TY - JOUR
T1 - How language flows when movements don't
T2 - An automated analysis of spontaneous discourse in Parkinson's disease
AU - García, Adolfo M.
AU - Carrillo, Facundo
AU - Orozco-Arroyave, Juan Rafael
AU - Trujillo, Natalia
AU - Vargas Bonilla, Jesús F.
AU - Fittipaldi, Sol
AU - Adolfi, Federico
AU - Nöth, Elmar
AU - Sigman, Mariano
AU - Fernández Slezak, Diego
AU - Ibáñez, Agustín
AU - Cecchi, Guillermo A.
N1 - Publisher Copyright:
© 2016 Elsevier Inc.
PY - 2016/11/1
Y1 - 2016/11/1
N2 - To assess the impact of Parkinson's disease (PD) on spontaneous discourse, we conducted computerized analyses of brief monologues produced by 51 patients and 50 controls. We explored differences in semantic fields (via latent semantic analysis), grammatical choices (using part-of-speech tagging), and word-level repetitions (with graph embedding tools). Although overall output was quantitatively similar between groups, patients relied less heavily on action-related concepts and used more subordinate structures. Also, a classification tool operating on grammatical patterns identified monologues as pertaining to patients or controls with 75% accuracy. Finally, while the incidence of dysfluent word repetitions was similar between groups, it allowed inferring the patients’ level of motor impairment with 77% accuracy. Our results highlight the relevance of studying naturalistic discourse features to tap the integrity of neural (and, particularly, motor) networks, beyond the possibilities of standard token-level instruments.
AB - To assess the impact of Parkinson's disease (PD) on spontaneous discourse, we conducted computerized analyses of brief monologues produced by 51 patients and 50 controls. We explored differences in semantic fields (via latent semantic analysis), grammatical choices (using part-of-speech tagging), and word-level repetitions (with graph embedding tools). Although overall output was quantitatively similar between groups, patients relied less heavily on action-related concepts and used more subordinate structures. Also, a classification tool operating on grammatical patterns identified monologues as pertaining to patients or controls with 75% accuracy. Finally, while the incidence of dysfluent word repetitions was similar between groups, it allowed inferring the patients’ level of motor impairment with 77% accuracy. Our results highlight the relevance of studying naturalistic discourse features to tap the integrity of neural (and, particularly, motor) networks, beyond the possibilities of standard token-level instruments.
KW - Grammatical features
KW - Graph embedding
KW - Latent semantic analysis
KW - Parkinson's disease
KW - Part-of-speech tagging
KW - Semantic fields
KW - Spontaneous discourse
KW - Word repetition
UR - http://www.scopus.com/inward/record.url?scp=84982684503&partnerID=8YFLogxK
U2 - 10.1016/j.bandl.2016.07.008
DO - 10.1016/j.bandl.2016.07.008
M3 - Article
C2 - 27501386
AN - SCOPUS:84982684503
SN - 0093-934X
VL - 162
SP - 19
EP - 28
JO - Brain and Language
JF - Brain and Language
ER -