Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.746654
Title: What text mining analysis of psychotherapy records can tell us about therapy process and outcome
Author: Yelland, E. R.
ISNI:       0000 0004 7225 2178
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
Increasing demand for mental health treatment and the transfer of a large portion of our lives online has led to the development of a growing range of computerized psychological therapy programmes. We are also creating and storing data at ever increasing rates, a trend that has led to the development of sophisticated textual analysis approaches. This thesis sits at the cross-section of these evolving areas. It is an exploratory analysis of how text mining analysis can be applied to online cognitive behaviour therapy. The project emerged as a collaboration between two commercial partners: Ieso Digital Health and Linguamatics, and UCL. Ieso Digital Health provide online cognitive behaviour therapy via an online instant messaging platform and Linguamatics are the developers of text mining software I2E. The involvement of the two industrial partners in this project shaped two major components of this research; the data studied and the platform for textual analysis. Linguistic analysis of textual data in mental health is a wide and variable field that brings together a variety of methods and data formats. These are broadly introduced in Chapter 1 and Chapter 2 provides a systematic review of research on the analysis of language used within therapeutic exchanges during mental health treatment. The research carried out in this thesis involved the development of a number of linguistic features within I2E and statistical analyses to explore their association with mental health outcomes and the development of predictive models of outcome. The results (Chapters 4-10) suggested that there were statistically significant associations between selected language features and therapy outcome scores but that these language features did not fare well as predictors of outcome when developed models were externally validated. These results and recommendations for the application of text mining in therapy transcripts are discussed in Chapter 11.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.746654  DOI: Not available
Share: