口述历史档案数据故事化 语义描述与数据模型构建  

Semantic Description and Data Model for Data Storytelling Based on Oral Historical Archives

作　　者：孙翌[1] Sun Yi

机构地区：[1]上海交通大学图书馆

出　　处：《浙江档案》2024年第10期23-27,共5页Zhejiang Archives

基　　金：国家社会科学基金项目一般课题“数字人文视域下口述历史档案资源知识图谱构建及应用研究”(22BTQ083)研究成果之一。

摘　　要：本研究从数据化整理、故事化模型、语义化组织以及故事化生成等设计了数据故事化语义描述框架,划分数据故事的7个核心类、11个语义关系描述属性,可实现主题领域的知识图谱构建,并以数据模型为数据故事的自动生成提供了技术路径。以上海交通大学李政道图书馆中保存的李政道少年求学经历为主题的口述历史档案资料为研究对象,实例化验证了数据故事化语义描述与数据模型的可行性,能够较好地表示预测性数据分析故事的核心内容,支持数据故事化的自动生成目标。The memory data contained in them can be reorganized to enable the re creation of thematic stories,making the data more humane and machine understandable.This study designed a data storytelling semantic description framework from the perspectives of data organization,storytelling models,semantic organization,and storytelling generation.The framework divides data stories into 7 core classes and 11 semantic relationship description attributes,enabling the construction of knowledge graphs in thematic domains.The data model provides a technical path for the automatic generation of data stories.The T.D.Lee Library has a large collection of oral historical archives related to T.D.Lee.The study focuses on the oral historical archives of T.D.Lee's youth education experience,and the feasibility of data storytelling semantic description and data model is verified through instantiation.It can better represent the core content of predictive data analysis stories and support the automatic generation of data storytelling goals.

关 键 词：口述历史档案 数据故事化 语义描述 数据模型 李政道档案 

分 类 号：G273[文化科学—档案学]