Identifying the Nature of Interdisciplinary Research in Sci-tech Literature Based on Multi-label Classification
Wang Weijun,Ning Zhiyuan,Du Yi,Zhou Yuanchun
(Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China)
(University of Chinese Academy of Sciences, Beijing 100049, China)
[Objective] Recognize the interdisciplinary nature of research in sci-tech literature to provide support for uncovering issues on the interdisciplinary frontier.[Methods] The paper combines discipline labels of sci-tech literature provided by specialists with discipline labels predicted by text classification algorithms to jointly identify the nature of sci-tech literature interdisciplinary research. [Results] The F1 index for the method proposed in the paper for identifying interdisciplinary research sci-tech literature was increased from 0.23 to 0.45. [Limitations] The model in the paper performs poorly in identifying recall metrics for interdisciplinary sci-tech literature and should be explored further in future work. [Conclusions] The paper focuses on the data of misclassified sci-tech literature among different disciplines to determine the nature of interdisciplinary research in sci-tech literature, which is a research direction that deserves further attention.
王卫军, 宁致远, 杜一, 周园春.
基于多标签分类的科技文献学科交叉研究性质识别
[J]. 数据分析与知识发现, 10.11925/infotech.2096-3467.2022-0358.
Wang Weijun, Ning Zhiyuan, Du Yi, Zhou Yuanchun.
Identifying the Nature of Interdisciplinary Research in Sci-tech Literature Based on Multi-label Classification
. Data Analysis and Knowledge Discovery, 0, (): 1-.
