基于多维指标的未来新兴科学研究前沿识别研究

Frontier Identification of Emerging ScientificResearch Based on Multi-indicators

当今世界范围内新一轮科技革命正在风起云涌,前瞻识别未来新兴科学研究前沿有助于科学布局未来必争研究领域。本文通过融合科技规划文本数据、基金项目数据和论文数据,综合运用自然语言处理技术、文本主题识别技术、复杂网络分析技术,提出了一种基于研究主题相似度、主题强度、主题新颖度等多维度指标的研究前沿识别方法。通过碳纳米管研究领域进行实证研究,结果表明该方法能够有效识别出该领域的热点研究前沿、新兴研究前沿、潜在研究前沿以及衰弱研究前沿。

A new trend of scientific and technological revolution is surging in the world today,and identifying the frontier of emerging scientific research in the future will help the scientific layout of the areas of future competition.Based on the integration of scientific and technological planning text data,fund project data,and paper data,using natural language processing technology,text theme recognition technology,and complex network analysis technology,this study proposes a research frontier discriminating model using multi-dimensional indexes,such as topic intensity and topic novelty.Empirical research has been conducted in the field of carbon nanotube research.The results demonstrate that the model can effectively identify the hotspot research frontier,emerging research frontier,potential research frontier,and weak research frontier.