서브메뉴
검색
Leaving Their Mark: New Computational Methods Reveal Rich Latent Structure in Children's Human Figure Drawings
Leaving Their Mark: New Computational Methods Reveal Rich Latent Structure in Children's Human Figure Drawings
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105140
- ISBN
- 9798291588581
- DDC
- 153
- 저자명
- Jensen, Clint A.
- 서명/저자
- Leaving Their Mark: New Computational Methods Reveal Rich Latent Structure in Childrens Human Figure Drawings
- 발행사항
- [Sl] : The University of Wisconsin - Madison, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 248 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: A.
- 주기사항
- Advisor: Rogers, Timothy T.
- 학위논문주기
- Thesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
- 초록/해제
- 요약Because most children happily produce drawings, there has long been interest in what those drawings might suggest about a child's inner life. From the earliest descriptions of children's drawings through more careful and rigorous scientific research, it is common to begin with two basic assumptions. The first holds that across the drawings that children produce, there will be many commonalities shared between children. The second assumption is that within the drawings an individual child produces, some aspect or group of features will connote abilities, competencies, emotional/mental states, or underlying characteristics of that particular child. So that any commonalities, discrepancies, or attributes can be better identified, both historic and current methods of drawing assessment involve checklists wherein raters determine the presence or absence of a predetermined set of features (e.g., within human figure drawings: head, arms, eyes, etc.). After indicating which features are present, a count value for individual features can be summed together to produce a single integer score for a given drawing. The resulting drawing scores are then aggregated with other behavioral and cognitive measures or used independently to predict a diversity of outcomes with perhaps surprising effectiveness. Nevertheless, the checklist method may-despite its apparent simplicity-both add an unnecessary burden to the researcher while also underrepresenting the performance of the child. Within this dissertation, I will present recent research that leverages computational advances in both collecting and analyzing drawings through the use of crowd-sourced perceptual judgements and convolutional neural networks trained on photographs of real-world images to uncover latent structure in children's drawings. These methodologies offer an opportunity to both improve and enhance the assessment of children's development through their drawings.
- 일반주제명
- Cognitive psychology
- 일반주제명
- Developmental psychology
- 일반주제명
- Psychology
- 일반주제명
- Information science
- 키워드
- Cognition
- 키워드
- Machine vision
- 기타저자
- The University of Wisconsin - Madison Psychology
- 기본자료저록
- Dissertations Abstracts International. 87-03A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359575
■00520260202105140
■006m o d
■007cr#unu||||||||
■020 ▼a9798291588581
■035 ▼a(MiAaPQ)AAI32240571
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a153
■1001 ▼aJensen, Clint A.
■24510▼aLeaving Their Mark: New Computational Methods Reveal Rich Latent Structure in Children's Human Figure Drawings
■260 ▼a[Sl]▼bThe University of Wisconsin - Madison▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a248 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: A.
■500 ▼aAdvisor: Rogers, Timothy T.
■5021 ▼aThesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
■520 ▼aBecause most children happily produce drawings, there has long been interest in what those drawings might suggest about a child's inner life. From the earliest descriptions of children's drawings through more careful and rigorous scientific research, it is common to begin with two basic assumptions. The first holds that across the drawings that children produce, there will be many commonalities shared between children. The second assumption is that within the drawings an individual child produces, some aspect or group of features will connote abilities, competencies, emotional/mental states, or underlying characteristics of that particular child. So that any commonalities, discrepancies, or attributes can be better identified, both historic and current methods of drawing assessment involve checklists wherein raters determine the presence or absence of a predetermined set of features (e.g., within human figure drawings: head, arms, eyes, etc.). After indicating which features are present, a count value for individual features can be summed together to produce a single integer score for a given drawing. The resulting drawing scores are then aggregated with other behavioral and cognitive measures or used independently to predict a diversity of outcomes with perhaps surprising effectiveness. Nevertheless, the checklist method may-despite its apparent simplicity-both add an unnecessary burden to the researcher while also underrepresenting the performance of the child. Within this dissertation, I will present recent research that leverages computational advances in both collecting and analyzing drawings through the use of crowd-sourced perceptual judgements and convolutional neural networks trained on photographs of real-world images to uncover latent structure in children's drawings. These methodologies offer an opportunity to both improve and enhance the assessment of children's development through their drawings.
■590 ▼aSchool code: 0262.
■650 4▼aCognitive psychology
■650 4▼aDevelopmental psychology
■650 4▼aPsychology
■650 4▼aInformation science
■653 ▼aChild development
■653 ▼aChildren's drawings
■653 ▼aCognition
■653 ▼aConvolutional neural networks
■653 ▼aHuman figure drawing
■653 ▼aMachine vision
■690 ▼a0633
■690 ▼a0620
■690 ▼a0621
■690 ▼a0723
■71020▼aThe University of Wisconsin - Madison▼bPsychology.
■7730 ▼tDissertations Abstracts International▼g87-03A.
■790 ▼a0262
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359575▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


