtering; browsing; context-sensitive; hypertext; user model;
interests | |||
| Proficiency-Adapted Information Browsing and Filtering in Hypermedia Educational Systems | | BIBAK | Full-Text | 257-277 | |
| Licia Calvi; Paul De Bra | |||
| We present a framework for proficiency-adapted information browsing and
filtering in educational hypermedia systems. In hyperdocuments, information is
acquired by browsing through highly interconnected sets of information nodes.
In order to find specific information, users follow links to nodes they judge
to be relevant. In order to help users find relevant information and new
learning material that match their levels of domain knowledge, we present a
framework for adapting the information nodes, and the links leading to them, to
the user's proficiency in the subject matter. Such a proficiency-adapted,
user-centered educational environment is intended to enhance learning. We
believe that learning in educational hypertext-based applications cannot be
reduced to traversing a static information space. Navigating through any space,
be it a physical or an information space, normally requires that users have a
prior degree of proficiency in the domain knowledge. Learning is an evolving
dynamic process through which users progress from a situation of unfamiliarity
to one of mastery of a knowledge corpus. Therefore, we propose a model of
proficiency-adapted learning and information browsing in which the presented
choices (links and the textual context of links) are selected based on the
user's knowledge state. Ultimately, such an adaptive course not only guides the
learning process of the student, but it gradually transforms itself into a
reference guide. Keywords: User-adaptivity; adaptive hypermedia systems; intelligent tutoring;
information browsing; information filtering; cognitive load; self-modifying
hyperdocuments | |||
| Feature-based and Clique-based User Models for Movie Selection: A Comparative Study | | BIBAK | Full-Text | 279-304 | |
| Joshua Alspector; Aleksander Koicz | |||
| The huge amount of information available in the currently evolving world
wide information infrastructure at any one time can easily overwhelm end-users.
One way to address the information explosion is to use an 'information
filtering agent' which can select information according to the interest and/or
need of an end-user. However, at present few information filtering agents exist
for the evolving world wide multimedia information infrastructure. In this
study, we evaluate the use of feature-based approaches to user modeling with
the purpose of creating a filtering agent for the video-on-demand application.
We evaluate several feature and clique-based models for 10 voluntary subjects
who provided ratings for the movies. Our preliminary results suggest that
feature-based selection can be a useful tool to recommend movies according to
the taste of the user and can be as effective as a movie rating expert. We
compare our feature-based approach with a clique-based approach, which has
advantages where information from other users is available. Keywords: User modeling; information filtering; collaborative filtering; feature
extraction; neural networks; linear models; regression trees; bagging; CART | |||
| Bis-97: Gi Workshop on Adaptivity and User Modeling in Interactive Software Systems | | BIB | Full-Text | 305-314 | |
| Ralph Schäfer; Mathias Bauer | |||
| Intelligent Scheduling, Monte Zweben, Mark S. Fox | | BIB | Full-Text | 315-318 | |
| M. Sasikumar | |||