基于BERTopic的新兴技术主题识别研究  

Research on Emerging Technology Topic Identification Based on BERTopic

作　　者：汪大锟 化柏林[1] WANG Dakun;HUA Bolin(Department of Information Management,Peking University,Beijing 100871)

机构地区：[1]北京大学信息管理系,北京100871

出　　处：《科技情报研究》2025年第1期131-140,共10页Scientific Information Research

基　　金：国家社会科学基金重大项目“大数据驱动的科技文献语义评价体系研究”(编号:21&ZD329)。

摘　　要：[目的/意义]识别并预见新兴技术,为企业和政府带来技术先发优势,及时把握技术发展趋势。[方法/过程]本研究采用BERTopic的主题建模方法获取领域主题分布,依据主题向量的余弦相似度合并论文和专利主题,实现新兴主题的识别。[结果/结论]运用BERTopic主题建模方法结合指标评价,能够实现新兴主题与新兴术语的有效识别。以新能源汽车领域为例开展实证研究,使用划分验证期和资料验证法2种方式进行验证,在识别出的16项主题中有12项通过验证,证实了本研究方法的有效性。[Purpose/significance]Identifying and foreseeing emerging technologies,bring technological first-mover advantages to enterprises and governments,and grasp technological development trends in a timely manner.[Method/process]This study uses BERTopic's topic modeling method to obtain domain topic distribution,and merges paper and patent topics based on the cosine similarity of topic vectors to identify emerging topics.[Result/conclusion]Using the BERTopic topic modeling method combined with index evaluation can effectively identify emerging topics and emerging terms.Taking the field of new energy vehicles as an example to carry out empirical research,using two methods:divided verification period and data verification method,12 of the 16 identified topics passed the verification,which verified the effectiveness of this research method.

关 键 词：新兴技术 主题识别 BERTopic 新能源汽车 

分 类 号：G353[文化科学—情报学] TP393[自动化与计算机技术—计算机应用技术]