Automatic classification of dysfunctional thoughts: a feasibility test

Katja Wiemer-Hastings, A. Janit, Peter Wiemer-Hastings, S. Cromer, and J. Kinser. Automatic classification of dysfunctional thoughts: a feasibility test. Behavior Research Methods Instruments and Computers, 36:203–212, 2004.

Download

(unavailable)

Abstract

The identification of cognitive distortions is a central effort in cognitive therapy. This paper describes the first version of a system designed to classify distortions automatically. The system rules were developed based on language markers that were identified from a sample of 188 example thoughts. The system was tested with an independent set of 112 example thoughts. The evaluation study shows that the system detects the majority of dysfunctional thoughts, but works reliably only for some thought categories. Potential applications of systems like this in the therapy domain are discussed. Automatic thought classification may be a first step towards dialogic computer modules in cognitive therapy.

BibTeX

@ARTICLE{Wiemer-Hastings:BRMIC04,
        AUTHOR = {Katja Wiemer-Hastings and {A. Janit} and Peter Wiemer-Hastings and {S. Cromer} and {J. Kinser}},
        YEAR = {2004},
	JOURNAL = {Behavior Research Methods Instruments and Computers},
        volume = 36, 
	TITLE = {Automatic classification of dysfunctional thoughts: a feasibility test},
	PAGES = {203-212},
  cvnote = {Impact factor = 2.458, g-index = 175},
  abstract = {The identification of cognitive distortions is a central effort in cognitive therapy.  This paper describes the first version of a system designed to classify distortions automatically.  The system rules were developed based on language markers that were identified from a sample of 188 example thoughts.  The system was tested with an independent set of 112 example thoughts.  The evaluation study shows that the system detects the majority of dysfunctional thoughts, but works reliably only for some thought categories.  Potential applications of systems like this in the therapy domain are discussed.  Automatic thought classification may be a first step towards dialogic computer modules in cognitive therapy.},
}