Navigation in Hyperspace and Cognitive Representation/Literature

Lambert Schomaker, 12 Dec 1994

This page is being developed during the Cognitive Ergonomics course CO440 of Cognitive Science at the Nijmegen University, The Netherlands. The subject is on how people build up mental representations of information collected in a hypermedia tour.

Literature, Bits & Pieces

Analyzing traces or trails of hypertext navigation

Trying to find structure in a history of hypermedia navigation is something similar to detecting probabilistic grammars (in case of symbolic noise in the action sequence) and deterministic grammar inference (in the noise-free case). Below are some interesting papers. Note that the idea of context-free grammar inference is impractical. The adding of goals narrows down the search space considerably. In this course: this means adding knowledge on User Goals.
%TI An ALPS ASCII interchange format for describing hypertext trails
%OR UNISA
%AV fax +61 8 3023381
%LT CIS-92-002
%AU Thomas, B.H.
%YR 1992
%AB A subset of ALPS (A Language for Process Specification) has been
used to describe hypertext trails.  One major problem in describing
these hypertext trails is having a proper interchange language external
to the information spaces.  This paper describes an ASCII file format
for the subset of ALPS used for hypertext trail definition.  This paper
gives a BNF grammar, lexicon, and a detailed example of an ALPS
program.

%TI The Use of Explicit Goals for Knowledge to Guide Inference and Learning
%AU Ashwin Ram
%AU Lawrence Hunter
%PU Journal of Applied Intelligence, 2(1):47-73, 1992
%AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-04.ps.Z
%OR GTECH
%LT GIT-CC-92/04
%YR 1992
%AB Combinatorial explosion of inferences has always been a central
problem in artificial intelligence.  Although the inferences that
can be drawn from a reasoner's knowledge and from available inputs
is very large (potentially infinite), the inferential resources
available to any reasoning system are limited.  With limited
inferential capacity and very many potential inferences, reasoners
must somehow control the process of inference.  Not all inferences
are equally useful to a given reasoning system.  Any reasoning
system that has goals (or any form of a utility function) and acts
based on its beliefs indirectly assigns utility to its beliefs.
Given limits on the process of inference, and variation in the
utility of inferences, it is clear that a reasoner ought to draw the
inferences that will be most valuable to it.  This paper presents an
approach to this problem that makes the utility of a (potential)
belief an explicit part of the inference process.  The method is to
generate explicit desires for knowledge.  The question of focus of
attention is thereby transformed into two related problems: How can
explicit desires for knowledge be used to control inference and
facilitate resource-constrained goal pursuit in general? and, Where
do these desires for knowledge come from?  We present a theory of
knowledge goals, or desires for knowledge, and their use in the
processes of understanding and learning.  The theory is illustrated
using two case studies, a natural language understanding program
that learns by reading novel or unusual newspaper stories, and a
differential diagnosis program that improves its accuracy with
experience.

The method in this next paper could potentially be used in creating a model of hypertext navigation in a given document. This is sufficient if one aims at a surface-level simulation of user behavior. However, the method does not make the detected grammar explicit.
%TI Learning a Class of Large Finite State Machines with a Recurrent Neural Network
%AU C. L. Giles
%AU B. G. Horne
%AU T. Lin
%MN August
%YR 1994
%LT CS-TR-3328
%AB One of the issues in any learning model is how it scales with problem 
size. Neural networks have not been immune to scaling issues. We show that a 
dynamically-driven discrete-time recurrent network (DRNN) can learn rather 
large grammatical inference problems when the strings of a finite memory 
machine (FMM) are encoded as temporal sequences. FMMs are a subclass of finite 
state machines which have a finite memory or a finite order of inputs and 
outputs. The DRNN that learns the FMM is a neural network that maps directly 
from the sequential machine implementation of the FMM. It has feedback only 
from the output and not from any hidden units; an example is the recurrent 
network of Narendra and Parthasarathy. (FMMs that have zero order in the 
feedback of outputs are called definite memory machines and are analogous to 
Time-delay or Finite Impulse Response neural networks.) Due to their 
topology these DRNNs are as least as powerful as any sequential machine 
implementation of a FMM and should be capable of representing any FMM. We 
choose to learn ``particular FMMs.\' Specifically, these FMMs have a large 
number of states (simulations are for $256$ and $512$ state FMMs) but have 
minimal order, relatively small depth and little logic when the FMM is 
implemented as a sequential machine. Simulations for the number of training 
examples versus generalization performance and FMM extraction size show that 
the number of training samples necessary for perfect generalization 
is less than that necessary to completely characterize the FMM to be learned. 
This is in a sense a best case learning problem since any arbitrarily chosen 
FMM with a minimal number of states would have much more order and string 
depth and most likely require more logic in its sequential machine 
implementation.
%OR UMD
%AV url ftp://ftp.cs.umd.edu/pub/papers/TRs/3328.ps.Z

%AU Margaret Recker
%PU Educational Multimedia and Hypermedia Annual 1994
%AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-94-01.ps.gz
%OR GTECH
%LT ER-MR-94/01
%YR 1994
%AB We present a theoretical approach and a methodology for
analyzing data from students interacting with and learning from
hypermedia systems.  In our approach, interactions are viewed to be
mutually influenced by individual students' goals and strategies and
the actions supported by the interface of the learning environment.
The approach is illustrated by modelling data from an empirical study
in which students browsed through a hypertext instructional
environment to learn about programming concepts.  By
using the explanatory power of the computational model, interactions
can be analyzed to determine patterns of use.  Results obtained from
this method of analysis yield specific feedback on system design and
prescriptions for improving the design.  More theoretically, they
provide valuable insights on the nature of human cognition and
learning in the context of interactive educational technologies.

And, finally, here is a paper with critical remarks with respect to visualization:

Petre & Price (1992), "Why Computer Interfaces Are Not Like Paintings: the user as a deliberate reader".

Abstract

Designers seeking to improve human-computer interfaces, particularly those concerned with programming environments, often assume that "graphics" will always result in an improvement over "text". Such claims are especially difficult to assess, given that people have used the terms "text" and "graphics" in different and conflicting ways throughout the literature. This paper suggests a preliminary, consistent terminology for discussing "graphical interfaces" (including so-called "visual programming systems") to highlight some of the issues involved in using "graphics" in notations and interfaces. It discusses evidence from empirical studies showing that the use of "graphics" doesn't necessarily lead to improvement and may introduce its own problems. The paper concludes with a discussion of the succesful integration of "graphics" and "text".


schomaker@nici.kun.nl