An intelligent agent for sentence completion test: creation and application in depression assessment

During large-scale psychological screening, traditional self-report questionnaires face challenges like response deception or social desirability bias, while the Sentence Completion Test (SCT) as a projective technique shows potential but is limited by manual scoring and high costs. Leveraging advan...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuchen Huang, Mengxiao Lei, Hanyu Zhang, Lu Zong, Bin Zhu, Hong Luo
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Psychology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1649905/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235692383633408
author Yuchen Huang
Yuchen Huang
Mengxiao Lei
Hanyu Zhang
Lu Zong
Bin Zhu
Hong Luo
author_facet Yuchen Huang
Yuchen Huang
Mengxiao Lei
Hanyu Zhang
Lu Zong
Bin Zhu
Hong Luo
author_sort Yuchen Huang
collection DOAJ
description During large-scale psychological screening, traditional self-report questionnaires face challenges like response deception or social desirability bias, while the Sentence Completion Test (SCT) as a projective technique shows potential but is limited by manual scoring and high costs. Leveraging advancements in Large Language Models (LLMs), this study integrates SCT’s theoretical framework with LLM capabilities to develop a specialized set of SCT items for depression assessment in Chinese university students, using a self-built intelligent agent across three progressive empirical studies. Results show the agent demonstrates good reliability (Cronbach’s α = 0.89–0.92) and validity, with high consistency to manual scoring (r = 0.96), significant criterion correlations with the Beck Depression Inventory (r = 0.89) and Self-Rating Depression Scale (r = 0.85), confirmed structural validity via exploratory factor analysis. Furthermore, the intelligent agent could identify most invalid responses (F1 = 0.94, Accuracy = 0.99, Precision = 0.99, Recall = 0.90). This research marks a key milestone in SCT’s intelligent transformation, driving innovation in psychological assessment and offering new academic and practical pathways.
format Article
id doaj-art-99054c6ecce04157b4b9a1de9edd5133
institution Kabale University
issn 1664-1078
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychology
spelling doaj-art-99054c6ecce04157b4b9a1de9edd51332025-08-20T04:02:41ZengFrontiers Media S.A.Frontiers in Psychology1664-10782025-08-011610.3389/fpsyg.2025.16499051649905An intelligent agent for sentence completion test: creation and application in depression assessmentYuchen Huang0Yuchen Huang1Mengxiao Lei2Hanyu Zhang3Lu Zong4Bin Zhu5Hong Luo6Affiliated Mental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaHangzhou PsychSnail Technology Company Limited, Hangzhou, ChinaHangzhou PsychSnail Technology Company Limited, Hangzhou, ChinaHangzhou Yunqi Interdisciplinary Technology Research Institute, Hangzhou, ChinaSuzhou Guangzhinian Technology Company Limited, Suzhou, ChinaSchool of Journalism & Communication, Hangzhou City University, Hangzhou, ChinaAffiliated Mental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDuring large-scale psychological screening, traditional self-report questionnaires face challenges like response deception or social desirability bias, while the Sentence Completion Test (SCT) as a projective technique shows potential but is limited by manual scoring and high costs. Leveraging advancements in Large Language Models (LLMs), this study integrates SCT’s theoretical framework with LLM capabilities to develop a specialized set of SCT items for depression assessment in Chinese university students, using a self-built intelligent agent across three progressive empirical studies. Results show the agent demonstrates good reliability (Cronbach’s α = 0.89–0.92) and validity, with high consistency to manual scoring (r = 0.96), significant criterion correlations with the Beck Depression Inventory (r = 0.89) and Self-Rating Depression Scale (r = 0.85), confirmed structural validity via exploratory factor analysis. Furthermore, the intelligent agent could identify most invalid responses (F1 = 0.94, Accuracy = 0.99, Precision = 0.99, Recall = 0.90). This research marks a key milestone in SCT’s intelligent transformation, driving innovation in psychological assessment and offering new academic and practical pathways.https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1649905/fullsentence completion testprojective testlarge language modelsAI agentdepression assessment
spellingShingle Yuchen Huang
Yuchen Huang
Mengxiao Lei
Hanyu Zhang
Lu Zong
Bin Zhu
Hong Luo
An intelligent agent for sentence completion test: creation and application in depression assessment
Frontiers in Psychology
sentence completion test
projective test
large language models
AI agent
depression assessment
title An intelligent agent for sentence completion test: creation and application in depression assessment
title_full An intelligent agent for sentence completion test: creation and application in depression assessment
title_fullStr An intelligent agent for sentence completion test: creation and application in depression assessment
title_full_unstemmed An intelligent agent for sentence completion test: creation and application in depression assessment
title_short An intelligent agent for sentence completion test: creation and application in depression assessment
title_sort intelligent agent for sentence completion test creation and application in depression assessment
topic sentence completion test
projective test
large language models
AI agent
depression assessment
url https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1649905/full
work_keys_str_mv AT yuchenhuang anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT yuchenhuang anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT mengxiaolei anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT hanyuzhang anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT luzong anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT binzhu anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT hongluo anintelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT yuchenhuang intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT yuchenhuang intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT mengxiaolei intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT hanyuzhang intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT luzong intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT binzhu intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment
AT hongluo intelligentagentforsentencecompletiontestcreationandapplicationindepressionassessment