Item – Theses Canada

​
OCLC number
60797560
Link(s) to full text
LAC copy
LAC copy
Author
Thomas, Calvin MacDonald,1980-
Title
Rating dementia of Alzheimer type through lexical analysis of spontaneous speech.
Degree
M.C. Sc. -- Dalhousie University, 2004
Publisher
Ottawa : National Library of Canada = Bibliothèque nationale du Canada, [2005]
Description
1 microfiche.
Notes
Includes bibliographical references.
Abstract
Current methods of assessing dementia of Alzheimer type (DAT) in older adults involve structured interviews that attempt to capture the complex nature of deficits suffered. One of the most significant areas affected by the disease is the capacity for functional communication as linguistic skills break down. Current methods of assessing this breakdown often do not capture the true nature of language deficits in spontaneous speech. Therefore, researchers working in this field should look for automatic and objective methods for use in diagnosing patients through analysis of spontaneous speech that overcome the shortfalls of current methods. In this thesis, we detail several lexical approaches to the problem of detecting and rating DAT in patients from our corpus. All of the approaches explored in this thesis were motivated by a desire to develop machine learning algorithms over lexical attributes automatically extracted from plain text transcripts of spontaneous speech. The goal of this research is to show that automatic techniques based on the analysis of spontaneous speech can provide objective measures of dementia levels in AD patients. This interdisciplinary area brings opportunities for novel research to be conducted with generic text classification algorithms. Also explored are novel extensions to existing techniques that were developed to address specific qualities inherent to the corpus analyzed. Our results show that purely computational solutions offer a viable alternative to standard approaches to diagnosing the level of impairment in patients. Although more work needs to be done to improve the accuracy of these methods, these results are significant step forward towards automatic and objective means to identifying early symptoms of DAT in older adults.
ISBN
0612941019
9780612941014