Ex-Ray: Text classification and machine learning for the assessment of mental health
Speaker: Prof Joachim Diederich, ITEE
When: 2003-08-14 14:00:00
Venue: 78-420
Host: Ralf Muhlberger
Abstract:Machine learning techniques such as support vector machines,
decision tree learners and neural networks are applied to a text
classification task to determine mental health problems. Inputs are
transcribed speech samples from a "structured-narrative task" and
outputs are psychiatric categories such as schizophrenia. In a
preliminary trial, subjects from three groups generated speech
samples: those with clinically diagnosed schizophrenia (31
patients), clinically diagnosed mania (16 patients) and controls (9
subjects). Even though the structured narrative task resulted in the
use of a limited vocabulary by all subjects (only a total of 1100
different words were used), a classification performance of close to
80% accuracy (SVMs), 88% precision and 82% recall (decision tree
learners) was achieved for the schizophrenia vs. control task. It is
expected that results improve further in experiments utilising
free-speech samples.
Biography:(biography unavailable)
Type: DKE Seminar
Contact:Ralf Muhlberger, seminar host (ralf@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)