基于课表知识抽取的情报学课程设置启示研究

Research on Information Science Curricula Based on Curriculum Knowledge Extraction

情报学课程体系改革近年来逐渐成为研究的热点。在获取国外iSchool学校课程表的基础上,结合Bi-LSTM和BERT深度学习模型,构建课程名称的自动抽取模型,其中最优的BERT模型的调和平均值达到了92.92%。在该模型的基础上完成对所有课程名称的知识抽取,从而构建了相对全面和体系化的iSchool课程知识体系。在所抽取的知识基础上,从整体和类别的角度对国外iSchool课程的内容进行系统和深入的统计与分析;并在上述分析的基础上,对国内开设情报学相应的课程提供了切实可行的建议。

The reform of information science curricula has become a hot topic in recent years.Based on an acquired curriculum of foreign iSchools,an automatic extraction model for course names is constructed combining the deep learning model of Bi-LSTM and BERT;the best value of the F-measure of the BERT model reached 92.92%.The knowledge extraction of all course names was completed with the model,and a comprehensive and systematic iSchool curriculum knowledge system was constructed.On the basis of the extracted knowledge,this study systematically and deeply analyzed the course contents of iSchool from the perspective of hierarchy and region.Some practical suggestions are provided for the design of the corresponding courses of information science in China on the basis of the above analysis.