GOLDEN: KDC
RICHARD GOLDEN HOME PAGE
KDC: A Computer Program for the Analysis of Coherence Relations in Discourse
KDC is a statistical software tool environment specifically intended to support
the analysis and exploitation of local coherence relations in traversal data
during comprehension or production data (e.g., recall, summarization, think-aloud).
Briefly, KDC analysis is a categorical time-series analysis which views
the observed data as an ordered sequence of complex propositions.
The researcher postulates several directed graphs corresponding to different
possible predictions regarding how the sequence of propositions is organized
and then the relative contribution of each directed graph is estimated.
Golden (1998), Jaynes and Golden (2003), and the recent thesis by Ismaili (2012)
are good places to start learning about KDC analysis.
SELECTED TALKS, PUBLICATIONS, and PRESENTATIONS
Ismaili, P. B. (2012)
Effects of Expertise and Hypertext Presentation Formats on
Dynamic Mental Models using Both Classical and Novel Statistical
Sequential Analysis.
Doctoral dissertation. School of Behavioral and Brain Sciences.
University of Texas at Dallas, Richardson, TX.
Ismaili, P. B. and Golden, R. M. (2008).
Traversal patterns for content designed web environment.
WSEAS Transactions on Information Science and Applications, 11,
5, 1521-1530.
Jaynes, C. and Golden, R. M. (2003). Statistical detection
of local coherence relations in narrative recall and summarization
data. In R. Alterman and D. Kirsh (eds.).
Proceedings of the 25th Annual Conference of the Cognitive Science
Society,
Boston, MA: Cognitive Science Society, 3-8.
Golden, R. M. (1998).
Knowledge digraph contribution analysis of protocol data.
Discourse Processes, 25,
179-210.
Semi-final draft of the original!
Golden, R. M. (1997). Causal network analysis validation
using synthetic recall protocols.
Behavior Research Methods Instruments & Computers, 29,
15-24.
Golden, R. M. (1994). Analysis of Categorical Time-Series
Text Recall Data using a Connectionist Model.
Journal of Biological Systems, 2, 283-305.
283-305.
Golden, R. M. (2006).
Technical Report: Knowledge Digraph
Contribution Analysis.
School of Behavioral and Brain Sciences, GR4.1,
University of Texas at Dallas, Richardson, TX 75083-0688.
Golden, R. M. (2006).
KDC Software Powerpoint Tutorial.
School of Behavioral and Brain Sciences, GR4.1,
University of Texas at Dallas, Richardson, TX 75083-0688.
KDC SOFTWARE (Academic License for Non-Commercial Use Only)
Currently, we are only supporting KDC on PC computers. Eventually
it will be made available for MACS and LINUX operating systems.
STEP 1: Download and Install MATLAB Compiler Run-Time Library
DOWNLOAD MATLAB MCR INSTALLER
After you have downloaded the MCRINSTALLER, click on the MCRINSTALLER
and it will walk you through the installation procedure
for installing the MATLAB Compiler Run-Time Library on your computer.
You have legal permission to install this MATHWORKS software to run KDC
but you do not have permission to use the MATHWORKS
software for any other purpose.
Uninstalling the MATLAB Compiler Run-Time Library software.
Do not delete the MCRINSTALLER software from your machine. If you
ever want to uninstall the MATLAB Compiler Run-Time
Library software then you will need
to use the MCRINSTALLER for a "clean" uninstall. To uninstall,
simply go through the motions as if you wanted to install the software,
the MCRINSTALLER is smart enough to figure out that the software is
already installed and will ask you if you want to uninstall the
software. This is the best way to uninstall the MATLAB
Compiler Run-Time Library. After you have completed this
uninstallation procedure, then feel free to delete anything you like!
STEP 2: Download the KDC Software
DOWNLOAD KDC SOFTWARE
Note that the KDC Software is for ACADEMIC use only to support scientific
research. Also note that the KDC software is not a commercial software package
and we are constantly updating and revising the software. Please check the
website
KDC Software Updates
for KDC software updates and fixes and known problems.
Note that if you skip Step 1 then the downloaded KDC software will
not work properly (or at all) on your machine unless you just happen
to already have MATLAB R2011b installed on your computer. In that
case, you can skip Step 1; otherwise YOU MUST HAVE INSTALLED
the MATHWORKS COMPILER RUN-TIME LIBARY on your computer before installing
KDC!!!
STEP 3: Download the Example KDC work folder
DOWNLOAD EXAMPLE KDC WORK FOLDER
After you download this folder, unzip the folder. When you start up
the KDC software you will need to identify this folder. Then you
should load in one of the example models. There is a text file
in the folder called
KDChelpREADME.txt
which should be helpful.
Example data files are
neurostudents.data
and
psychstudents.data.
Example model files are
BiDirectionalALL.model
and
BiDirectionalSemantic.model.
NATIONAL SCIENCE FOUNDATION (NSF) FUNDING SUPPORT
NSF AWARD 0113669
This research was funded in part by the NSF Information Technology
Research Initiative through the Research and Learning on Education Program
jointly with the Directorate for Social, Behavioral, and Economic Sciences
and the Directorate for Computer & Information Science and Engineering and the
Directorate for Education and Human Resources.
NSF AWARD 0624983
This research was also funded in part by NSF Award 0624983 entitled
Dissertation Research: Statistical Models of Hypertext Comprehension
to Dr. Richard Golden to support the dissertation research of Dr. Perwaiz Ismaili.
NSF Award 0624983 was funded by the Directorate for Social, Behavioral,
and Economic Sciences (SBE), Division of Social and Economic Sciences (SES),
Methodology, Measurement and Statistics (MMS).
RICHARD GOLDEN HOME PAGE