TY  - GEN
AB  - As neurological disorders such as dementia, autism, and language impairment become more common, there is growing need for simple, objective screening tools. Narrative retelling tasks—where subjects listen to a short story and retell it—offer promise because these abilities are often impaired in affected populations. This dissertation evaluates the reliability and diagnostic utility of automated narrative analysis. We introduce a novel word alignment method using random walks, achieving faster and more accurate alignment than traditional approaches. Automated scoring based on these alignments predicts impairment with accuracy comparable to manual scoring and generalizes to other language samples, supporting its potential as a flexible screening tool.
AD  - Oregon Health and Science University
AU  - Tucker Prud'hommeaux, Emily
DA  - 2012
DO  - 10.6083/M4X63JZK
DO  - DOI
ED  - van Santen, Jan
ED  - Roark, Brian
ED  - Co-Advisor
ED  - Co-Advisor
ID  - 787
KW  - Neuropsychological Tests
KW  - Medical Informatics
KW  - Narration
KW  - Electronic Data Processing
KW  - Language Development Disorders
KW  - Nervous System Diseases
KW  - narratees (rhetoric)
L1  - https://digitalcollections.ohsu.edu/record/787/files/790_etd.pdf
L2  - https://digitalcollections.ohsu.edu/record/787/files/790_etd.pdf
L4  - https://digitalcollections.ohsu.edu/record/787/files/790_etd.pdf
LK  - https://digitalcollections.ohsu.edu/record/787/files/790_etd.pdf
N2  - As neurological disorders such as dementia, autism, and language impairment become more common, there is growing need for simple, objective screening tools. Narrative retelling tasks—where subjects listen to a short story and retell it—offer promise because these abilities are often impaired in affected populations. This dissertation evaluates the reliability and diagnostic utility of automated narrative analysis. We introduce a novel word alignment method using random walks, achieving faster and more accurate alignment than traditional approaches. Automated scoring based on these alignments predicts impairment with accuracy comparable to manual scoring and generalizes to other language samples, supporting its potential as a flexible screening tool.
PB  - Oregon Health and Science University
PY  - 2012
T1  - Alignment of narrative retellings for automated neuropsychological assessment
TI  - Alignment of narrative retellings for automated neuropsychological assessment
UR  - https://digitalcollections.ohsu.edu/record/787/files/790_etd.pdf
Y1  - 2012
ER  -