Text mining and IRT for psychiatric and psychological assessment

Qiwei He

Research output: ThesisPhD Thesis - Research UT, graduation UTAcademic

102 Downloads (Pure)

Abstract

The information age has made it easy to store and process large amounts of data, including both structured data (e.g., responses to questionnaires) and unstructured data (e.g., natural language or prose). As an additional source of information in assessments, textual data has been increasingly used by cognitive, personality, clinical, and social psychologists in attempt to understand human beings. The questions how to handle these textual data and how to combine them with structured data in psychiatric and psychological assessments are the major themes in this thesis. The research initiates a new intake procedure for psychiatric screening for posttraumatic stress disorder (PTSD), which combines the utilization of advanced text mining techniques and item response modeling in one framework. The project consists of three parts: (1) computerized text classification on patients’ self narratives to screen for PTSD. (2) exploring the generalizability of DSM-IV diagnostic criteria for PTSD using item response modeling and identifying the differential symptom functioning related to various background variables such as gender, marital status and educational level. And (3) combining textual assessment on patients’ self-narratives and item-based assessments in one systematic framework to further improve the screening efficiency. Further, the automated intake framework is also validated in two psychological assessments. One focused on the application of text mining techniques in learning patterns among undergraduate students’ personality adaption with their life stories. The other engaged in an interesting analysis of Internet data that was collected from Facebook. This study investigated the relationship between people’s self-monitoring skills and verbal features in their textual posts on the Facebook wall. To sum up, the combination of the text mining technique with item response modeling is an innovation in psychiatric and psychological assessments. It is promising to be applied for a broader scope within the field of education, psychology, sociology in both research settings and practical use.
Original languageEnglish
Awarding Institution
  • University of Twente
Supervisors/Advisors
  • Glas, Cees A.W., Supervisor
  • de Vries, Theo , Supervisor
  • Veldkamp, Bernard P., Supervisor
  • Glas, C.A.W., Supervisor
  • de Vries, T., Supervisor
  • Veldkamp, B.P., Supervisor
Award date3 Oct 2013
Place of PublicationEnschede
Publisher
Print ISBNs978-90-365-0056-2
DOIs
Publication statusPublished - 3 Oct 2013

Fingerprint

posttraumatic stress disorder
facebook
personality
narrative
marital status
psychologist
source of information
diagnostic
sociology
psychology
utilization
monitoring
innovation
Internet
efficiency
human being
questionnaire
gender
language
learning

Keywords

  • IR-87394
  • METIS-297994

Cite this

He, Qiwei. / Text mining and IRT for psychiatric and psychological assessment. Enschede : Universiteit Twente, 2013. 143 p.
@phdthesis{b68fcf530b0a4b2da2aeddc392e77704,
title = "Text mining and IRT for psychiatric and psychological assessment",
abstract = "The information age has made it easy to store and process large amounts of data, including both structured data (e.g., responses to questionnaires) and unstructured data (e.g., natural language or prose). As an additional source of information in assessments, textual data has been increasingly used by cognitive, personality, clinical, and social psychologists in attempt to understand human beings. The questions how to handle these textual data and how to combine them with structured data in psychiatric and psychological assessments are the major themes in this thesis. The research initiates a new intake procedure for psychiatric screening for posttraumatic stress disorder (PTSD), which combines the utilization of advanced text mining techniques and item response modeling in one framework. The project consists of three parts: (1) computerized text classification on patients’ self narratives to screen for PTSD. (2) exploring the generalizability of DSM-IV diagnostic criteria for PTSD using item response modeling and identifying the differential symptom functioning related to various background variables such as gender, marital status and educational level. And (3) combining textual assessment on patients’ self-narratives and item-based assessments in one systematic framework to further improve the screening efficiency. Further, the automated intake framework is also validated in two psychological assessments. One focused on the application of text mining techniques in learning patterns among undergraduate students’ personality adaption with their life stories. The other engaged in an interesting analysis of Internet data that was collected from Facebook. This study investigated the relationship between people’s self-monitoring skills and verbal features in their textual posts on the Facebook wall. To sum up, the combination of the text mining technique with item response modeling is an innovation in psychiatric and psychological assessments. It is promising to be applied for a broader scope within the field of education, psychology, sociology in both research settings and practical use.",
keywords = "IR-87394, METIS-297994",
author = "Qiwei He",
year = "2013",
month = "10",
day = "3",
doi = "10.3990/1.9789036500562",
language = "English",
isbn = "978-90-365-0056-2",
publisher = "Universiteit Twente",
school = "University of Twente",

}

Text mining and IRT for psychiatric and psychological assessment. / He, Qiwei.

