Blurb:

The clinical interview is commonly used in psychiatry for diagnosis, though it is time-consuming, needs special training, and multiple sources of information. Recently computerized analysis of speech offers objective means for evaluating symptoms in schizophrenia. Cohen writes: "Accurate measurement of negative symptoms is crucial for understanding and treating schizophrenia. However, current measurement strategies are reliant on subjective symptom rating scales, which often have psychometric and practical limitations. Computerized analysis of patients’ speech offers a sophisticated and objective means of evaluating negative symptoms" (2007: 827). Specific to schizophrenia, machine learning techniques have been used in the study of patients’ writings (Strous et al. 2008). With large within group differences, there is no one language characteristic that distinguishes speakers with schizophrenia and mania. However, this study has found that combinations of features and possible correlations among the features separated the diagnostic groups, characterizing the disorders. Transcripts of subjects with schizophrenia (six transcripts) and mania (four transcripts) were digitalized to compose two sub-corpora. The texts were annotated and analyzed (UAM Corpus Tool, O’Donnell 2008) for syntactic complexity, amount of talk, dysfluencies, type-token ratio, lexical similarity, and word frequency among other variables.