Academic journal article American Journal of Psychotherapy

The Application of Computerized Content Analysis of Natural Language in Psychotherapy Research Now and in the Future

Academic journal article American Journal of Psychotherapy

The Application of Computerized Content Analysis of Natural Language in Psychotherapy Research Now and in the Future

Article excerpt

For many years the author and his colleagues have been involved in studying the roots and processes of the conveyance of semantic messages via spoken language and verbal texts. After establishing that reliable and valid measurements of highly relevant neuropsychiatric categories, such as anxiety, depression, and cognitive impairment, can be made by identifying and counting the occurrence per grammatical clause of language content and form categories typifying specific content-analysis scales, the research focus has turned towards computerizing this process of content analysis. This report summarizes the achievements and applications of the current empirical status of this method of computerized content analysis of natural language to psychotherapy research, and it speculates on possible future applications in the millennium.


For the millennium, what are the prospects for application of computerized content analysis of natural language in psychotherapy for the future? The amazing progress during the late 1990s in technology and, especially, in computer software and hardware, promises applications and discoveries that are very likely to relate constructively to the subjectivity characterizing the processes and procedures of psychotherapy

For the benefit of the many individuals who have not been able to keep informed up to the present time of the advances and applications of computerized content analysis of verbal behavior, a review of the scientific status of computerized content analysis of language would be appropriate.


The development of an objective and reliable method of measuring the magnitude of various psychological dimensions from natural language was motivated by the recognition that diagnosticians and therapists use their patients' speech as the major source of information for their diagnostic formulations and therapeutic interventions. In doing so, they assess how and what is said in an impressionistic manner that may allow for a relatively high likelihood of distortion and/or error from potentially incorrect empathic responses and inferences during the process of evaluating the meanings and significance of their patients' talk. How to minimize such error and how to maximize the uniformity and consistency of the inferential evaluations concerning a speaker's subjective experience and the relative magnitude of these psychobiological states and traits became a major aim in our development of a computerized method of measuring these dimensions from natural language.

In the process of our probing the immediate emotional reactions of individuals from speech, an effort was made in the elicitation of speech to minimize a speaker's reactions of guarding or covering up. In initial studies, the instructions to elicit speech from patients or other subjects were purposely relatively ambiguous and nonstructured-simulating a request to free-associate-so as to avoid guiding the speaker to talk about any specific topics. This approach was used to establish norms for the neuropsychiatric dimensions to be measured for medically and neuropsychiatrically healthy individuals, as well as to compare any individuals in a standard context so that demographic and personality variables could be explored and investigated while holding relatively constant the influence of such variables as the instructions for eliciting speech, the nature and personality of the interviewer, the context, and the situation. The effects of varying these noninterviewee variables were subsequently investigated, one by one, after reliable and valid content-analysis scales were developed. The development of the Gottschalk-Gleser method of content analysis, which is the focus of this report, involved a long series of steps. 1. The lexical cues per grammatical clause (the smallest unit of verbal communication) were carefully pinpointed by which a receiver of any verbal messages infers the occurrence of any of these psychobiological states in the speaker. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.