Enschede : Universiteit Twente, 2013. 143 p.

Research output: ThesisPhD Thesis - Research UT, graduation UTAcademic

TY - THES

T1 - Text mining and IRT for psychiatric and psychological assessment

AU - He, Qiwei

PY - 2013/10/3

Y1 - 2013/10/3

N2 - The information age has made it easy to store and process large amounts of data, including both structured data (e.g., responses to questionnaires) and unstructured data (e.g., natural language or prose). As an additional source of information in assessments, textual data has been increasingly used by cognitive, personality, clinical, and social psychologists in attempt to understand human beings. The questions how to handle these textual data and how to combine them with structured data in psychiatric and psychological assessments are the major themes in this thesis. The research initiates a new intake procedure for psychiatric screening for posttraumatic stress disorder (PTSD), which combines the utilization of advanced text mining techniques and item response modeling in one framework. The project consists of three parts: (1) computerized text classification on patients’ self narratives to screen for PTSD. (2) exploring the generalizability of DSM-IV diagnostic criteria for PTSD using item response modeling and identifying the differential symptom functioning related to various background variables such as gender, marital status and educational level. And (3) combining textual assessment on patients’ self-narratives and item-based assessments in one systematic framework to further improve the screening efficiency. Further, the automated intake framework is also validated in two psychological assessments. One focused on the application of text mining techniques in learning patterns among undergraduate students’ personality adaption with their life stories. The other engaged in an interesting analysis of Internet data that was collected from Facebook. This study investigated the relationship between people’s self-monitoring skills and verbal features in their textual posts on the Facebook wall. To sum up, the combination of the text mining technique with item response modeling is an innovation in psychiatric and psychological assessments. It is promising to be applied for a broader scope within the field of education, psychology, sociology in both research settings and practical use.

AB - The information age has made it easy to store and process large amounts of data, including both structured data (e.g., responses to questionnaires) and unstructured data (e.g., natural language or prose). As an additional source of information in assessments, textual data has been increasingly used by cognitive, personality, clinical, and social psychologists in attempt to understand human beings. The questions how to handle these textual data and how to combine them with structured data in psychiatric and psychological assessments are the major themes in this thesis. The research initiates a new intake procedure for psychiatric screening for posttraumatic stress disorder (PTSD), which combines the utilization of advanced text mining techniques and item response modeling in one framework. The project consists of three parts: (1) computerized text classification on patients’ self narratives to screen for PTSD. (2) exploring the generalizability of DSM-IV diagnostic criteria for PTSD using item response modeling and identifying the differential symptom functioning related to various background variables such as gender, marital status and educational level. And (3) combining textual assessment on patients’ self-narratives and item-based assessments in one systematic framework to further improve the screening efficiency. Further, the automated intake framework is also validated in two psychological assessments. One focused on the application of text mining techniques in learning patterns among undergraduate students’ personality adaption with their life stories. The other engaged in an interesting analysis of Internet data that was collected from Facebook. This study investigated the relationship between people’s self-monitoring skills and verbal features in their textual posts on the Facebook wall. To sum up, the combination of the text mining technique with item response modeling is an innovation in psychiatric and psychological assessments. It is promising to be applied for a broader scope within the field of education, psychology, sociology in both research settings and practical use.

KW - IR-87394

KW - METIS-297994

U2 - 10.3990/1.9789036500562

DO - 10.3990/1.9789036500562

M3 - PhD Thesis - Research UT, graduation UT

SN - 978-90-365-0056-2

PB - Universiteit Twente

CY - Enschede

ER -