摘要
新文科建设对高等教育人才培养提出了厚植人文精神、培育文化自信、培养时代意识、赋予担当能力的要求.在新文科建设理念的要求下,课程知识图谱构建需要考虑实体定义标准多元化、实体间关系多样化、实体属性丰富化及知识抽取信息化的特点.以经济学课程为例,探索以新文科建设理念下课程知识体系特点为基础,对课程知识图谱的实体、属性和关系进行定义,利用爬虫技术构建语料库,基于TF-IDF算法、专家法和TOPS IS法相结合的综合评价法进行关键词提取和实体筛选,最终以Protégé为工具完成课程知识图谱的本体构建.
Abstract
The construction of new liberal arts puts forward requirements for cultivating humanistic spirit,nurturing cultural confidence,cultivating awareness of the times,and endowing with the ability to shoulder responsibilities in higher education.Under the requirements of the new liberal arts concept,the knowledge graph construction needs to consider the characteristics of diversified entity definition standards,diversified entity relationships,rich entity attributes,and knowledge extraction informationization.Taking the course"Economics"as an example,this study explores defining the entities,attributes,and relationships of the course knowledge graph based on the characteristics of the curriculum knowledge system under the new liberal arts construction concept.It utilizes web crawling technology to build a corpus,and employs a comprehensive evaluation method combining TF-IDF algorithm,expert method,and TOPSIS method for keyword extraction and entity screening.Finally,the ontology construction of the course knowledge graph is completed using Protégé.
维普
万方数据