The Shape of Testimony: A Scalable Framework for Oral History Archive Comparison

Itamar Trainin, Renana Keydar, Amit Pinchevski

arXiv:2605.21623 · 2026-05-23 공개 · arXiv · PDF

topic-modeling discourse-segmentation llm-analysis corpus-comparison holocaust-studies narrative-analysis oral-history annotation-platforms

Abstract

Researchers in Holocaust studies have often distinguished between two styles of oral survivor testimony: the USC Shoah Foundation's interviews tend to follow a structured, interviewer-guided format, whereas the Yale Fortunoff Video Archive generally favors a more free-form, open-ended style. This distinction has influenced both scholarly research and the development of later archives. In this study, we critically examine that claim by conducting a large-scale computational analysis of more than 1,600 testimonies from both collections. Leveraging discourse segmentation, topic modeling, and large language model (LLM) based analysis, we quantify the "structuredness" level of testimonies through topic coherence, interviewer-survivor dynamics, and the distribution of question types. Our results generally corroborate the structural differences identified in earlier research, while also revealing significant overlaps between the collections, both within individual interviews and across common narrative patterns. This complicates the simple "structured vs. free-form" dichotomy often applied to these oral histories. Beyond revisiting a foundational claim in Holocaust studies, our work provides a scalable, replicable framework for comparative corpus analysis. As a proof of concept, it suggests broader applications for digital oral history, narrative analysis, and the design of citizen-science annotation platforms.

한국어 요약

📋 한 줄 요약

**[Digital Humanities / Oral History]** USC Shoah·Yale Fortunoff 1,600+ 증언 corpus를 discourse segmentation·topic modeling·LLM 분석으로 비교, "구조적 vs 자유 형식" 이분법의 통계 검증과 상당한 중첩 확인·확장 가능 corpus 분석 프레임워크 제안.

🎯 핵심 기여도

💡 핵심 아이디어

Oral history archive 비교는 학자적 인상이 아닌 대규모 computational corpus 분석으로 검증돼야 하며, discourse segmentation·topic modeling·LLM을 결합한 다축 정량화가 archive 간 구조적 차이와 중첩을 동시에 드러내 단순 이분법을 정교화한다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: Holocaust 연구의 foundational 주장 재검토, digital oral history·narrative 분석·시민 과학 annotation 플랫폼 설계의 확장 가능 방법론 제공, 정량 corpus 분석의 humanities 가치 입증. **한계**: 분석이 두 archive에 한정, 자동 분석의 미세 nuance 포착의 한계, 인터뷰어 변동·시대 차이 등 교란 요인 통제 어려움.

🚀 실용적 활용