Combining text mining of long constructed responses and item-based measures: A hybrid test design to screen for posttraumatic stress disorder (PTSD)

Qiwei He*, Bernard P. Veldkamp, Cees A.W. Glas, Stéphanie M. van den Berg

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

5 Downloads (Pure)

Abstract

This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future.

Original languageEnglish
Article number2358
JournalFrontiers in psychology
Volume10
Issue numberOCT
DOIs
Publication statusPublished - 22 Oct 2019

Fingerprint

Data Mining
Post-Traumatic Stress Disorders
Educational Measurement
Psychiatry
Hand
Psychology
Surveys and Questionnaires

Keywords

  • Bayesian framework
  • Item response theory
  • Posttraumatic stress disorder
  • Self-narratives
  • Text mining

Cite this

@article{f42b43ffde6e413cb026947941cba555,
title = "Combining text mining of long constructed responses and item-based measures: A hybrid test design to screen for posttraumatic stress disorder (PTSD)",
abstract = "This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future.",
keywords = "Bayesian framework, Item response theory, Posttraumatic stress disorder, Self-narratives, Text mining",
author = "Qiwei He and Veldkamp, {Bernard P.} and Glas, {Cees A.W.} and {van den Berg}, {St{\'e}phanie M.}",
year = "2019",
month = "10",
day = "22",
doi = "10.3389/fpsyg.2019.02358",
language = "English",
volume = "10",
journal = "Frontiers in psychology",
issn = "1664-1078",
publisher = "Frontiers Media S.A.",
number = "OCT",

}

TY - JOUR

T1 - Combining text mining of long constructed responses and item-based measures

T2 - A hybrid test design to screen for posttraumatic stress disorder (PTSD)

AU - He, Qiwei

AU - Veldkamp, Bernard P.

AU - Glas, Cees A.W.

AU - van den Berg, Stéphanie M.

PY - 2019/10/22

Y1 - 2019/10/22

N2 - This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future.

AB - This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future.

KW - Bayesian framework

KW - Item response theory

KW - Posttraumatic stress disorder

KW - Self-narratives

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85074518864&partnerID=8YFLogxK

U2 - 10.3389/fpsyg.2019.02358

DO - 10.3389/fpsyg.2019.02358

M3 - Article

AN - SCOPUS:85074518864

VL - 10

JO - Frontiers in psychology

JF - Frontiers in psychology

SN - 1664-1078

IS - OCT

M1 - 2358

ER -