共词分析识别研究热点的内容效度研究:基于自然语言处理

The Content Validity of Hot Research Issues Identified by Co-words Analysis:a Study based on the Natural Language Processing

文章应用自然语言处理的方法,基于选定领域的文献的题名、摘要、关键词和全文,识别了研究热点并对其内容效度进行了检验。研究发现:关键词在研究热点识别中内容效度较低,存在一定效度风险;从综合指标来看,基于题名、全文和摘要而识别的研究热点具有相对较高的内容效度;从单项指标(算法)来看,基于不同分析单元而识别研究热点的内容效度具有一定的不稳定性。

Present study conducted a Natural Language Processing procedure to test the content validity of the hot research issues identified by titles,abstracts,keywords and full text of academic papers.The findings include:Firstly,the hot research issues identified by keywords facing a high validity risks.Secondly,the content validity of hot research issues identified by titles are highest compared to other analysis unit from a comprehensive perspective.Thirdly,the hot research issues identified by various units are unstable from perspective of solo-index.